Current Medical Imaging - Current Issue

Anemia is a common blood disorder caused by a low red blood cell count, reducing blood hemoglobin. It affects children, adolescents, and adults of all genders. Anemia diagnosis typically involves invasive procedures like peripheral blood smears and complete blood count (CBC) analysis. This study aims to develop a cost-effective, non-invasive tool for anemia detection using eye conjunctiva images.

Eye conjunctiva images were captured from 54 subjects using three imaging modalities such as a DSLR camera, a smartphone camera, and a smartphone camera fitted with a 3D-printed spacer macro lens. Image processing techniques, including You Only Look Once (YOLOv8) and the Segment Anything Model (SAM), and K-means clustering were used to analyze the image. By using an MLP classifier, the images were classified as anemic, moderately anemic, and normal. The trained model was embedded into an Android application with geotagging capabilities to map the prevalence of anemia in different regions.

Features extracted using SAM segmentation showed higher statistical significance (p < 0.05) compared to K-Means. Comparing high resolution (DSLR modality) and the proposed 3D-printed spacer macrolens shows statistically significant differences (p < 0.05). The classification accuracy was 98.3% for images from a 3D spacer-equipped smartphone camera, on par with the 98.8% accuracy obtained from DSLR camera-based images.

The mobile application, developed using images captured with a 3D spacer-equipped modality, provides portable, cost-effective, and user-friendly non-invasive anemia screening. By identifying anemic clusters, it assists healthcare workers in targeted interventions and supports global health initiatives like Sustainable Development Goal (SDG) 3.

This study explored a generative image synthesis method based on diffusion models, potentially providing a low-cost and high-efficiency training data augmentation strategy for medical artificial intelligence (AI) applications.

The MedMNIST v2 dataset was utilized as a small-volume training dataset under low-performance computing conditions. Based on the characteristics of existing samples, new medical images were synthesized using the proposed annotated diffusion model. In addition to observational assessment, quantitative evaluation was performed based on the gradient descent of the loss function during the generation process and the Fréchet Inception Distance (FID), using various loss functions and feature vector dimensions.

Compared to the original data, the proposed diffusion model successfully generated medical images of similar styles but with dramatically varied anatomic details. The model trained with the Huber loss function achieved a higher FID of 15.2 at a feature vector dimension of 2048, compared with the model trained with the L2 loss function, which achieved the best FID of 0.85 at a feature vector dimension of 64.

The use of the Huber loss enhanced model robustness, while FID values indicated acceptable similarity between generated and real images. Future work should explore the application of these models to more complex datasets and clinical scenarios.

This study demonstrated that diffusion model-based medical image synthesis is potentially applicable as an augmentation strategy for AI, particularly in situations where access to real clinical data is limited. Optimal training parameters were also proposed by evaluating the dimensionality of feature vectors in FID calculations and the complexity of loss functions.

In chronic liver disease (CLD) and liver cirrhosis (LC), assessing hepatic function and disease severity is crucial for patient management. This study aimed to evaluate the relationship between platelet-albumin-bilirubin (PALBI) grade and aspartate aminotransferase/platelet ratio index (APRI) with the functional liver imaging score (FLIS) and liver-to-kidney enhancement ratio (LKER) using gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced hepatobiliary phase (HBP) magnetic resonance imaging (MRI).

After applying exclusion criteria, 86 patients with CLD or LC who underwent Gd-EOB-DTPA-enhanced MRI between January 2018 and October 2023 were included. APRI and PALBI grades were calculated from laboratory data. FLIS was determined as the sum of three HBP imaging features (liver parenchymal enhancement, biliary excretion, and portal vein sign), with each scoring 0–2. LKER was calculated by dividing liver signal intensity by kidney intensity using region of interest (ROI) measurements. Spearman’s correlation was used to assess relationships between the variables.

APRI showed a weak negative correlation with both FLIS (r = –0.327, p = 0.02) and LKER (r = –0.308, p = 0.004). PALBI showed a moderate negative correlation with FLIS (r = –0.495, p = 0.001) and LKER (r = –0.554, p = 0.0001).

FLIS and LKER moderately correlated with PALBI and weakly with APRI. LKER may be a more practical tool due to its quantitative nature. Despite limitations, combining imaging and lab-based scores could enhance liver function assessment.

FLIS and LKER can validate, rather than predict or exclude, liver dysfunction in CLD and LC.

Pneumonia represents a dangerous respiratory illness that leads to severe health problems when proper diagnosis does not occur, followed by an increase in deaths, particularly among at-risk populations. Appropriate treatment requires the correct identification of pneumonia types in conjunction with swift and accurate diagnosis.

This paper presents the deep learning framework SqueezeViX-Net, specifically designed for pneumonia classification. The model benefits from a Self-Optimized Adaptive Enhancement (SOAE) method, which makes programmed changes to the dropout rate during the training process. The adaptive dropout adjustment mechanism leads to better model suitability and stability. The evaluation of SqueezeViX-Net is conducted through the analysis of extensive X-ray and CT image collections derived from publicly accessible Kaggle repositories.

SqueezeViX-Net outperformed various established deep learning architectures, including DenseNet-121, ResNet-152V2, and EfficientNet-B7, when evaluated in terms of performance. The model demonstrated better results, as it performed with higher accuracy levels, surpassing both precision and recall metrics, as well as the F1-score metric.

The validation process of this model was conducted using a range of pneumonia data sets, comprising both CT images and X-ray images, which demonstrated its ability to handle modality variations.

SqueezeViX-Net integrates SOAE technology to develop an advanced framework that enables the specific identification of pneumonia for clinical use. The model demonstrates excellent diagnostic potential for medical staff through its dynamic learning capabilities and high precision, contributing to improved patient treatment outcomes.

Accurate segmentation of lesion areas from Lugol's Iodine Staining images is crucial for screening pre-cancerous cervical lesions. However, in underdeveloped regions lacking skilled clinicians, this method may lead to misdiagnosis and missed diagnoses. In recent years, deep learning methods have been widely applied to assist in medical image segmentation.

This study aims to improve the accuracy of cervical cancer lesion segmentation by addressing the limitations of Convolutional Neural Networks (CNNs) and attention mechanisms in capturing global features and refining upsampling details.

This paper presents a Multi-Scale Bidirectional Lesion Enhancement Network, named MBLEformer, which employs the Swin Transformer encoder to extract image features at multiple stages and utilizes a multi-scale attention mechanism to capture semantic features from different perspectives. Additionally, a bidirectional lesion enhancement upsampling strategy is introduced to refine the edge details of lesion areas.

Experimental results demonstrate that the proposed model exhibits superior segmentation performance on a proprietary cervical cancer colposcopic dataset, outperforming other medical image segmentation methods, with a mean Intersection over Union (mIoU) of 82.5%, accuracy, and specificity of 94.9% and 83.6%.

MBLEformer significantly improves the accuracy of lesion segmentation in iodine-stained cervical cancer images, with the potential to enhance the efficiency and accuracy of pre-cancerous lesion diagnosis and help address the issue of imbalanced medical resources.

Medical imaging has undergone significant advancements with the integration of deep learning techniques, leading to enhanced accuracy in image analysis. These methods autonomously extract relevant features from medical images, thereby improving the detection and classification of various diseases. Among imaging modalities, Magnetic Resonance Imaging (MRI) is particularly valuable due to its high contrast resolution, which enables the differentiation of soft tissues, making it indispensable in the diagnosis of brain disorders. The accurate classification of brain tumors is crucial for diagnosing many neurological conditions. However, conventional classification techniques are often limited by high computational complexity and suboptimal accuracy. Motivated by these issues, an innovative model is proposed in this work for segmenting and classifying brain tumors. The research aims to develop a robust and efficient deep learning framework that can assist clinicians in making precise and early diagnoses, ultimately leading to more effective treatment planning. The proposed methodology begins with the acquisition of MRI images from standardized medical imaging databases.

Subsequently, the abnormal regions from the images are segmented using the Multiscale Bilateral Awareness Network (MBANet), which incorporates multi-scale operations to enhance feature representation and image quality. A novel classification architecture then processes the segmented images, termed Region Vision Transformer-based Adaptive EfficientNetB7 with Atrous Spatial Pyramid Pooling (RVAEB7-ASPP). To optimize the performance of the classification model, hyperparameters are fine-tuned using the Modified Random Parameter-based Hippopotamus Optimization Algorithm (MRP-HOA).

The model's effectiveness is verified through a comprehensive experimental evaluation that utilizes various performance metrics and is compared to current state-of-the-art methods. The proposed MRP-HOA-RVAEB7-ASPP model achieves an impressive classification accuracy of 98.2%, significantly outperforming conventional approaches in brain tumor classification tasks.

The MBANet effectively performs brain tumor segmentation, while the RVAEB7-ASPP model provides reliable classification. The integration of the MRP-HOA-RVAEB7-ASPP model optimizes feature extractions and parameter tuning, leading to improved accuracy and robustness.

The integration of advanced segmentation, adaptive feature extraction, and optimal parameter tuning enhances the reliability and accuracy of the model. This framework provides a more effective and trustworthy solution for the early detection and clinical assessment of brain tumors, leading to improved patient outcomes through timely intervention.

Thyroid ultrasound has emerged as a critical diagnostic modality, attracting substantial research attention. This bibliometric analysis systematically maps the 30-year evolution of thyroid ultrasound research to identify developmental trends, research hotspots, and emerging frontiers.

English-language articles and reviews (1994-2023) from Web of Science Core Collection were extracted. Bibliometric analysis was performed using VOSviewer and CiteSpace to examine collaborative networks among countries/institutions/authors, reference timeline visualization, and keyword burst detection.

A total of 8,489 documents were included for further analysis. An overall upward trend in research publications was found. China, the United States, and Italy were the productive countries, while the United States, Italy, and South Korea had the greatest influence. The journal Thyroid obtained the highest IF. The keywords with the greatest strength were “disorders”, “thyroid volume”, and “association guidelines”. The timeline view of reference demonstrated that deep learning, ultrasound-based risk stratification systems, and radiofrequency ablation were the latest reference clusters.

Three dominant themes emerged: the ultrasound characteristics of thyroid disorders, the application of new techniques, and the assessment of the risk of malignancy of thyroid nodules. Applications of deep learning and the development and improvement of correlation guides such as TI-RADS are the present focus of research.

The specific application efficacy and improvement of TI-RADS and the optimization of deep learning algorithms and their clinical applicability will be the focus of subsequent research.

Collagenous fibroma (CF), or desmoplastic fibroblastoma, is a rare benign tumor with few reported cases involving the facial region. Its presence in uncommon sites can pose diagnostic challenges due to overlapping clinical and radiologic features with malignant neoplasms.

Herein, we report a case of a 48-year-old female with CF in the juxtaforaminal premaxillary fat pad, presenting with neuralgic pain extending to the ipsilateral upper gingiva. The patient had a history of adenoid cystic carcinoma (AdCC) of the right nasolabial fold, which was treated surgically four years prior. During evaluation with a multimodal radiologic approach using ultrasonography, CT, and MRI, the lesion was revealed to be a soft tissue lesion in the premaxillary region, raising suspicion of recurrent AdCC. However, histopathologic examination of the surgical excision confirmed the diagnosis of CF.

This case highlights the importance of integrating clinical history, imaging findings, and pathological analysis for accurate diagnosis and appropriate management.

This study aims to evaluate the diagnostic value of extracellular volume fraction (ECV) and spectral CT parameters in assessing the pathological grading of lung invasive adenocarcinoma (IAC) presenting as solid or subsolid nodules.

A retrospective collection of patients who were pathologically confirmed as IAC with solid or subsolid pulmonary nodules at our hospital from March 2023 to November 2024 was conducted. Relevant data were recorded, and the patients were divided into two groups: intermediate/high differentiation and low differentiation. The parameters including arterial phase iodine concentration (ICA), arterial phase normalized iodine concentration (NICA), arterial phase normalized effective atomic number (nZeffA), arterial phase extracellular volume fraction (ECVA), venous phase iodine concentration (ICV), venous phase Normalized Iodine Concentration (NICV), venous phase normalized effective atomic number (nZeffV), and venous phase extracellular volume fraction (ECVV) were compared between the two groups. Parameters with statistical significance were evaluated for their diagnostic performance using Receiver Operating Characteristic (ROC) curves.

A total of 61 patients were included, comprising 40 in the intermediate to high differentiation group and 21 in the low differentiation group. The intermediate/high differentiation group had higher values of ECVA, NICA, ECVV, ICV, NICV, and nZeffV than the low differentiation group (P < 0.05). The AUC values for these parameters were 0.679, 0.620, 0.757, 0.688, 0.724 and 0.693 respectively. Among these, ECVV had the largest AUC, with a sensitivity and specificity of 72.5% and 71.4%, respectively. Through binary logistic regression analysis, five features were identified: the maximum diameter of the lesion, bronchus encapsulated air sign, lobulation sign, spiculation sign, and pleural traction sign. The integration of these imaging features with ECVV resulted in a model with enhanced diagnostic performance, characterized by an AUC of 0.886, a sensitivity of 85.7%, and a specificity of 80.0%.

ECVV outperforms other spectral parameters in differentiating IAC grades, reflecting changes in the tumor microenvironment. Combining ECVV with imaging features enhances diagnostic accuracy, though the study’s single-center design and small sample size limit generalizability.

Extracellular volume fraction can provide more information for the pathological grading assessment of invasive adenocarcinoma of the lung. Compared to other spectral parameters, ECVV exhibits the highest diagnostic performance, and its combination with conventional imaging features can further enhance diagnostic accuracy.

Knee osteoarthritis (KOA) is a degenerative joint disease commonly assessed using X-ray images based on the Kellgren-Lawrence (KL) criteria. Although the KL standard exists, its ambiguity often causes patients to misunderstand their condition, leading to overtreatment or delayed treatment and challenges in guiding precise surgical decisions. Moreover, the data-driven technology has been impeded by low resolution and feature distribution inconsistency of knee X-ray images. The imbalances between positive and negative samples further degrade detection accuracy.

The objective of this study was to develop a deep learning-based model, namely Task-aligned Path Aggregation Feature Fusion For Knee Osteoarthritis Detection (TPAFFKnee), to improve KOA detection accuracy by addressing limitations in traditional methods. Its more accurate detection could help in terms of proper treatment for patients and precision in surgery by physicians.

We proposed the TPAFFKnee model based on the EfficientNetB4 network, which introduced a path aggregation network for better feature extraction and replaced Fully Convolutional Network (FCN) with task-aligned detection as the head. Additionally, the loss function was improved by replacing the original loss function with Efficient Intersection over Union Loss (EIoU Loss) to address the imbalance between positive and negative samples.

The results showed that the model could accurately detect KOA categories and lesion locations based on the KL classification criteria, with a Mean Average Precision (mAP) of 93% on the Mendeley KOA dataset of 1650 knee osteoarthritis X-ray images from several hospitals. The mAP for the K2, K3, and K4 categories were 98.6%, 98.5%, and 99.6%, respectively. Compared with Faster R-CNN, SSD, RetinaNet, EfficientNetB4, and YOLOX, the proposed algorithm improved detection mAP by 14.3%, 12.4%, 15.3%, 22.7%, and 4.3%.

This study emphasizes the importance of the EfficientNetB4 network in KOA detection. The TPAFFKnee model provides an effective solution for improving the accuracy of KOA detection and offers a promising approach for standardized KL classification in medical applications. Future research can integrate more clinical data while improving the overall landscape of healthcare delivery through data-driven automation solutions.

It is not rare to experience a biochemical recurrence (BCR) following radical prostatectomy (RP) for prostate cancer (PCa). It has been reported that early detection and management of BCR following surgery could improve survival in PCa.

This study aimed to develop a nomogram integrating deep learning-based radiomic features and clinical parameters to predict 1-year BCR after RP and to examine the associations between radiomic scores and the tumor microenvironment (TME).

In this retrospective multicenter study, two independent cohorts of patients (n = 349) who underwent RP after multiparametric magnetic resonance imaging (mpMRI) between January 2015 and January 2022 were included in the analysis. Single-cell RNA sequencing data from four prospectively enrolled participants were used to investigate the radiomic score-related TME. The 3D U-Net was trained and optimized for prostate cancer segmentation using diffusion-weighted imaging, and radiomic features of the target lesion were extracted. Predictive nomograms were developed via multivariate Cox proportional hazard regression analysis. The nomograms were assessed for discrimination, calibration, and clinical usefulness.

In the development cohort, the clinical-radiomic nomogram had an AUC of 0.892 (95% confidence interval: 0.783--0.939), which was considerably greater than those of the radiomic signature and clinical model. The Hosmer–Lemeshow test demonstrated that the clinical-radiomic model performed well in both the development (P = 0.461) and validation (P = 0.722) cohorts.

Decision curve analysis revealed that the clinical-radiomic nomogram displayed better clinical predictive usefulness than the clinical or radiomic signature alone in both cohorts. Radiomic scores were associated with a significant difference in the TME pattern.

Our study demonstrated the feasibility of a DWI-based clinical-radiomic nomogram combined with deep learning for the prediction of 1-year BCR. The findings revealed that the radiomic score was associated with a distinctive tumor microenvironment.

This study aimed to assess the long-term volumetric and radiological effects of COVID-19 on lung anatomy. The severity of the disease was evaluated using radiological scoring, and lung volume measurements were performed via 3D Slicer software.

A retrospective analysis was conducted on a total of 127 patients diagnosed with COVID-19 between April 2020 and December 2023. Initial and follow-up chest CT scans were reviewed to analyze lung volumes and radiological findings. Lung lobes were segmented using 3D Slicer software to measure volumes. Severity scores were assigned based on the Chung system, and statistical methods, including logistic regression and Wilcoxon signed-rank tests, were used to analyze outcomes.

Follow-up CT scans showed significant improvements in lung volumes and severity scores. The left lung total volume increased significantly (p = 0.038), while right lung total volume and COVID-19-affected lung volumes demonstrated non-significant improvements. Severity scores and the number of affected lobes decreased significantly (p 0.05). Correlation analyses revealed that age negatively influenced lung volume recovery (r = -0.177, p = 0.047). Persistent pathological findings, such as interstitial thickening and fibrotic bands, were observed.

COVID-19 induces lasting changes in lung structure, particularly in elderly and severely affected patients. Long-term follow-up and the consideration of antifibrotic therapies are essential to manage post-COVID-19 complications effectively. A multidisciplinary approach is recommended to support patient recovery and minimize healthcare burdens.

Predicting the recurrence risk of NMIBC after TURBT is crucial for individualized clinical treatment.

The objective of this study is to evaluate the ability of radiomic feature analysis of intratumoral and peritumoral regions based on computed tomography (CT) imaging to predict recurrence in non-muscle-invasive bladder cancer (NMIBC) patients who underwent transurethral resection of bladder tumor (TURBT).

A total of 233 patients with NMIBC who underwent TURBT were retrospectively analyzed. Within the intratumoral and peritumoral regions of the venous phase images, 1316 radiomics features were extracted. Feature selection was used to identify a set of top recurrence-associated features within the training cohort. Three models were constructed to predict recurrence for a given patient using Random Forest (RF): Model 1 was based on the radiomics features set from the intratumoral region, Model 2 was based on a combination of intratumoral and peritumoral regions, and Model 3 combined the radiomics features from Model 2 and clinical factors. The three models were then independently tested on internal and external cohorts, and their performance was evaluated. We also employed the bootstrap method on the internal cohort to further validate the performance of the model.

Combining intratumoral and peritumoral regions, Model 2 yielded a higher area under the receiver operator characteristic curves (AUC) than Model 1, with 0.826 AUCs of the training cohort. After adding clinical factors, the predictive performance of Model 3 for postoperative recurrence of NMIBC was further improved, and the AUCs of the training, internal, and external validation cohorts of Model 3 were 0.860 (95% CI: 0.829-0.954), 0.829 (0.812-0.863), and 0.805 (0.652-0.840), respectively (all p>0.05). The bootstrap value of Model 3 on the internal cohort was 0.852. Model 3 stratified patients into high- and low-risk groups with significantly different recurrence-free survival (RFS) (p<0.001).

Radiomic features derived from intratumoral regions can predict the 2-year recurrence risk following TURBT in patients with NMIBC. The predictive performance is further enhanced when combined with radiomic features from peritumoral regions and clinical risk factors.

Image enhancement of the Hypoxic-Ischemic Encephalopathy (HIE) lesion region in neonatal brain MR images is a challenging task due to the diffuse (i.e., multi-focal) nature, small size, and low contrast of the lesions. Classifying the stages of HIE is also difficult because of the unclear boundaries and edges of the lesions, which are dispersed throughout the brain. Moreover, unclear boundaries and edges are due to chemical shifts, partial volume artifacts, and motion artifacts. Further, voxels may reflect signals from adjacent tissues. Existing algorithms perform poorly in HIE lesion enhancement due to artifacts, voxels, and the diffuse nature of the lesion.

In this paper, we propose a Rough Neural Network and Anti-Homomorphic Filter (RNN-AHF) framework for the enhancement of the HIE lesion region.

The RNN-AHF framework reduces the pixel dimensionality of the feature space, eliminates unnecessary pixels, and preserves essential pixels for lesion enhancement.

The RNN efficiently learns and identifies pixel patterns and facilitates adaptive enhancement based on different weights in the neural network. The proposed RNN-AHF framework operates using optimized neural weights and an optimized training function. The hybridization of optimized weights and the training function enhances the lesion region with high contrast while preserving the boundaries and edges.

The proposed RNN-AHF framework achieves a lesion image enhancement and classification accuracy of approximately 93.5%, which is better than traditional algorithms.

This study aims to evaluate the potential of Dual-Energy Computed Tomography (DECT)-based radiomics in preoperative risk stratification for the prediction of initial recurrence in Papillary Thyroid Carcinoma (PTC).

The retrospective analysis included 236 PTC cases (165 in the training cohort, 71 in the validation cohort) collected between July 2020 and June 2021. Tumor segmentation was carried out in both intratumoral and peritumoral areas (1 mm inner and outer to the tumor boundary). Three region-specific rad-scores were developed (rad-score [VOI^whole], rad-score [VOI^{outer layer}], and rad-score [VOI^{inner layer}]), respectively. Three radiomics models incorporating these rad-scores and additional risk factors were compared to a clinical model alone. The optimal radiomics model was presented as a nomogram.

Rad-scores from peritumoral regions (VOI^{outer layer} and VOI^{inner layer}) outperformed the intratumoral rad-score (VOI^whole). All radiomics models surpassed the clinical model, with peritumoral-based models (radiomics models 2 and 3) outperforming the intratumoral-based model (radiomics model 1). The top-performing nomogram, which included tumor size, tumor site, and rad-score (VOI^{inner layer}), achieved an Area Under the Curve (AUC) of 0.877 in the training cohort and 0.876 in the validation cohort. The nomogram demonstrated good calibration, clinical utility, and stability.

DECT-based intratumoral and peritumoral radiomics advance PTC initial recurrence risk prediction, providing clinical radiology with precise predictive tools. Further work is needed to refine the model and enhance its clinical application.

Radiomics analysis of DECT, particularly in peritumoral regions, offers valuable predictive information for assessing the risk of initial recurrence in PTC.

Early-stage Brain tumor detection is critical for timely diagnosis and effective treatment. We propose a hybrid deep learning method, Convolutional Neural Network (CNN) integrated with YOLO (You Only Look once) and SAM (Segment Anything Model) for diagnosing tumors.

A novel hybrid deep learning framework combining a CNN with YOLOv11 for real-time object detection and the SAM for precise segmentation. Enhancing the CNN backbone with deeper convolutional layers to enable robust feature extraction, while YOLOv11 localizes tumor regions, SAM is used to refine the tumor boundaries through detailed mask generation.

A dataset of 896 MRI brain images is used for training, testing, and validating the model, including images of both tumors and healthy brains. Additionally, CNN-based YOLO+SAM methods were utilized successfully to segment and diagnose brain tumors.

Our suggested model achieves good performance of Precision as 94.2%, Recall as 95.6% and mAP50(B) score as 96.5% demonstrating and highlighting the effectiveness of the proposed approach for early-stage brain tumor diagnosis

The validation is demonstrated through a comprehensive ablation study. The robustness of the system makes it more suitable for clinical deployment.

This study aims to propose and evaluate a two-stage semi-supervised segmentation framework with dual multiscale uncertainty estimation and graph reasoning, addressing the challenges of obtaining high-precision pixel-level labels and effectively utilizing unlabeled data for accurate pneumonia lesion segmentation.

First, we design a guided supervised training strategy for modeling aleatoric uncertainty (AU) at dual scales, reducing the impact on segmentation performance caused by aleatoric uncertainties introduced by blurred lesions and their boundaries in the image. Second, we design a training strategy for multi-scale noisy pseudo-label correction to reduce the cognitive bias problem caused by unreliable predictions in the model. Finally, we design a new combination of fused feature interaction graph reasoning (FIGR) and attention modules, which enables the network model to better capture image features in small infected regions.

Our study was validated using the MosMedData public dataset. The proposed algorithm improves the performance by 1.25%, 1.03%, 2.98%, and 0.59% on Dice, Jaccard, normalized surface dice (NSD), and average distance of boundaries (ADB), respectively, compared to the baseline model.

Our semi-supervised pneumonia segmentation framework, through two-stage multi-scale uncertainty estimation and modeling, significantly improves segmentation performance by leveraging unlabeled data and addressing uncertainties, offering clinical benefits in pneumonia diagnosis while facing challenges in generalization and computational efficiency that future work will target with GAN-based data synthesis and architecture optimization.

It can be convincingly concluded that the proposed algorithm is of profound importance and value in the domain of clinical practice.

This meta-analysis aimed to evaluate the diagnostic performance of Machine Learning (ML) models for early prediction of bronchopulmonary dysplasia (BPD) in preterm infants, addressing the need for timely risk stratification.

Systematic searches of PubMed, Embase, and other databases identified 9 eligible studies (12,755 infants). Data were extracted and pooled using bivariate generalized linear mixed models. Study quality was assessed via QUADAS-2.

ML models demonstrated high accuracy (pooled sensitivity: 0.81, specificity: 0.85, AUC: 0.90). Multimodal models and ensemble algorithms (e.g., Random Forest) outperformed single-modality approaches. Models using data from the first 7 postnatal days achieved superior performance compared to those using data from day 28.

ML enables ultra-early BPD prediction, preceding conventional diagnosis by weeks. Heterogeneity in data modalities and validation strategies highlights the need for standardized reporting.

ML-based BPD prediction shows promise for clinical translation but requires prospective validation and cost-effectiveness analysis.

The noise emergence in the digital image can occur throughout image acquisition, transmission, and processing steps. Consequently, eliminating the noise from the digital image is required before further processing. This study aims to denoise noisy images (including Magnetic Resonance Images (MRIs)) by employing our proposed image denoising approach.

This proposed approach is based on the Stationary Wavelet Transform (SWT 2-D) and the 2 - D Dual-Tree Discrete Wavelet Transform (DWT). The first step of this approach consists of applying the 2 - D Dual-Tree DWT to the noisy image to obtain noisy wavelet coefficients. The second step of this approach consists of denoising each of these coefficients by applying an SWT 2-D based denoising technique. The denoised image is finally obtained by applying the inverse of the 2-D Dual-Tree DWT to the denoised coefficients obtained in the second step. The proposed image denoising approach is evaluated by comparing it to four denoising techniques existing in literature. The latters are the image denoising technique based on thresholding in the SWT-2D domain, the image denoising technique based on deep neural network, the image denoising technique based on soft thresholding in the domain of 2-D Dual-Tree DWT, and Non-local Means Filter.

The proposed denoising approach, and the other four techniques previously mentioned, are applied to a number of noisy grey scale images and noisy Magnetic Resonance Images (MRIs) and the obtained results are in terms of PSNR (Peak Signal to Noise Ratio), SSIM (Structural Similarity), NMSE (Normalized Mean Square Error) and Feature Similarity (FSIM). These results show that the proposed image denoising approach outperforms the other denoising techniques applied for our evaluation.

In comparison with the four denoising techniques applied for our evaluation, the proposed approach permits to obtain highest values of PSNR, SSIM and FSIM and the lowest values of NMSE. Moreover, in cases where the noise level σ = 10 or σ = 20, this approach permits the elimination of the noise from the noisy images and introduces slight distortions on the details of the original images. However, in case where σ = 30 or σ = 40, this approach eliminates a great part of the noise and introduces some distortions on the original images.

The performance of this approach is proven by comparing it to four image denoising techniques existing in literature. These techniques are the denoising technique based on thresholding in the SWT-2D domain, the image denoising technique based on a deep neural network, the image denoising technique based on soft thresholding in the domain of 2 - D Dual-Tree DWT and the Non-local Means Filter. All these denoising techniques, including our approach, are applied to a number of noisy grey scale images and noisy MRIs, and the obtained results are in terms of PSNR (Peak Signal to Noise Ratio), SSIM(Structural Similarity), NMSE (Normalized Mean Square Error) and FSIM (Feature Similarity). These results show that this proposed approach outperforms the four denoising techniques applied for our evaluation.

This study aimed to compare the consistency between smart pelvic floor ultrasound and biplanar transrectal ultrasound in detecting early stress urinary incontinence (SUI) by assessing urethral dilation and bladder structure.

We selected 40 multiparas who went through prenatal assessment after delivery and had standard pelvic floor ultrasounds at 6 weeks after childbirth, spanning from June 2022 to September 2022. The Bland-Altman method was employed to evaluate the consistency between biplanar transrectal ultrasound and transperineal pelvic floor ultrasound in assessing the mobility of the bladder neck and the posterior bladder wall in women.

Biplanar transrectal ultrasound and transperineal pelvic floor ultrasound demonstrated strong consistency in evaluating bladder neck and posterior bladder wall mobility in women (P>0.05). The analysis of each pelvic floor observation index using Bland-Altman plots indicated that approximately 97.5% of data points fell within the 95% consistency limit.

Our findings suggest that biplanar transrectal ultrasound is a reliable supplementary method to transperineal pelvic floor ultrasound for diagnosing SUI.

Driven by environmental pollution and the rise in infectious diseases, the increasing prevalence of lung conditions demands advancements in diagnostic techniques.

This study explores the use of various features, such as spectrograms, chromograms, and Mel Frequency Cepstral Coefficients (MFCC), to extract crucial information from auscultation recordings. It addresses challenges through filter-based audio enhancement methods. The primary goal is to improve disease detection accuracy by leveraging convolutional neural networks (CNNs) for feature extraction and dense neural networks for classification.

While deep learning models like CNNs and Recurrent Neural Network (RNN) outperform traditional machine learning models such as Sequence Vector Machine, K-Nearest Neighbours (KNN) and random forest with accuracies ranging from 70% to 85%. The combination of CNN, RNN, and long short-term memory achieved an accuracy of 88%. By integrating MFCC, Chroma Short-Term Fourier Transform (STFT), and spectrogram features with a CNN-based classifier, the proposed multi-feature deep learning model achieved the highest accuracy of 92%, surpassing all other methods.

The study effectively addresses key issues, including the overrepresentation of Chronic Obstructive Pulmonary Disease (COPD) samples over Lower Respiratory Tract Infections (LRTI) and Upper Respiratory Tract Infections (URTI) which hampers generalization across test audio samples.

The proposed methodology caters common challenges like background noise in recordings, and the limited and imbalanced nature of datasets. These findings pave the way for enhanced clinical applications, showcasing the transformative potential of multi-feature deep learning methods in the classification of pulmonary diseases.

This cross-sectional study aimed to evaluate the relationship between presternal adipose tissue thickness and the pericardial adipose tissue volume in relation to coronary artery disease.

A total of 108 patients who underwent coronary computed tomography angiography (CCTA) for suspected coronary disease between 2019 and 2022 were evaluated. Patients whose epicardial adipose tissue could not be optimally measured due to imaging artifacts, those with a pre-existing coronary artery anomaly or known heart disease, individuals under 18 years of age, and those who had undergone sternotomy and bypass surgery were excluded from the study. Accordingly, 95 patients (61 males and 34 females) who met the inclusion criteria and did not meet any of the exclusion criteria were included in the study. CCTA images were analyzed retrospectively. Pericardial adipose tissue volume was measured automatically using Syngo Via software. Presternal fat thickness (PFTT) was measured at the level of the pulmonary artery bifurcation, from the anterior to the posterior surface.

The study sample comprised 64.2% males and 35.7% females. The median thickness of the presternal fat tissue was found to be 11.5 mm, with a range of 3 to 44 mm. The median PFTT was measured at 9 mm (3−23 mm) in the male patient group, while in the female patient group, it was 20 mm (10−44 mm). The median epicardial fat volume (EFV) for the full sample was 83.1 ml (22.3−171 ml), measuring 81.1 ml (37−171 ml) and 79.5 ml (22.3−167 ml) in males and females, respectively. A significant correlation was observed between PFTT and EFV in the full sample (Rho = 0.236, p = 0.02), as well as among male patients (Rho = 0.409, p = 0.001), but not in the female patient group (Rho = 0.264, p = 0.131). In the male cohort, there was no significant difference between EFV and PFTT, and the presence of coronary plaque.

This study examines the relationship between presternal adipose tissue thickness (PFTT) and coronary artery disease (CAD), building on previous evidence that links epicardial adipose tissue (EAT) to cardiovascular risk. We found a significant correlation between PFTT and epicardial fat volume (EFV) in male patients, but not in females, which is likely due to hormonal influences and variability in breast tissue. Importantly, measurement of PFTT provides a practical, non-invasive method for assessing CAD risk in clinical settings. Although our small sample size limits the generalisability of our findings, these results suggest that PFTT may serve as an indirect marker of CAD risk and highlight the need for further research with larger cohorts to validate its clinical relevance. Incorporating PFTT assessment into routine practice may improve the early identification of high-risk patients and enhance strategies for preventing ischemic heart disease.

The study reveals that increased presternal fat thickness correlates with elevated epicardial fat volume, indicating that presternal fat measurements could serve as a simple and effective tool for assessing the risk of coronary artery disease, particularly in male patients.

Hematemesis is a rare manifestation of a bronchial artery aneurysm (BAA), as bleeding from a ruptured BAA typically occurs into the bronchial tree, leading to hemoptysis rather than gastrointestinal bleeding.

A 71-year-old male presented to the emergency department with syncope and hematemesis. Computed tomography angiography (CTA) revealed a ruptured bronchial artery aneurysm in the posterior mediastinum, with contrast extravasation into the lower esophagus. The patient underwent transcatheter arterial embolization (TAE) using coils, a mixture of N-butyl cyanoacrylate and ethiodized oil. However, due to persistent bleeding signs and recanalization observed on follow-up CTA, a second TAE was performed the following day using the same technique. Hemostasis was achieved, and the patient recovered well, being discharged on the 16^th day without complications.

Ruptured BAA presenting as hematemesis is extremely rare, making it difficult to diagnose. Prompt diagnosis with CTA and timely intervention, such as TAE, can be important in achieving favorable outcomes and preventing life-threatening complications.

Finding a convenient, accurate, and non-invasive method to differentiate between benign and malignant breast masses is especially important for clinical practice, and this study aimed to explore the clinical value of Nomogram model based on multimodality ultrasound image characteristics and clinical baseline data for detecting benign and malignant breast masses.

A retrospective analysis of the clinical data and ultrasound imaging characteristics of 132 patients with breast masses. Data were randomly divided into a training set (92 cases) and a validation set (40 cases) in a ratio of 7:3. Logistic regression was applied to the training set data to analyze risk factors related to malignant breast masses and to construct a Nomogram model. Clinical applicability of the model was evaluated and validated.

In training set, ROC cure analysis results showed that AUC of Nomogram model constructed with CA15-3, CA125, Emax, Esd, Ratio of Elastic Moduli, Elasticity Scoring, blurry boundaries, irregular shape, penetrating vessels, and stiff rim sign was 1.00 (95%CI: 0.99-1.00), Hosmer-Lemeshow goodness-of-fit test result showed predicted curve closely aligns with ideal curve, and DCA showed that Nomogram model exhibited high net benefits across multiple thresholds. The clinical applicability of the Nomogram model was also confirmed with consistent results in the validation set.

In this study, we constructed a Nomogram model using risk factors associated with malignant breast masses, and the model showed good clinical applicability in distinguishing benign and malignant breast masses. However, this study is a single-center study, and the sample size of the dataset is relatively small, which, to some extent, limits the breadth and depth of validation.

The Nomogram model built on multimodal ultrasound imaging features and clinical data demonstrates a strong discriminative ability for malignant breast masses, allowing patients to achieve a significant net benefit.

Brachial plexopathy is a diagnostically challenging condition that requires a comprehensive evaluation, including physical examination, imaging, and Electrodiagnostic (EDx).testing. Ultrasound guidance may improve the efficiency and precision of nerve conduction studies by addressing the limitations of blind techniques, such as discomfort and inaccurate localization.

We prospectively enrolled 30 patients undergoing electrodiagnostic testing. The left upper limb was examined with ultrasound guidance (Group A), while the right upper limb underwent the blind method (Group B). The examined nerves included the median, ulnar, radial, medial and lateral antebrachial cutaneous, axillary, musculocutaneous, suprascapular, and long thoracic nerves. Stimulation duration, number of stimulation attempts, average current, and total examination time were recorded. The differences in data between the two groups were compared and analyzed.

Group A demonstrated significantly lower stimulation duration (156.70±50.13 vs. 260.17±53.19 s), fewer stimulation attempts (17.73±3.94 vs. 25.80±5.23), and lower average current [32.45 (30.28, 40.13) vs. 42.75 (37.78,50.68) mA] compared to Group B (all P 0.001). No significant difference was observed in total examination time (387.40 ± 33.72 vs. 372.00 ± 47.01 s; P = 0.150).

Ultrasound guidance improves procedural precision and reduces the need for repeated stimulations and higher electrical intensities. These benefits are achieved without extending the total examination time, making it a feasible and patient-friendly approach for routine use in clinical neurophysiology.

Ultrasound-guided nerve conduction studies of the brachial plexus enhance procedural efficiency and patient comfort compared to the blind method. Further large-scale studies are recommended to validate these findings and assess broader clinical applications.

An accurate staging diagnosis of rectal cancer holds crucial importance in determining the appropriate treatment plan for patients.

To evaluate the application of transrectal biplane ultrasonography combined with Sound Touch Elastography (STE) technology in preoperative uT stage of rectal cancer.

A retrospective analysis was conducted on the ultrasonographic data of 32 patients. The STE values within the tumor and the adjacent peritumoral fat tissue were recorded, and the ratio of STE values between adjacent and distant peritumoral fat tissues was defined as the Stiffness Ratio (SR).

The STE values were not statistically significantly different between the high and low pT stage groups within tumors (P > 0.05). However, there were statistically significant differences in the STE values of the adjacent peritumoral fat tissue and the SR between the two groups (P < 0.05). Binary logistic regression analysis showed that the SR was a relevant factor in distinguishing high and low pT stages of rectal cancer. The optimal cut-off value of the SR was 1.915, with a sensitivity of 95.7% and a specificity of 88.9% in predicting high pT stages of rectal cancer. The consistency observed between traditional TRUS and pathological staging in differentiating between high and low pT stages of rectal cancer was moderate. However, the incorporation of SR had enhanced this consistency to a favorable level.

The combination of TRUS and STE technology enhanced the accuracy of pT stage in rectal cancer, with SR serving as a critical indicator for predicting high pT stages and constituting a valuable supplement to traditional TRUS.

Detecting Pulmonary Embolism (PE) is critical for effective patient care, and Artificial Intelligence (AI) has shown promise in supporting radiologists in this task. Integrating AI into radiology workflows requires not only evaluation of its diagnostic accuracy but also assessment of its acceptance among clinical staff.

This study aims to evaluate the performance of an AI algorithm in detecting pulmonary embolisms (PEs) on contrast-enhanced computed tomography pulmonary angiograms (CTPAs) and to assess the level of acceptance of the algorithm among radiology department staff.

This retrospective study analyzed anonymized computed tomography pulmonary angiography (CTPA) data from a university clinic. Surveys were conducted at three and nine months after the implementation of a commercially available AI algorithm designed to flag CTPA scans with suspected PE. A thoracic radiologist and a cardiac radiologist served as the reference standard for evaluating the performance of the algorithm. The AI analyzed 59 CTPA cases during the initial evaluation and 46 cases in the follow-up assessment.

In the first evaluation, the AI algorithm demonstrated a sensitivity of 84.6% and a specificity of 94.3%. By the second evaluation, its performance had improved, achieving a sensitivity of 90.9% and a specificity of 96.7%. Radiologists’ acceptance of the AI tool increased over time. Nevertheless, despite this growing acceptance, many radiologists expressed a preference for hiring an additional physician over adopting the AI solution if the costs were comparable.

Our study demonstrated high sensitivity and specificity of the AI algorithm, with improved performance over time and a reduced rate of unanalyzed scans. These improvements likely reflect both algorithmic refinement and better data integration. Departmental feedback indicated growing user confidence and trust in the tool. However, many radiologists continued to prefer the addition of a resident over reliance on the algorithm. Overall, the AI showed promise as a supportive “second-look” tool in emergency radiology settings.

The AI algorithm demonstrated diagnostic performance comparable to that reported in similar studies for detecting PE on CTPA, with both sensitivity and specificity showing improvement over time. Radiologists’ acceptance of the algorithm increased throughout the study period, underscoring its potential as a complementary tool to physician expertise in clinical practice.

Ultrasound has been used in the field of clinical nutrition to measure body composition. However, the consistency of these measurements varies across studies, and the impact of examination posture remains largely unexplored, creating a critical methodological gap in clinical practice. The purpose of this study was to investigate the consistency of ultrasonic measurement of fat thickness (FT) and evaluate the impact of posture on these measurements.

FT was measured at 10 body sites in routine and special postures using ultrasound to determine intra-observer and inter-observer consistency and to assess the impact of different postures on FT measurements. Body fat mass (BFM) was measured by bioelectrical impedance analysis (BIA), and subcutaneous skinfold thickness was measured with calipers for correlation analysis.

Results revealed significant sex differences in BFM (P<0.05) and FT at most sites (P<0.001), with women exhibiting thicker fat measurements. High intra-observer and inter-observer consistency was demonstrated in special examination postures (intraclass correlation coefficients were both ≥0.925). Posterior upper arm FT measured in the sitting posture was greater than that measured in the prone posture (P<0.001) while there was no significant difference in subscapular FT between the two postures (P = 0.289).

There were significant differences in posterior lower leg FT among the four postures (P<0.001). Positive correlations were observed between FT and skinfold at site 5 (abdominal subcutaneous fat), site 7 (posterior upper arm), and site 8 (subscapular) (r = 0.921, 0.878, 0.882, P<0.01).

Ultrasound measurements of FT have proven reliable, offering advantages in cost, ease, accuracy, and scalability. The findings highlight the importance of posture in ultrasound measurement of FT, which may influence clinical practice and research protocols. The limitations of the study mainly lie in the narrow age and BMI ranges of the sample, which restrict the generalizability of the research findings.

This study provides a comprehensive evidence base for posture-specific ultrasound protocols in fat thickness measurement. Our results demonstrate that ultrasound is a reliable method for measuring fat thickness, exhibiting good to excellent inter-observer and intra-observer consistency. The impact of body posture on fat thickness measurements varies by anatomical location. Strong correlations were found between ultrasound measurements and skinfold thickness at subcutaneous sites, confirming the validity of ultrasound for fat thickness assessment.

The aim of this study was to evaluate the correlation between ultrasonography, magnetic resonance imaging, and pathology with Fibrolipomatous Hamartoma (FLH) of the peripheral nerve.

Sixteen patients who underwent surgical treatment for FLH of the peripheral nerve were included in the study. Ultrasound examination and Magnetic Resonance Imaging (MRI) were used to display the detailed anatomical structure of the region well enough to detect FLH. The features presented based on the results of ultrasound examination and magnetic resonance imaging were recorded.

The involved peripheral nerve showed expansive growth in ultrasonography and MRI. The hyperechoic fat tissue and hypoechoic nerve fibers alternated with one another. In ultrasonography and MRI, the peripheral nerve exhibited a lotus-like appearance in the transverse plane, and a cable-like appearance in the longitudinal plane, while there was no blood flow signal in the nerve.

The imaging features of FLH, including the characteristic lotus-like and cable-like appearances, align closely with pathological findings, underscoring the diagnostic value of ultrasonography and MRI. These non-invasive techniques facilitate differentiation from other peripheral nerve pathologies, such as carpal tunnel syndrome or hemangioma. Limitations include the retrospective design, small MRI subgroup, and lack of long-term follow-up. Future multicenter studies with larger cohorts are recommended to validate these findings.

Ultrasonography and MRI may be valuable in the diagnosis of FLH of the peripheral nerve.

This study aimed to explore the relationship between radiomics features and anaplastic lymphoma kinase (ALK) gene mutation status in lung adenocarcinoma and to develop a radiomics nomogram for preoperative prediction of ALK mutations.

A retrospective analysis was conducted on 210 patients with histologically confirmed lung adenocarcinoma (50 ALK mutation-positive, 160 mutation-negative), divided into training (n=147) and validation (n=63) cohorts (7:3 ratio). Preoperative enhanced CT images were analyzed using ITK-SNAP for region-of-interest delineation, and radiomics features were extracted via A.K. software. The least absolute shrinkage and selection operator algorithm selected features to generate a radiomics score. Multivariate logistic regression identified independent risk factors, and a radiomics nomogram combining clinical features and radiomics signatures was developed. Model performance was evaluated using AUC in both training and validation sets.

Nineteen radiomics features were selected to construct the radiomics signature. The signature achieved an AUC of 0.89 (95% CI: 0.84–0.95) in the training set and 0.79 (95% CI: 0.63–0.95) in the validation set. The radiomics nomogram demonstrated superior performance (AUC=0.80, 95% CI: 0.63–0.97) compared to the clinical model alone (AUC=0.66, 95% CI: 0.47–0.85) in the validation set. While the nomogram showed no statistically significant improvement over the radiomics signature alone (P>0.05), it outperformed the clinical model significantly (P<0.001 in training; P=0.0337 in validation).

The radiomics nomogram integrating clinical and radiomics data demonstrated robust predictive capability for ALK mutations, highlighting the potential of non-invasive CT-based radiomics in guiding personalized treatment. However, the lack of significant difference between the nomogram and radiomics signature alone suggests limited incremental value from clinical variables in this cohort. Limitations include the retrospective design, single-center data, and class imbalance (fewer ALK-positive cases), which may affect generalizability. External validation is warranted to confirm clinical utility.

The CT-derived radiomics signature and nomogram show promise for preoperative ALK mutation prediction in lung adenocarcinoma. These tools could enhance clinical decision-making by identifying candidates for targeted therapies, though further validation is needed to optimize their application in diverse populations.

This case study aimed to report the rare computed tomography (CT) features of advanced pericochlear otosclerosis, with an emphasis on a proposed new nomenclature to describe the imaging findings.

A 70-year-old woman with recurrent rhinosinusitis presented to our center for clinical management. The CT scan revealed the incidental rare findings of advanced retrofenestral otosclerosis in the form of extensive symmetrical pericochlear tubular lucencies in bilateral otic capsules. We coined the new term “C-hoop earring” sign for this CT appearance. She was asymptomatic and declined further audiological or imaging evaluation.

Herein, the CT features of advanced pericochlear otosclerosis are described and the imaging and clinical connotations of the presence of the C-hoop earring sign are reviewed. This new terminology provides a more intuitive description of the imaging findings in the temporal bones for clearer understanding and communication in clinical radiological practice and education.

Leptomeningeal metastasis (LM) is a severe complication of solid malignancies, including lung adenocarcinoma, characterized by poor prognosis and diagnostic challenges. This study assesses whether curvilinear peri-brainstem hyperintense signals on MRI are a characteristic feature of LM in lung adenocarcinoma patients.

This retrospective study analyzed data from multiple centers, encompassing lung adenocarcinoma patients with peri-brainstem curvilinear hyperintense signals on MRI between January 2016 and March 2022. Clinical and radiological data were reviewed, and diagnostic and survival outcomes were analyzed.

Eleven patients (45-76 years; 6 males and 5 females) were included. The mean interval from lung adenocarcinoma diagnosis to detection of brainstem signal was 1.59 years. Four patients had elevated carcinoembryonic antigen levels, and 6 showed systemic metastases. MRI revealed curvilinear hyperintense signals along the pons, medulla, and cerebral peduncles on T2-Weighted Imaging (T2WI), Fluid-Attenuated Inversion Recovery (FLAIR), and Diffusion-Weighted Imaging (DWI). Mild linear enhancement was observed in 4 of 6 patients undergoing contrast-enhanced MRI, and tumor cells were detected in 4 of 6 Cerebrospinal Fluid (CSF) samples. The mean survival time in 7 patients with follow-up data was 3.42 months. Two patients exhibited peri-brainstem calcifications on CT 4–6 months after MRI and died shortly after.

These findings suggest that peri-brainstem curvilinear hyperintense signals and mild linear enhancement may serve as radiological markers of LM in lung adenocarcinoma. This pattern may reflect tumor infiltration or secondary changes in the leptomeninges.

Peri-brainstem curvilinear hyperintense signals and mild linear enhancement on T2WI, FLAIR, and DWI may be characteristic of LM in lung adenocarcinoma. These findings suggest further evaluation with contrast-enhanced MRI or CSF analysis for confirmation.

This study aims to improve the accuracy of distinguishing Tuberculous Spondylitis (TBS) from Brucella Spondylitis (BS) by developing radiomics models using Deep Learning and CT images enhanced with Super-Resolution (SR).

A total of 94 patients diagnosed with BS or TBS were randomly divided into training (n=65) and validation (n=29) groups in a 7:3 ratio. In the training set, there were 40 BS and 25 TBS patients, with a mean age of 58.34 ± 12.53 years. In the validation set, there were 17 BS and 12 TBS patients, with a mean age of 58.48 ± 12.29 years. Standard CT images were enhanced using SR, improving spatial resolution and image quality. The lesion regions (ROIs) were manually segmented, and radiomics features were extracted. ResNet18 and ResNet34 were used for deep learning feature extraction and model training. Four multi-layer perceptron (MLP) models were developed: clinical, radiomics (Rad), deep learning (DL), and a combined model. Model performance was assessed using five-fold cross-validation, ROC, and decision curve analysis (DCA).

Statistical significance was assessed, with key clinical and imaging features showing significant differences between TBS and BS (e.g., gender, p=0.0038; parrot beak appearance, p<0.001; dead bone, p<0.001; deformities of the spinal posterior process, p=0.0044; psoas abscess, p<0.001). The combined model outperformed others, achieving the highest AUC (0.952), with ResNet34 and SR-enhanced images further boosting performance. Sensitivity reached 0.909, and Specificity was 0.941. DCA confirmed clinical applicability.

The integration of SR-enhanced CT imaging and deep learning radiomics appears to improve diagnostic differentiation between BS and TBS. The combined model, especially when using ResNet34 and GAN-based super-resolution, demonstrated better predictive performance. High-resolution imaging may facilitate better lesion delineation and more robust feature extraction. Nevertheless, further validation with larger, multicenter cohorts is needed to confirm generalizability and reduce potential bias from retrospective design and imaging heterogeneity.

This study suggests that integrating Deep Learning Radiomics with Super-Resolution may improve the differentiation between TBS and BS compared to standard CT imaging. However, prospective multi-center studies are necessary to validate its clinical applicability.

This study aimed to determine the depth of the SF, bone thicknesses in the buccal and lingual areas of the mandibular canal (MC), vertical positions of the SF and MC relative to each other, and the tooth level at which the deepest point of the SF was observed in the cross-sectional section.

440 cone beam computed tomography (CBCT) images were retrospectively evaluated. The depth of the SF was determined. The buccal bone thickness (BBT) and lingual bone thickness (LBT) of the MC were measured, and the tooth alignment of the deepest point of the SF and the vertical position of the SF and MC relative to each other were determined.

In both jaws, SF depth Type I ratios were lower in males than in females, and SF depth Type III ratios were higher than in females. When the relationship between the vertical position of the MC and the region where the SF was deepest was examined, it was observed that the MC was in an inferior position in most patients.

In order to reduce the complication rate in the SF region, the relevant region should be analyzed in detail with CBCT before surgical procedures. The main limitation of our study is that the number of men and women was not equal.

SF depth and BBT values in the right and left jaws were higher in males than in females. LBT was higher in females in the right jaw. As the depth of the SF increased, BBT and LBT values decreased.

The calcaneal apophysis develops through a complex ossification process during childhood growth, with multiple secondary ossification centers emerging in distinct temporal and spatial patterns. Its ossification patterns, fusion process, and associated pediatric injuries and osteochondral conditions have been well documented in the literature. This report presents a previously unreported case of bilateral unfused medial process of calcaneal apophysis incidentally discovered in an adolescent patient during evaluation for genu valgum. We aim to describe this unique presentation and discuss potential pathogenic mechanisms underlying this distinctive anatomical variation.

A 12-year-old female patient was referred for idiopathic bilateral genu valgum and ankle valgus deformity management, with no prior treatment history or symptoms. Initial radiographs showed bilateral symmetric deformities, while CT revealed bilateral separated apophyses (Lt.; 8.8 mm, Rt.; 9.4 mm) at the medial process of the calcaneus with sclerotic margins. No underlying bone pathology or structural abnormalities were identified.

The bilateral unfused medial processes of the calcaneal apophysis in this patient represent a novel anatomical variation occurring alongside coxa valga and genu valgum. Biomechanical research indicates that hindfoot eversion increases medial heel pressure by 15%, with valgus alignment generating 11-12% higher medial heel pressure compared to lateral regions. These altered pressure patterns may influence apophyseal development. Normally, the medial process develops around age 9-10 and fuses 12-24 months later, with complete fusion by ages 14-16 in females. Our patient's bilateral persistence of unfused apophysis deviated significantly from this timeline. This selective non-fusion pattern differed from known pathological conditions, thus warranting further investigation through systematic studies.

This case highlights a rare anatomical variant of bilateral unfused medial calcaneal apophyses discovered incidentally in an adolescent. While the clinical significance remains uncertain, the bilateral and symmetric nature of these findings suggests a developmental variant rather than a pathological condition. This observation contributes to our understanding of variations in calcaneal apophyseal development.

To evaluate the effectiveness of spectral-CT in assessing the severity of liver diseases in patients with chronic liver disease (CLD).

A total of 148 CLD patients who underwent spectral-CT were retrospectively recruited, including 40 non-advanced CLD (non-ACLD), 74 compensated ACLD (cACLD), and 34 decompensated ACLD (dACLD). Iodine concentrations in the liver and spleen were assessed on iodine (water) images during the equilibrium phase, which allowed for the calculation of liver and splenic extracellular volume fractions (ECV). We determined the total liver volume, liver segmental volume ratio, and splenic volume from portal phase images. Moreover, established non-invasive tests were also collected. Areas under receiver operating characteristic curve (AUCs) were employed to evaluate the diagnostic performance of CT parameters and non-invasive tests in predicting CLD severity. Additionally, we analyzed the correlations between CT parameters and non-invasive tests.

The spleen volume demonstrated the highest AUC (0.815, P<0.001) for distinguishing between non-ACLD and cALCD. Child-Pugh score exhibited the highest AUC (0.948, P<0.001) for distinguishing cALCD and dACLD. Splenic ECV exhibited the highest AUC (0.853, P<0.001) for distinguishing non-ALCD and ACLD. In contrast, the liver ECV showed strong correlations with the Fibrosis-4 Index (r=0.653, p<0.001) and the Aminotransferase-to-Platelet Ratio Index (r=0.607, p<0.001), while spleen ECV correlated more strongly with the Child-Pugh score (r=0.719, p<0.001) and the Albumin-Bilirubin Index (r=0.742, p<0.001).

Liver and splenic ECV can effectively reflect the dynamic progression of CLD and correlate well with non-invasive tests in these patients.

Spectral-CT liver and splenic ECV could serve as non-invasive imaging biomarkers for severity stratification.

Breast cancer is a major cause of mortality among women globally. While mammography remains the gold standard for detection, its interpretation is often limited by radiologist variability and the challenge of differentiating benign and malignant lesions. The study explores the use of Auto-Sklearn, an automated machine learning (AutoML) framework, for breast tumor classification based on mammographic radiomic features.

244 mammographic images were enhanced using Contrast Limited Adaptive Histogram Equalization (CLAHE) and segmented with Active Contour Method (ACM). Thirty-seven radiomic features, including first-order statistics, Gray-Level Co-occurance Matrix (GLCM) texture and shape features were extracted and standardized. Auto-Sklearn was employed to automate model selection, hyperparameter tuning and ensemble construction. The dataset was divided into 80% training and 20% testing set.

The initial Auto-Sklearn model achieved an 88.71% accuracy on the training set and 55.10% on the testing sets. After the resampling strategy was applied, the accuracy for the training set and testing set increased to 95.26% and 76.16%, respectively. The Receiver Operating Curve and Area Under Curve (ROC-AUC) for the standard and resampling strategy of Auto-Sklearn were 0.660 and 0.840, outperforming conventional models, demonstrating its efficiency in automating radiomic classification tasks.

The findings underscore Auto-Sklearn’s ability to automate and enhance tumor classification performance using handcrafted radiomic features. Limitations include dataset size and absence of clinical metadata.

This study highlights the application of Auto-Sklearn as a scalable, automated and clinically relevant tool for breast cancer classification using mammographic radiomics.

Fundus fluorescein angiography captures detailed images of fundus vasculature, enabling precise disease assessment. Translating fundus images to fundus fluorescein angiography images can assist patients unable to use contrast agents due to physical constraints, facilitating disease analysis. Previous studies on this translation task were limited by the use of only 17 image pairs for training, potentially restricting model performance.

Image pairs were collected from patients through a collaborating hospital to create a larger dataset. A fundus image to fundus fluorescein angiography translation model was developed using structure self-supervised representation cycle learning. This model focuses on vascular structures for self-supervised learning, incorporates an auxiliary branch, and utilizes cycle learning to enhance the main training pipeline.

Comparative evaluations on the test set demonstrate superior performance of the proposed model, with significantly improved Fréchet inception distance and kernel inception distance scores. Additionally, generalization experiments conducted on public datasets further confirm the model's advantages in various evaluation metrics.

The enhanced performance of the proposed model can be attributed to the larger dataset and the novel structure self-supervised cycle learning approach, which effectively captures vascular details critical for accurate translation. The model's robust generalization across public datasets suggests its potential applicability in diverse clinical settings. However, challenges such as computational complexity and the need for further validation in real-world scenarios warrant additional investigation to ensure scalability and clinical reliability.

The proposed model effectively translates fundus images to fundus fluorescein angiography images, overcoming limitations of small datasets in previous studies. This approach demonstrates strong generalization capabilities, highlighting its potential to aid in large-scale disease analysis and patient care.

Conventional skin tumor examination shows inherent limitations in accurately assessing tumor depth. HR-MRI offers superior soft tissue resolution and a comprehensive evaluation of skin cancer.

Patients confirmed by pathological diagnosis as non-melanoma skin cancer from January 2021 to December 2023 were enrolled. Patients in Group 1 received both HR-MRI and tumorectomy, while those in Group 2 received tumorectomy only. The exclusion criteria include patients with contraindications to magnetic resonance examination. MRI sequences included T1WI, T2WI, and T2WI fat suppression, and a dynamic contrast-enhanced(DCE) scan. The advantages of different sequences in evaluating the level of invasion were independently assessed by two radiologists. The advantages of different sequences in evaluating the level of invasion were independently assessed by two radiologists. Tumor size, shape, invasion, and dynamic curves were measured in a corresponding sequence. And tumor signal intensity was recorded in different sequences. For each group, the number of postoperative tissue sections, sections with positive margins, and cases of secondary surgery were recorded. For Group 1, pathological invasion levels were also recorded.

89 cases of non-melanoma skin cancer were collected, including 69 basal cell carcinoma (BBC) and 20 squamous cell carcinoma (SCC). There were 25 patients in group 1 and 59 patients in group 2. T1WI showed mainly isointensity or hypointensity for BCC and SCC. T2WI showed predominantly hyperintense, and T2WI with fat suppression all showed hyperintense. T2WI effectively showed the relationship between tumors and nearby structures, while fat-suppressed T2WI highlighted tumor contours. The positive rate of pathological sections and the rate of secondary resection in group 1 and group 2 were 9.7% and 20%, 23.1% and 44.1%. There was a higher consistency between tumor invasion levels observed by MRI and pathological results in the first group (p>0.75)

Advancements in skin tumor diagnosis and treatment reveal that some tumors penetrate deeper than traditional methods can detect, prompting interest in MRI research. HR-MRI, known for its excellent soft tissue resolution, proves useful in outlining tumors and determining their location, particularly with the T2 fat-suppressed sequence. The T2WI sequence effectively assesses skin invasion, aligning well with pathological findings, and this significantly reduces the need for subsequent surgical interventions.. This underscores HR-MRI's value as a preoperative tool. However, the study's small sample size is a limitation, and future research will include more cases for deeper insights.

Skin HR-MRI is valuable for non-melanoma skin cancer, providing accurate preoperative tumor scope assessment, and reducing the rate of secondary surgeries.

Magnetic Resonance Imaging (MRI) is a crucial method for clinical diagnosis. Different abdominal MRI sequences provide tissue and structural information from various perspectives, offering reliable evidence for doctors to make accurate diagnoses. In recent years, with the rapid development of intelligent medical imaging, some studies have begun exploring deep learning methods for MRI sequence recognition. However, due to the significant intra-class variations and subtle inter-class differences in MRI sequences, traditional deep learning algorithms still struggle to effectively handle such types of complex distributed data. In addition, the key features for identifying MRI sequence categories often exist in subtle details, while significant discrepancies can be observed among sequences from individual samples. In contrast, current deep learning based MRI sequence classification methods tend to overlook these fine-grained differences across diverse samples.

To overcome the above challenges, this paper proposes a fine-grained prototype network, SequencesNet, for MRI sequence classification. A network combining convolutional neural networks (CNNs) with improved vision transformers is constructed for feature extraction, considering both local and global information. Specifically, a Feature Selection Module (FSM) is added to the visual transformer, and fine-grained features for sequence discrimination are selected based on fused attention weights from multiple layers. Then, a Prototype Classification Module (PCM) is proposed to classify MRI sequences based on fine-grained MRI representations.

Comprehensive experiments are conducted on a public abdominal MRI sequence classification dataset and a private dataset. Our proposed SequencesNet achieved the highest accuracy with 96.73% and 95.98% in two sequence classification datasets, respectively, and outperform the comparative prototypes and fine-grained models. The visualization results exhibit that our proposed sequencesNet can better capture fine-grained information.

The proposed SequencesNet shows promising performance in MRI sequence classification, excelling in distinguishing subtle inter-class differences and handling large intra-class variability. Specifically, FSM enhances clinical interpretability by focusing on fine-grained features, and PCM improves clustering by optimizing prototype-sample distances. Compared to baselines like 3DResNet18 and TransFG, SequencesNet achieves higher recall and precision, particularly for similar sequences like DCE-LAP and DCE-PVP.

The proposed new MRI sequence classification model, SequencesNet, addresses the problem of subtle inter-class differences and significant intra-class variations existing in medical images. The modular design of SequencesNet can be extended to other medical imaging tasks, including but not limited to multimodal image fusion, lesion detection, and disease staging. Future work can be done to decrease the computational complexity and increase the generalization of the model.

VETC-positive has emerged as a novel predictor of HCC for poor prognosis. Enhanced CT is one of the most common diagnostic methods, which can indicate VETC positivity, providing important evidence for the diagnosis and treatment of VETC-positive HCC.

The objective of this study is to investigate the clinical and preoperative enhanced CT imaging characteristics and diagnostic value of VETC-positive hepatocellular carcinoma (HCC) patients.

A retrospective analysis was conducted on the clinical, pathological, and imaging data of 53 HCC patients from the First Affiliated Hospital of Ningbo University between June 2019 and September 2022. According to pathological results, patients were categorized into 11 VETC-positive and 42 VETC-negative cases. Observational parameters included: (1) Clinical indicators: gender, age, history of hepatitis B virus infection, preoperative AFP, TNM staging, and preoperative biochemical and coagulation laboratory tests, including Alb, AST, ALT, TBil, DB, PT, TT, and INR. Additionally, pathological results such as histological grading, microvascular invasion (MVI), satellite nodules, neural invasion, and postoperative recurrence were analyzed. (2) Preoperative enhanced CT observational indicators: maximum tumor diameter, intrahepatic growth, irregular tumor margins, peritumoral hepatic parenchymal enhancement, mosaic structure, non-ring-like arterial phase hyperenhancement, marked heterogeneous enhancement, non-peripheral washout, absence of enhancing capsule, enhancing/clear capsule, intratumoral arteries, intratumoral necrosis, along with measurement of unenhanced CT values and enhanced CT values at various phases, calculating enhancement ratios (enhancement ratio = enhanced CT value - unenhanced CT value / unenhanced CT value).

Quantitative data were expressed as mean ± standard deviation (x̅±s), with intergroup comparisons conducted using the t-test; categorical variables were compared using the χ² test or Fisher's exact test. Multivariate analysis employed stepwise regression for logistic regression, incorporating clinical and imaging characteristics into the logistic regression equation. Based on logistic regression results, receiver operating characteristic (ROC) curves were plotted, calculating the area under the curve (AUC), sensitivity, specificity, and their 95% confidence intervals (CI). Analysis on survival was performed using Kaplan-Meier methods and log-rank tests, aiming survival curves.

(1) Clinical characteristics of VETC-positive versus VETC-negative patients: Preoperative AFP levels showed statistical significance (P=0.037), while no significant differences were observed in gender, age, Alb, TB, DB, AST, ALT, PT, TT, and INR between VETC-positive and VETC-negative patients (P>0.05). (2) Enhanced CT imaging features of VETC-positive versus VETC-negative patients: Intratumoral necrosis showed statistical significance (P<0.05), with intratumoral arteries being 63.6% (7/11) in the positive group compared to 42.9% (18/42) in the negative group. No significant differences were found in maximum tumor diameter, irregular tumor margins, peritumoral hepatic parenchymal enhancement, mosaic structure, non-ring-like arterial phase hyperenhancement, marked heterogeneous enhancement, non-peripheral washout, absence of enhancing capsule, enhancing capsule, intratumoral arteries, as well as unenhanced CT values and enhanced CT values at various phases, arterial phase enhancement ratio, portal phase enhancement ratio, and delayed phase enhancement ratio (P>0.05). (3) Multivariate analysis influencing VETC positivity: Arterial phase CT values (HU) (OR=0.937, P=0.029), intratumoral arteries (OR=9.452, P=0.021), and intratumoral necrosis (OR=0.013, P=0.003) were identified as independent risk factors for VETC positivity (Odds Ratio=0.937, 9.452, 0.013, 95% CI=0.883-0.993, 1.4-63.823, 0.001-0.223, P<0.05). The AUC of VETC was 0.863 (95% CI: 0.728-0.997), with a sensitivity of 81.8% and specificity of 88.1%. (4) Postoperative early tumor recurrence in VETC-positive and VETC-negative patients: All 53 patients were followed up, with an average tumor recurrence time of 11 (4-20) months, showing significant differences (P<0.05).

As one of the routine and preferred methods for HCC examination, enhanced CT plays a pivotal role in diagnosis, staging, and post-treatment evaluation. Combining preoperative enhanced arterial phase CT values, intratumoral arteries, and intratumoral necrosis can highly indicate VETC positivity.

In nuclear medicine, Prostate-specific Membrane Antigen (PSMA) is a potential target for theranostics. Offering superior diagnostic accuracy to conventional imaging in prostate cancer (PCa), Gallium-68 labeled PSMA (⁶⁸Ga-PSMA) positron emission tomography/computed tomography (PET/CT) is considered the new standard of care in PCa management. Tumor cells identified as PSMA-avid on PET/CT imaging can be targeted and eliminated with PSMA-labeled Lutetium-177 (¹⁷⁷Lu-PSMA) therapy.

A sixty-eight years old patient who had metastatic castration-resistant PCa was reported in this study. Prior to receiving ¹⁷⁷Lu-PSMA therapy, the patient’s PSA level was 358 ng/ml, and experienced extensive bone discomfort. Following ten cycles of ¹⁷⁷Lu-PSMA therapy, exceptional results were observed.

¹⁷⁷Lu-PSMA therapy is likely to result in significantly better outcomes if first- or second-line treatments preserve the patient's bone marrow reserve or if the therapy is administered at earlier stages of the disease.

The Myocardial Salvage Index (MSI) is a valuable indicator in ST-segment Elevation Myocardial Infarction (STEMI) treated with Percutaneous Coronary Intervention (PCI), yet challenges exist in its acquisition. This study aims to calculate MSI using Coronary Angiography (CAG) and myocardial perfusion imaging, and further investigate its correlation with long-term cardiac function.

In 203 STEMI, the myocardium at risk was measured through CAG using the Bypass Angioplasty Revascularization Investigation Myocardial Jeopardy Index (BARI) score. The infarcted myocardium was measured by the Total Perfusion Deficit (TPD) obtained in Myocardial Perfusion Imaging (MPI) after PCI. MSI was computed as (BARI score–TPD)/BARI score. Long-term cardiac function was assessed via echocardiography.

The MSI is notably associated with the long-term cardiac function [EF: Beta = 16 (13, 20), P < 0.00; LVD: Beta = -7.3 (-9.3, -5.3), P < 0.001]. TIMI flow grades 2-3 demonstrate a superior MSI compared to grades 0-1 [0.78 (0.32) vs. 0.61 (0.38), P = 0.002]. TIMI flow grades have an impact on MSI [Beta = 0.08 (0.04, 0.13), P < 0.001]. Compared to patients with a Killip grade of < 2, those with a grade ≥ 2 exhibit a lower MSI [0.69 (0.35) vs. 0.48 (0.42), p = 0.005]. The Killip classification has an impact on MSI [Beta = -0.12(-0.19, -0.04), P = 0.003].

The study indicates the pivotal role of MSI in predicting long-term cardiac function in STEMI, compares the advantages and limitations of SPECT, CMR, and hybrid SPECT/CAG methods, analyzes the impact of residual blood flow and acute heart failure on MSI, and highlights current technological challenges and future research directions.

CAG combining MPI after PCI can be used to obtain MSI. MSI is linked to long-term cardiac function. The amount of antegrade flow before PCI and the initial cardiac function upon admission significantly influence MSI.

This study aimed to assess the effectiveness and precision of a deep learning-based model in forecasting the early response of HCC patients to TACE.

A comprehensive review of HCC-TACE data involving 111 patients with HCC was carried out, encompassing both pre-TACE MR images (captured before the first TACE) and post-TACE imaging (acquired between 30 and 60 days following TACE). Based on the mRECIST criteria, patients were divided into two cohorts: a training dataset (91 subjects, 645 images) and a test dataset (20 subjects, 155 images). A deep learning-based model utilizing LeNet architecture with an attention mechanism was developed, targeting the prediction of HCC patients' response to TACE. The robustness and accuracy of the model were examined via ROC curves and confusion matrices.

Post-TACE treatment, 56 patients (50.5%) manifested an objective response (CR+PR), whereas 55 patients (49.5%) exhibited no response (SD+PD). Concerning the model's predictive ability for TACE response, the AUC was found to be 0.760 in the training dataset and 0.729 in the test dataset. The model's prediction accuracy was further corroborated by the confusion matrix, revealing an average accuracy of 70.7% in the training dataset and 72.3% in the test dataset.

Implementing a deep learning-based model using MRI data is potent for forecasting HCC patients’ response to TACE treatment. The novel LeNet model with the attention mechanism conceived in this study contributes valuable insights that can guide the formulation of effective treatment strategies.

Unilateral upper ureteral obstruction is one of the most common causes of acute kidney function impairment. Grading perirenal changes secondary to acute unilateral upper urinary tract obstruction (AUUTO) with multidetector spiral computed tomography (MDCT) and exploring its association with kidney function are useful for diagnosing and assessing damage to the ipsilateral kidney. However, the correlation between renal function impairment and the severity of perinephric changes secondary to AUUTO has not been reported.

This study aimed to investigate the association of perirenal changes secondary to AUUTO with hydronephrosis and serum creatinine levels, as well as white blood cell counts.

This retrospective study included 376 patients with acute unilateral upper ureteral obstruction, all of whom were subjected to MDCT scans. They were classified into four grades (0-III) according to their perirenal changes on MDCT images. The severity of hydronephrosis was classified into four grades based on MDCT scans. The serum creatinine level and leukocyte counts were compared among the MDCT grade groups, and logistic regression analysis was conducted.

Among 376 patients, 77 (20.5%), 103 (27.4%), 140 (37.2%), and 56 (14.9%) cases were graded into MDCT 0, I, II, and III, respectively. The proportions of patients who had normal kidneys in MDCT 0, I, II, and III were 20 (26.0%), 10 (9.7%), 11(7.9%), and 3 (5.4%), respectively. The proportions of patients who had mild hydronephrosis in MDCT 0, I, II, and III were 55 (71.4%), 83 (80.6%), 118 (84.2%), and 46 (82.1%), respectively. The proportions of patients who had moderate and severe hydronephrosis in MDCT 0, I, II, and III were 2(2.6%), 10 (9.7%), 11 (7.9%), 7 (12.5%), respectively. Serum creatinine levels and white blood cell counts were significantly different among the MDCT grade groups (P < 0.001). Univariate and multivariate logistic regression analyses indicated that the serum creatinine level and white blood cell counts were positively associated with the MDCT grades (P < 0.001).

Perinephric changes secondary to AUUTO on MDCT images were associated with the degree of obstruction. The severity of perinephric changes can reflect the functional impairment in the ipsilateral kidney. The MDCT grades may aid clinicians in assessing renal function impairment early in patients with AUUTO, which may help patients receive early intervention and avoid the potential risk of infection and deterioration of renal function.

The incidence of Alzheimer’s disease is rising with the increasing elderly population worldwide. While no cure exists, early diagnosis can significantly slow disease progression. Computer-aided diagnostic systems are becoming critical tools for assisting in the early detection of Alzheimer’s disease. In this systematic review, we aim to evaluate recent advancements in computer-aided decision support systems for Alzheimer’s disease diagnosis, focusing on data modalities, machine learning methods, and performance metrics.

We conducted a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Studies published between 2021 and 2024 were retrieved from PubMed, IEEEXplore and Web of Science, using search terms related to Alzheimer’s disease classification, neuroimaging, machine learning, and diagnostic performance. A total of 39 studies met the inclusion criteria, focusing on the use of Magnetic Resonance Imaging, Positron Emission Tomography, and biomarkers for Alzheimer’s disease classification using machine learning models.

Multimodal approaches, combining Magnetic Resonance Imaging with Positron Emission Tomography and Cognitive assessments, outperformed single-modality studies in diagnostic accuracy reliability. Convolutional Neural Networks were the most commonly used machine learning models, followed by hybrid models and Random Forest. The highest accuracy reported for binary classification was 100%, while multi-class classification achieved up to 99.98%. Techniques like Synthetic Minority Over-sampling Technique and data augmentation were frequently employed to handle data imbalance, improving model generalizability.

Our review highlights the advantages of using multimodal data in computer-aided decision support systems for more accurate Alzheimer’s disease diagnosis. However, we also identified several limitations, including data imbalance, small sample sizes, and the lack of external validation in most studies. Future research should utilize larger, more diverse datasets, include longitudinal data, and validate models in real-world clinical trials. Additionally, explainability is needed in machine learning models to ensure they are interpretable and reliable in clinical settings.

While computer-aided decision support systems show significant promise in improving the early diagnosis of Alzheimer’s disease, further work is needed to enhance their robustness, generalizability, and clinical applicability. By addressing these challenges, computer-aided decision support systems could play a key role in the early detection of Alzheimer’s disease and potentially reduce health care costs.

Adrenal incidentalomas have increased over the past years. Although there are a lot of studies related to the frequency of adrenal masses and comorbidities, whether patients with functional or nonfunctional adrenal masses have higher risk is still a controversial issue.

A total of 464 patients (female/male: 309/155) with adrenal incidentalomas were evaluated and followed up for 8 years. The patients were divided into 5 subgroups, including Autonomous Cortisol Secretion (ACS), Cushing Syndrome (CS), Pheochromocytoma (Pheo), Non-functional Adrenal Incidentalomas (NFAI), and Primary Aldosteronism (PA).

While 336 (72.4%) of the patients had NFAI, the others suffered from ACS (10.8%), CS (4.3%), Pheo (4.1%), and PA (8.4%), respectively. When comparing biochemical and demographical data, BMI (p=0.77), Hba1c (p=0.495), FPG (p=0.28), LDL (p=0.66), and HDL (p=0.521) were similar among the patients with functional and nonfunctional adrenal masses. The most common comorbidities were hypertension (n=259, 55.8%), diabetes mellitus (n=158, 34.1%), and dyslipidemia (33.4%), respectively. While 84 (32.4%) patients with hypertension had functional adrenal masses, the others (n=175, 67.6%) had non-functional adrenal incidentalomas. In subgroup analyses, hypertension was more common in patients with PA (87.2% vs. 72%, p=0.001) and ACS. In multivariable regression analyses, hypertension (p<0.001), cortisol (p=0.003), and aldosterone (p=0.04) levels were significantly correlated with functionality.

Hypertension was the most common comorbidity in patients with adrenal adenomas, especially in functional adrenal adenomas related to serum cortisol and aldosterone levels.

This study aimed to demonstrate the relationship between hemodynamic changes in head blood flow and headache during the premenstrual period in patients experiencing premenstrual syndrome.

Thirty-two female patients experiencing premenstrual headaches were prospectively examined using carotid and vertebral artery duplex ultrasonography during headache episodes in the premenstrual periods and headache-free periods across two consecutive menstrual cycles. The diameters and areas of both the carotid and vertebral arteries, along with systolic and end-diastolic velocities, pulsatility and resistivity indices, and volumetric flow rates, were measured using grayscale imaging. Total head blood flow was determined as the sum of bilateral common carotid artery and vertebral artery flow volumes. Measurements were compared between participants’ premenstrual and menstrual periods.

A statistically significant difference in the diameter of the left external carotid artery was observed between periods with and without headache during the two consecutive menstrual cycles assessed (p = 0.030). Left external carotid artery (p = 0.019), total external carotid artery (p = 0.028), and total head blood volumes (p = 0.030) were significantly higher when headache was present during the premenstrual period than when headache was absent.

Towards the end of the luteal phase, the total head blood flow and external carotid artery flow were high due to a decrease in peripheral resistance caused by the decline in progesterone and hormonal fluctuations during this period.

Increased flow volume in the external carotid arteries and total head blood flow may be a contributing factor to premenstrual headaches.

Post-hepatic resection liver failure (PHLF) remains one of the most serious complications after hepatic resection, with an overall morbidity rate as high as 32% and an approximate 5% mortality. Previous studies demonstrate the potential of shear wave elastography (SWE) to predict PHLF. This meta-analysis aimed to evaluate the diagnostic accuracy of SWE in identifying liver failure after hepatectomy.

A comprehensive search was performed across PubMed/Medline, Embase, and Web of Science to identify studies assessing the diagnostic accuracy of SWE for predicting PHLF. The combined sensitivity, specificity, and the hierarchical summary receiver operating characteristic curve (HSROC) for SWE in detecting PHLF in liver resection patients. The Quality Assessment of Diagnostic Accuracy Studies tool was used to evaluate the quality of the studies included in the analysis. Heterogeneity was explored through sensitivity analysis, univariable meta-regression and subgroup analysis.

This meta-analysis included a total of 13 studies involving 2985 patients. For quantitative analysis. The combined sensitivities and specificities of SWE for detecting post-hepatectomy liver failure were 0.81 and 0.68, respectively. The HSROC value for SWE was 0.82. Significant heterogeneity (I² = 80.22) was observed in pooled specificity. Meta-regression and subgroup analyses suggest that differences in the proportion of patients with HCC and in the diagnostic criteria for PHLF may account for the observed heterogeneity. For the qualitative analysis, six predictive models based on SWE were included, and their AUCs were 0.80-0.915.

Both SWE alone and SWE-based prediction models appear to accurately detect PHLF and help to categorize patients into high- and low-risk groups. It may also assist surgeons in identifying the best candidates for liver resection and enhancing perioperative management.

An accurate and reliable prognostic model for Nasal Extranodal Natural Killer/T-cell Lymphoma (ENKTL) is critical for survival outcomes and personalized therapy. Currently, there is no Magnetic Resonance Imaging (MRI)- based radiomics analysis in the prognosis model for nasal ENKTL patients.

We aim to explore the value of MRI-based radiomics signature in the prognosis of patients with nasal ENKTL.

A total of 159 nasal ENKTL patients were enrolled and divided into a training cohort (n=81) and a validation cohort (n=78) randomly. Radiomics features from pretreatment MRI examination were extracted, respectively. Then two-sample t-test and Least Absolute Shrinkage and Selection Operator (LASSO) regression were used to select the radiomics signatures and establish the Rad-score. Univariate and multivariate Cox proportional hazards regression models were used to investigate the prognostic value of baseline clinical features and establish clinical models. A radiomics nomogram based on the Rad-score and clinical features was constructed to predict Overall Survival (OS). The predictive efficacy of the three models was evaluated in two cohorts.

A total of 1,345 features were extracted from T2-weighted (T2-w) and Contrast-enhanced T1-weighted (CET1-w) images, respectively, and 1,037 features with Intraclass Correlation Coefficient (ICC) >0.7 were selected. Ultimately, 20 features were chosen to construct the Rad-score, which showed a significant association with OS. The C-indexes of the Rad-score were 0.733 (95% confidence interval (CI): 0.645 to 0.816) and 0.824 (95% CI: 0.766-0.882), respectively, in training and validation cohorts. Through the univariate and multivariate analyses, three independent risk factors for OS were identified: Rad-score (HR: 10.962, 95% CI: 3.417-35.167, P <0.001), lactate dehydrogenase (LDH) level (HR: 3.009, 95% CI: 1.128-8.510, P = 0.028) and distant lymph-node involvement (HR: 2.966, 95% CI: 1.015-8.664, P = 0.047). Patients with distal lymph node involvement and LDH level before treatment were included in the clinical model, which achieved a C-index of 0.707 (95% CI: 0.600–0.814) in the training cohort and 0.635 (95% CI: 0.527–0.743) in the validation cohort.

We integrated the Rad-score and clinical variables to establish a radiomics nomogram, which exhibited a satisfactory prediction performance with the C-indexes of 0.849(95% CI: 0.781-0.917) and 0.931 (95% CI: 0.882-0.980) in two cohorts, respectively. The radiomics nomogram was more accurate in predicting OS in patients with nasal ENKTL than the other two models. Based on the radiomics nomogram, patients were categorized into low-risk and high-risk groups in two cohorts (P all < 0.05). The high-risk group defined by this nomogram exhibited a shorter OS.

The Rad-score was significantly correlated with OS for nasal ENKTL patients. Moreover, the MRI-based radiomics nomogram could be used for risk stratification and might guide individual treatment decisions.

Magnetic resonance imaging can differentiate Alzheimer-type dementia from dementia with Lewy bodies using voxel-based specific regional analysis systems for Alzheimer’s disease and arterial spin labeling, which reveal reduced blood flow from the posterior cingulate gyrus to the precuneus in Alzheimer-type dementia. However, the relationship between voxel-based specific regional analysis system scores and arterial spin labeling remains unclear. To investigate the relationship between brain atrophy scores and arterial spin labeling values in the posterior cingulate precuneus.

Participants with suspected dementia who underwent brain magnetic resonance imaging using a voxel-based regional analysis system were included. They were classified as follows: Group 1 (suspected Alzheimer-type dementia) had atrophy ≥2 in the volume of interest; Group 2 (suspected dementia with Lewy body) had atrophy <2 in the volume of interest and ≥0.2 in the gray and white matter of the dorsal brainstem; and Group 3 included those not meeting these criteria. Correlation values among atrophy within the volume of interest, percentage of atrophic areas, atrophy ratio, percentage of total brain atrophy, age, and maximum arterial spin labeling value at the posterior cingulate precuneus were evaluated.

Groups 1, 2, and 3 comprised 179, 143, and 197 patients, respectively. Arterial spin labeling values at the posterior cingulate precuneus were 77.0±24.4–77.3±25.2, 78.3±81.3–80.2±23.6, and 80.2±22.3–80.4±22.8 mL/min/100 g, respectively. Group 1 had a correlation coefficient between total brain atrophy and arterial spin labeling of –0.189 to–0.214 (P<0.01). Group 2 had a correlation coefficient between total brain atrophy and arterial spin labeling of –0.215 to –0.223 (P<0.01). Group 3 showed no significant correlations. No statistically significant difference was observed in ASL 1 and 2 values between the Alzheimer-type dementia and other groups (ASL 1: 74.5 mL/min/100 g vs. 78.8 mL/min/100 g, P=0.08; ASL 2: 74.8 mL/min/100 g vs. 79.2 mL/min/100 g, P=0.101). No statistically significant difference was observed in ASL 1 and 2 values between the Alzheimer-type dementia and DLB groups (ASL 1: 74.5 mL/min/100 g vs. 69.3. mL/min/100 g, P=0.093; ASL 2: 74.8 mL/min/100 g vs. 78.9 mL/min/100 g, P=0.258).

Reduced blood flow in the posterior cingulate gyrus and precuneus shows only a weak correlation with brain atrophy in both Alzheimer-type dementia and dementia with Lewy bodies. Therefore, it is not a reliable marker for differentiating Alzheimer-type dementia from dementia with Lewy bodies and other groups.

It is necessary to avoid using cerebral blood flow assessment alone when diagnosing dementia.

The synchronous occurrence of primary pure squamous cell carcinoma (SCC) and invasive ductal carcinoma (IDC) of the breast is rare. Accurate identification of synchronous primary malignancies is crucial because their prognosis and treatment differ significantly from recurrent diseases. Herein, we present an unusual case highlighting the synchronous development of primary SCC and IDC in the ipsilateral breast.

A 48-year-old woman presented with a palpable mass in her right breast. Preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) demonstrated an irregularly shaped mass with internal rim enhancement. Surgical resection confirmed IDC of nuclear grade 3 with a high proliferation index (Ki-67: 70%), and the patient underwent adjuvant chemotherapy without radiation. Five months postoperation, a chest computed tomography (CT) revealed a new round-shaped lesion with rim enhancement and relatively circumscribed margins near the previous operation site. Breast ultrasound additionally identified a complex cystic and solid mass with an echogenic rind and increased vascularity. Following total resection, a pure squamous cell carcinoma with prominent keratinization was confirmed.

Accurate and early diagnosis of synchronous multiple primary malignancies from recurrence of the primary tumor is critical for improving prognosis by establishing an appropriate treatment and follow-up plan. Recognizing complex cystic and solid masses with relatively circumscribed margins on radiological imaging can assist clinicians in identifying and managing rare cases where IDC and SCC coexist or appear sequentially within a short period.

Dynamic changes in adenomyotic lesions in animal models have been difficult to observe and evaluate in vivo on a regular basis. Therefore, this study aims to investigate the feasibility of establishing a rat model of adenomyosis through autologous endometrial implantation and to assess the value of magnetic resonance imaging (MRI) for noninvasive evaluation of the model.

Forty rats were randomly divided into two groups (20 rats in the control group, 20 rats in the model group). A rat adenomyosis model was constructed through autologous endometrial implantation. Three months after the modeling surgery, the rats underwent MRI examination, including T2-weighted axial imaging and T1-weighted axial imaging. The thickness of the uterine myometrium and junctional zone was measured. Following the MRI, the rat uterus was sliced for hematoxylin-eosin (HE) staining.

In the model group, lesions of adenomyosis were successfully established in all surviving rats. The myometrium of the rat uterus showed uneven thickening accompanied by scattered spotty T2 hypersignal. The junctional zone appeared as a low-signal band between the endometrium with high signal and the myometrium. The average thicknesses of both the myometrium and the junctional zone were significantly greater in the model group compared to the control group, with the differences reaching statistical significance.

Ectopic endometrium can lead to hyperplasia of the peripheral muscle cells in the myometrium, which is manifested on T2-weighted images as localized thickening and hypo-intensity of the myometrium interspersed with punctiform hyperintensity. Histologically, regions of low signal intensity refer to hyperplasia of smooth muscle, while bright foci on T2-weighted images correspond to ectopic endometrial tissue and cystic dilation of glands. This study proved the noninvasive evaluation of a rat adenomyosis model and described the junctional zone in rats using MRI techniques. Histological examination using HE staining confirmed a higher nuclear-to-cytoplasmic ratio and a more compact cell arrangement in the junctional zone region of rats compared to the outer myometrium, which could explain its hypointensity.

MRI is a valuable method for evaluating the rat adenomyosis model non-invasively. Furthermore, the successful visualization of the junctional zone in the rat uterus using MRI may have potential applications in further evaluating the progression of adenomyosis.

The association between ABO and Rh blood groups and diseases is an intriguing topic that continues to be studied, but their potential influence on mandibular asymmetry has not been explored. Temporomandibular joint (TMJ) disorders are multifactorial, and subtle anatomical variations may be linked to genetic predispositions. Our study aims to investigate the relationship between ABO and Rh blood groups and mandibular condylar and ramal asymmetries in a healthy adult Turkish population.

This study included 149 adult patients (67 males, 82 females) who had no history of systemic diseases, craniofacial deformities, or TMJ-related complaints. Asymmetry was assessed in panoramic radiographic images using a formula developed in a previous study. The chi-square and Kruskal-Wallis tests were used to analyze differences among ABO groups while the Mann-Whitney U test was used for Rh groups.

No significant difference was found in terms of gender distribution, Rh factor or age between ABO or Rh groups. However, there was a significant difference in condylar asymmetry index (CAI) between ABO groups (p 0.05). Pairwise comparisons revealed that individuals with AB blood type exhibited significantly higher CAI values compared to those with B blood type. No statistically significant differences in asymmetry indices were observed between Rh groups.

The findings of our study indicate the existence of a significant relationship between blood groups and asymmetry indices in a healthy population. The significant differences in condylar asymmetry between AB and B blood groups indicate a possible association between blood type and mandibular anatomical variations, rather than a causal relationship. Further studies are needed to confirm these findings and to understand the underlying mechanisms of the relationship between blood groups and mandibular asymmetry.

The evaluation of the left atrial (LA) by imaging is becoming increasingly essential due to its significant role in numerous diseases. This study aimed to analyze and summarize research on LA imaging in the past 20 years through bibliometric analysis and offer insights into future research prospects.

The Web of Science (WOS) core collection database was retrieved for literature in LA imaging research from 2004 to 2023. Subsequently, the literature was processed and visualized by the VOSviewer and CiteSpace. VOSviewer was used to create cooperation networks for countries/regions and institutions. CiteSpace was used to analyze burst keywords in citation analysis.

A total of 3664 articles published in this field between January 2004 and December 2023 were analyzed. The number of published articles is increasing year by year. The USA contributed the most articles (1072). Hugh Calkins (44) was the most productive author with the highest publications.

Over the past 20 years, research on LA imaging has grown rapidly. The results of the present study provide insights into the field’s status and indicate the research hotspots. In recent years, research on left atrial appendage occlusion (LAAO) and LA strain has been notably focused, which is expected to remain a prominent topic in future research.

The sphenoid sinus is an important access point for trans-sphenoidal surgeries, but variations in its pneumatization may complicate surgical safety. Deep learning can be used to identify these anatomical variations.

We developed a convolutional neural network (CNN) model for the automated prediction of sphenoid sinus pneumatization patterns in computed tomography (CT) scans. This model was tested on mid-sagittal CT images. Two radiologists labeled all CT images into four pneumatization patterns: Conchal (type I), presellar (type II), sellar (type III), and postsellar (type IV). We then augmented the training set to address the limited size and imbalanced nature of the data.

The initial dataset included 249 CT images, divided into training (n = 174) and test (n = 75) datasets. The training dataset was augmented to 378 images. Following augmentation, the overall diagnostic accuracy of the model improved from 76.71% to 84%, with an area under the curve (AUC) of 0.84, indicating very good diagnostic performance. Subgroup analysis showed excellent results for type IV, with the highest AUC of 0.93, perfect sensitivity (100%), and an F1-score of 0.94. The model also performed robustly for type I, achieving an accuracy of 97.33% and high specificity (99%). These metrics highlight the model's potential for reliable clinical application.

The proposed CNN model demonstrates very good diagnostic accuracy in identifying various sphenoid sinus pneumatization patterns, particularly excelling in type IV, which is crucial for endoscopic sinus surgery due to its higher risk of surgical complications. By assisting radiologists and surgeons, this model enhances the safety of transsphenoidal surgery, highlighting its value, novelty, and applicability in clinical settings.

Rheumatoid arthritis (RA) is a systemic autoimmune disorder primarily characterized by joint degradation, with consequential cardiovascular ramifications significantly impacting patient mortality rates.

We systematically searched for full-text English-language journal articles from 1973 to 2025 in the PubMed and Web of Science databases. Utilizing keywords such as “Rheumatoid Arthritis,” “Autoimmune Diseases,” “Pathophysiology,” “Heart,” “Cardiac,” and “Echocardiography” to narrow the search results. Articles related to the evaluation of heart diseases in rheumatoid arthritis by echocardiography were included, while those with insufficient data or low data quality were excluded. Study quality was assessed using the CASP Quantitative Checklist (2018 version), and data were synthesized through thematic content analysis.

We included 52 studies in this review after the primary analysis. The results show that traditional echocardiography can identify organic changes in the heart and ventricular function impairment of patients with rheumatoid arthritis. New ultrasound techniques, such as speckle tracking and pressure-strain loops, can detect ventricular function impairment earlier than traditional echocardiography.

Echocardiography provides complementary diagnostic information for rheumatoid arthritis cardiac involvement through structural and functional assessment, yet limitations remain. Future work should establish multimodal ultrasound frameworks and develop AI-driven analytical platforms to enhance early detection and precision management.

The continuous progress of ultrasound technology has significantly improved the accuracy of assessing cardiac damage in patients with rheumatoid arthritis, and it has become an essential examination method for screening heart diseases in such patients, providing strong support for early diagnosis.

Unlike its well-established role in lung cancer staging, positron emission tomography /computed tomography (PET/CT)'s role in guiding lung biopsies remains unclear and underutilized, despite its potential to distinguish metabolically active regions from areas of necrosis or fibrosis within lesions.

This study aims to assess the diagnostic efficacy of PET/CT-aided versus conventional CT-guided lung biopsy by comparing the incidences of non-diagnostic results, false results, and complications.

Studies comparing PET/CT-aided and conventional CT-guided lung biopsy were identified through an intensive search of PubMed, Embase, and the Cochrane Library. Data on nondiagnostic results, false results, and complications were extracted. Risk ratios (RRs) with 95% confidence intervals (CIs) were calculated using a random-effects model.

Seven studies involving 1,661 procedures were included. PET/CT-aided lung biopsy significantly reduced nondiagnostic results compared to conventional CT-guided biopsy (2.8% vs. 9.1%; pooled RR: 0.38, 95% CI: 0.20–0.70, P = 0.002). False results were also significantly fewer in the PET/CT-aided group (6.5% vs. 17.0%; pooled RR: 0.48, 95% CI: 0.35–0.65, P < 0.001). There was no statistically significant difference in overall complication rates (28.1% vs. 32.5%; pooled RR: 0.92, 95% CI: 0.77–1.10, P = 0.352), while PET/CT-aided biopsy showed a slight tendency toward fewer major complications (0.9% vs. 1.7%; pooled RR: 0.67, 95% CI: 0.30–1.44, P = 0.303).

PET/CT-aided CT-guided lung biopsy offers advantages over conventional CT-guided lung biopsy by significantly reducing nondiagnostic and false results, without significant differences in the risk of complications.

This study evaluated the impact of Low-Intensity Pulsed Ultrasound (LIPUS) on bone radio density in patients undergoing orthodontic treatment with clear aligners, aiming to enhance bone remodeling and improve treatment stability.

This retrospective study included 68 participants divided into two groups: 34 treated with LIPUS and 34 in a control group. Bone radio density was measured using Hounsfield units from CBCT scans before and after treatment. Statistical analyses included Mann-Whitney U tests and paired t-tests.

The average age was 29.85 ± 14.85 years in the control group and 36.29 ± 12.78 years in the LIPUS group. Bone radio density in the upper arch of the LIPUS group significantly increased from 444.6 HU to 751.3 HU (p < 0.001), while the control group showed a slight decrease in the upper arch (657.4 HU to 650.5 HU, p = 0.86). In the lower arch, a similar trend was observed in the LIPUS group, with an increase from 767.7 HU to 823.4 HU (p = 0.17), though not statistically significant. There were no significant differences in post-treatment ABO DI scores between groups, suggesting equivalent effectiveness in achieving orthodontic outcomes.

LIPUS with clear aligners seems promising in enhancing bone radio density, indicating an improved bone remodeling effect. This highlights LIPUS's potential as a beneficial adjunct in orthodontic treatments.

Primary pituitary melanocytoma, an exceedingly rare tumor, may resemble pituitary adenoma with apoplexy owing to its heterogeneous melanin concentration and possible hemorrhagic events. An accurate diagnosis of melanocytoma is, therefore, essential.

We present a case of a 31-year-old female patient who exhibited a progressively worsening headache that commenced one month prior. MRI showed a significantly enlarged sella turcica with a gourd-shaped lesion that had a mixture of short T1 and T2 signals. In conjunction with the MRI findings, CT scans, both non-contrast and contrast-enhanced, revealed a circular, dense region in the sellar area, exhibiting heightened enhancement post-contrast administration. Subsequently, this patient was scheduled for endoscopic transnasal skull base tumor resection and skull base reconstruction. Later, histopathological assessment showed red-S-100 (+), red-melanin A (+), red-KI-67 (+5%), red-melanoma (+), P53 (+), red-P53 (+) and Ki-67 (+) and suggested an intermediate-grade melanocytoma, positioning this lesion between benign and malignant on the spectrum of melanocytic neoplasms.

This case report evaluated the presentation, key imaging findings, and histopathological features that help differentiate primary melanocytoma from other tumors and discussed key management and prognostic considerations following diagnosis.

Due to differences in subjective experience and professional level among doctors, as well as inconsistent diagnostic criteria, there are issues with the accuracy and reliability of single imaging diagnosis results for knee joint injuries.

To address these issues, magnetic resonance imaging (MRI), computed tomography (CT) and ultrasound (US) are adopted in this article for ensemble learning, and deep learning (DL) is combined for automatic analysis.

By steps such as image enhancement, noise elimination, and tissue segmentation, the quality of image data is improved, and then convolutional neural networks (CNN) are used to automatically identify and classify injury types. The experimental results show that the DL model exhibits high sensitivity and specificity in the diagnosis of different types of injuries, such as anterior cruciate ligament tear, meniscus injury, cartilage injury, and fracture.

The diagnostic accuracy of anterior cruciate ligament tear exceeds 90%, and the highest diagnostic accuracy of cartilage injury reaches 95.80%. In addition, compared with traditional manual image interpretation, the DL model has significant advantages in time efficiency, with a significant reduction in average interpretation time per case. The diagnostic consistency experiment shows that the DL model has high consistency with doctors’ diagnosis results, with an overall error rate of less than 2%.

The model has high accuracy and strong generalization ability when dealing with different types of joint injuries. These data indicate that combining multiple imaging technologies and the DL algorithm can effectively improve the accuracy and efficiency of diagnosing sports injuries of knee joints.

This study aimed to retrospectively analyze the curative effect and influencing factors of lauromacrogol in the treatment of symptomatic hepatic cysts of <10 cm.

In this study, a total of 51 patients with symptomatic hepatic cysts (maximum diameter ranging from 5 cm to 10 cm) were included. Polycystic Liver Disease Questionnaire (PLD-Q) was used to evaluate the symptoms of patients prior to treatment. The patients were followed up at 1, 3, 6, and 12 months after treatment. At the 12-month follow-up, patients were asked to fill out the PLD-Q to assess their symptoms. The improvement rate of patients' symptoms was evaluated using a 5-point Likert scale (worse, 1; slight difference, 2; roughly the same, 3; good, and 4; better, 5. Volume reduction rate (VRR) was calculated by measuring the volume of the cyst cavity via ultrasound. Treatment success at the 12-month follow-up was determined using two criteria: symptom improvement and changes in cyst volume. Symptom improvement was assessed using a Likert Scale, with a score greater than 3 points indicating significant improvement. Additionally, a volume reduction rate (VRR) of 50% or more in cyst size (VRR ≥ 50%) was considered an effective treatment outcome. The relationship between the clinical factors and the ultrasonographic manifestations of hepatic cysts, including the initial maximum diameter of the cyst (measured using ultrasound before operation), the initial volume of the cyst, and the formation of septa after sclerosis of the cyst, was analyzed.

All patients completed at least 12 months of follow-up. After a 12-month follow-up, the effective and ineffective rates were 96.1% (49/51) and 3.9% (2/51), respectively. The logistic regression univariate analysis showed significant differences in the initial cyst volume (p = 0.001), the initial maximum diameter of the cyst (p = 0.005), and the interval formation after cyst sclerosis (p = <0.001) between VRR ≥ 50% and VRR < 50%. Logistic regression analysis demonstrated that septa formation after cyst sclerosis was an independent factor related to treatment failure, with an odds ratio of 3.246 (95% confidence interval, 0.784–4.148).

Lauromacrogol is an effective method for hepatic cyst treatment. Septa formation after cyst sclerosis is an independent factor related to ineffective treatment.

The standard treatment for hydrocephalus is often the placement of a ventriculoperitoneal shunt (VPS), especially in patients with myelomeningocele (MMC). This case report aimed to enrich the existing knowledge by presenting a rare instance of asymptomatic anal extrusion of a VPS catheter in an infant, along with a review of the relevant literature.

A 2-month-old male infant with myelomeningocele (MMC) and hydrocephalus presented with asymptomatic anal extrusion of his ventriculoperitoneal shunt (VPS) catheter, discovered by his mother. Emergency imaging revealed distal catheter migration through the rectosigmoid junction. Surgical management included (1) laparoscopic-assisted catheter removal with bowel repair using Vicryl sutures, (2) intraoperative external ventricular drain (EVD) placement, and (3) 14-day antibiotic prophylaxis. Cerebrospinal fluid analysis remained normal throughout the treatment. Following three weeks of infection monitoring, contralateral VPS replacement was performed successfully, with postoperative imaging confirming optimal shunt function and resolved hydrocephalus. This case highlighted the importance of caregiver vigilance in identifying this rare but serious complication, even in asymptomatic patients (Fig. 1).

Although anal extrusion of a VPS catheter is an uncommon but serious complication, primarily seen in pediatric patients, it can lead to life-threatening infections if untreated. Prompt surgical intervention along with broad-spectrum antibiotic therapy is critical. This report highlights the need for recognizing classic symptoms of intestinal perforation and catheter migration in pediatric patients.

This study aimed to detect the performance of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) for assessing primary biliary cholangitis (PBC).

Seventy-five patients with PBC were included in this prospective study. Shear wave elastography (SWE) and Gd-EOB-DTPA-enhanced MRI were conducted, and then the signal intensity ratio (SIR) and contrast enhancement index (CEI) in different phases, including portal venous phase (PVP), equilibrium phase (EP), and hepatobiliary phase (HBP), were calculated. Afterward, the results were compared with Child-Pugh grading and non-invasive liver fibrosis models using the Kruskal-Wallis H test or Chi-squared test. The area under the curve (AUC) was applied to evaluate the diagnostic performance of SIRHBP, CEIHBP, and SWE across different Child-Pugh grades.

SWE (p0.001), SIR HBP (p0.001), CEIHBP (p0.001), APRI (p=0.002), and FIB-4(p0.001) showed significant differences in different Child-Pugh grades. Statistically significant differences were found in SIRHBP (p=0.005), CEIHBP (p=0.010), and FIB-4 (p=0.001) of different SWE levels. For the diagnosis of Child-Pugh C, the AUC of SWE, SIRHBP, and CEIHBP were 0.889, 0.778, and 0.761, respectively. Correspondingly, the sensitivity was 75.0%, 64.4%, and 54.2%, and the specificity was 94.9%, 100%, and 100%, respectively. For the diagnosis of Child-Pugh B+C, the AUC of SWE, SIRHBP, and CEIHBP were 0.919, 0.809, and 0.814, respectively.

Our study confirmed that Gd-EOB-DTPA-enhanced MRI is an effective and objective method for assessing liver function in patients with PBC.

SIRHBP and CEIHBP could be regarded as a novel imaging biomarker to evaluate liver function. Gd-EOB-DTPA-enhanced MRI and SWE outperformed serum-based models in sensitivity and specificity, strengthening the value of imaging in clinical decision-making.

The aim of this study is to assess the identification of incidental myocardial infarction on non-electrocardiogram-gated computed tomographic scans of the chest and its prognostic significance.

The increased utilization and abundance of thoracic computed tomographic (CT) scans have provided a substrate for potential screening purposes.

The objective of this study was to evaluate the detection of incidental myocardial infarction on routine non-gated thoracic CT performed for non-cardiac reasons and its associated major cardiovascular events and survival.

We retrospectively assessed routine non-gated thoracic CT scans of all consecutive individuals aged 18 or above who underwent thoracic CT scans as outpatients at the University of California Davis from January 2015 to December 2015. We evaluated the presence and location of incidental MI on non-gated thoracic CT and compared major adverse cardiac events (MACE) and overall survival in CT-positive infarct individuals with a CT-negative infarct control group.

We reviewed routine thoracic CT scans of 1157 individuals and identified 12 individuals with incidental MI. The mean age of individuals with infarction was 71.4 ± 14.1 years, and 50% were female. All individuals with incidental MI had coronary calcification. Individuals with incidental MI had a higher rate of MACE endpoint (92% vs. 28%, p=0.0001), number of MACE events (1.1 vs. 0.3, p<0.001), and lower overall survival (median survival of 67 months vs. not reached, p=0.023) compared with age and sex-matched controls without incidental MI.

Although small in number relative to the total number of individuals evaluated, subjects with incidental MI on routine non-gated thoracic CT scans have worse cardiovascular outcomes and survival compared with controls without infarction. This study highlights the potential opportunistic screening utility of routine thoracic CTs, which could lead to improved risk stratification and intervention.

Electrical Impedance Tomography (EIT) is widely used for bedside ventilation monitoring but is limited in reconstructing cardiac-related signals due to the dominance of lung impedance changes. This study aims to reconstruct heart-related impedance imaging from lung EIT using a novel semi-Siamese U-Net architecture.

A deep learning model was developed with a shared encoder and two decoders designed to segment lung and heart regions independently. The model was trained and validated on FEM-based EIT simulations and tested on real human EIT data. A weighted binary cross-entropy loss was applied to emphasize cardiac-related learning.

The model achieved a Dice coefficient >0.99 and MAE <0.1% on simulation data. It successfully separated lung and heart regions on human EIT frames without additional fine-tuning, demonstrating strong generalization capacity.

These findings reveal that the semi-Siamese U-Net can overcome signal dominance and improve cardiac-related EIT reconstruction. However, promising results are currently limited to qualitative evaluation of real data and simulation-based training.

The proposed method offers a potential pathway for simultaneous lung-heart monitoring in ICU settings. Future work will focus on clinical validation and real-time implementation.

To address the low efficiency of diagnosing pulmonary nodules using computed tomography (CT) images and the difficulty in obtaining the key signs of malignant pulmonary nodules, a ghost convolution residual network incorporating hybrid normalization (GCHN-net) is proposed.

Firstly, a three-dimensional ghost convolution with a small kernel is embedded in the GCHN-net. Secondly, we designed a hybrid normalized-activation module (TMNAM) that can handle the rich and complex features of lung nodules in both the deep and shallow layers of the network, and incorporating two different normalization methods. This allows the network to comprehensively learn the intricate relationships underlying the intrinsic features of lung nodules and enhances its capacity to classify the properties of unknown nodules. Additionally, to enhance the accuracy and detail of the category activation map, GradCAM++ is integrated into the third layer of the GCHN-net. This integration enables the visualization of specific regions within three-dimensional lung nodules that the model focuses on during its predictions.

The accuracy of the GCHN-net on the Lung Nodule Analysis 16 (LUNA16) dataset was 90.22%, with an F1-score of 88.31% and a G-mean of 90.48%.

Compared with existing methods, the proposed method can greatly improve the classification of pulmonary nodules and can effectively assist doctors in diagnosing patients with pulmonary nodules.

Recently, deep learning (DL) algorithms use Arithmetic Units (AU) in CPU/GPU hardware for processing images/data. AU operates in fixed precision and limits the representation of weights and activations in DL. The problem leads to quantization errors, which reduce accuracy during cancer cell segmentation.

In this study, arithmetic multiplication in convolution layers is replaced with Vedic multiplication in the proposed DnCNN algorithm. Next, Vedic multiplication-based convolution layers in the DnCNN architecture are optimized using POA (Pelican Optimization Algorithm), and the resulting POA-DnCNN is implemented on an FPGA device for breast cancer detection, segmentation, and classification of benign and malignant breast lesions.

In the convolution layer of DnCNN, floating-point operations are performed through the Hybrid-Vedic (HV) multiplier called ‘CUTIN,’ which is the combination of Urdhva Tryambakam and Nikhilam Sutra with the upasutra ‘Anurupyena.’ Larger image sizes increase processor size and gate count.

The proposed HV-FPGA-based breast cancer detection system, employing Vedic multiplication in the convolution layers of DnCNN and hyperparameters optimized by POA, detects stages of breast cancer with an accuracy of 96.3%, precision of 94.54%, specificity of 92.37%, F-score of 93.56%, IoU of 94.78%, and DSC of 95.45%, outperforming existing methods.

The proposed CUTIN multiplier uses a CSA (carry save adder) with simplified sum-carry generation logic (CSCGL), achieving lower area-delay, high speed, and improved precision.

Despite the increasing prevalence of hyperuricemia and gout, there remains a relative paucity of research focused on the use of straightforward clinical and laboratory markers to predict urate crystal formation. The identification of such predictive markers is crucial, as they would greatly enhance the ability of clinicians to make timely and accurate diagnoses, leading to more effective and targeted therapeutic interventions.

The aim of this study was to evaluate the diagnostic value of various easily obtainable clinical and laboratory indicators and to establish a decision tree (DT) model to analyze their predictive significance for monosodium urate (MSU) deposition in the first metatarsophalangeal (MTP) joint.

A retrospective study was conducted on 317 patients who presented to the outpatient clinic with a gout flare between January 2023 and June 2024 (181 cases with MSU deposition in the first MTP joint and 136 cases without such deposition). Clinical and laboratory indicators included gender, age, disease course, serum uric acid (SUA), glomerular filtration rate (GFR), serum creatinine (SCR), C-reactive protein (CRP), and erythrocyte sedimentation rate (ESR). Statistical analysis methods, including T-test, logistic regression and decision tree, were used to analyze the predictors of MSU deposition in the first MTP joint. The performance of the DT model was evaluated using receiver operating characteristic (ROC) curves and a 5-fold cross-validation method was used to ensure the robustness of the study results.

Disease course, GFR, SUA, age, and SCR emerged as significant predictors of MSU deposition in the first MTP joint in both LR and DT analyses. The DT model exhibited superior diagnostic performance compared to the LR model, with a sensitivity of 83.4% (151/181), specificity of 56.6% (77/136), and overall accuracy of 71.9% (228/317). The importance of predictive variables in the DT model showed disease course, GFR, SUA, age, and SCR as 53.36%, 21.51%, 15.1%, 5.5% and 4.53%, respectively. The area under the ROC curve predicted by the DT model was 0.752 (95% CI: 0.700~0.800).

The DT model demonstrates strong predictive capability. Disease duration, GFR, SUA, age, and SCR are pivotal factors for predicting MSU deposition at the first MTP joint, with disease course being the most critical factor.

Reversible cerebral vasoconstriction syndrome (RCVS) is a condition characterized by thunderclap headaches, which are sudden and severe headaches that peak within a few seconds. These headaches present diagnostic difficulties due to their diversity and low specificity, often leading to misdiagnoses and patient dissatisfaction.

We present the case of a 52-year-old woman with a 10-day history of recurrent thunderclap headaches. Initial imaging revealed no abnormalities, but she experienced further episodes of thunderclap headaches during hospitalization. Subsequent neurovascular imaging revealed multiple intracranial stenoses with a “string of beads” appearance, confirming the diagnosis of reversible cerebral vasoconstriction syndrome. She was treated with nimodipine, and most symptoms had resolved upon discharge, with no recurrence of headache reported during a 3-month follow-up.

Prior reviews on reversible cerebral vasoconstriction syndrome predominantly emphasized isolated symptoms or advanced neuroimaging findings, offering limited applicability in primary care services. More attention should be given to identifying clinical manifestations warranting heightened reversible cerebral vasoconstriction syndrome suspicion.

Early recognition of reversible cerebral vasoconstriction syndrome counts in primary care services. We proposed a revised diagnostic routine that begins with clinical suspicion prompted by typical manifestations, like recurrent thunderclap headaches, female sex, and specific triggers, and recommends advanced neurovascular imaging when accessible. Extreme headache severity or deviation from prior migraine patterns should raise suspicion for reversible cerebral vasoconstriction syndrome, while diagnostic consideration should still remain in patients with transient neurological deficits, seizures, or cerebrovascular events.

Cor Triatriatum Sinister (CTS) is a rare congenital anomaly, accounting for 0.1%- 0.4% of congenital heart diseases. While often diagnosed and treated in infancy, some cases remain asymptomatic until adulthood due to large fenestrations. This report presents a unique case of CTS in an adult coexisting with chronic adhesive pericarditis, which may have contributed to chronic atrial dilatation, a condition not previously documented.

A 60-year-old asymptomatic Taiwanese male underwent a routine medical examination. Coronary computed tomography angiography revealed a fenestrated septum dividing the left atrium, consistent with CTS. Virtual endoscopy confirmed two wide fenestrations. Notably, chronic adhesive pericarditis, evidenced by curvilinear calcifications, was diagnosed. This condition likely exacerbated the hemodynamic impact of CTS, contributing to left atrial dilation and atrial fibrillation. Atrial fibrillation was identified, and the patient was treated with an anticoagulant for stroke prevention.

This is the first reported case of CTS coexisting with chronic adhesive pericarditis. Advanced imaging modalities, including cardiac computed tomography, angiography, and virtual endoscopy, are crucial for diagnosis and anatomical evaluation. Chronic adhesive pericarditis may amplify the effects of CTS, leading to complications, including atrial fibrillation. Anticoagulation is essential for stroke prevention in such cases.

Type 2 diabetes mellitus (T2DM) complicated with interstitial lung abnormalities (ILAs) is often overlooked and can progress to severe diabetes-induced pulmonary fibrosis (DiPF). Therefore, early diagnosis of T2DM complicated with ILAs is crucial. Chest computed tomography (CT) is an important method for diagnosing T2DM complicated with ILAs. Quantitative computed tomography (QCT) is more objective and accurate than visual assessment on CT. However, there are currently limited studies on T2DM complicated with ILAs based on quantitative CT.

This study aimed to explore the utility of quantitative computed tomography for early detection of lung injury in individuals with T2DM by examining CT-derived metrics in T2DM complicated with ILAs.

We collected data from 135 T2DM complicated with ILAs on chest CT scans retrospectively, alongside 135 non-diabetic controls with normal CT findings. Employing digital lung software, chest CT images were processed to extract quantitative parameters: total lung volume (TLV), emphysema index (LAA-950%, the percentage of lung area with attenuation < –950 Hu to total lung volume), pulmonary fibrosis index (LAA-700~-200%, the percentage of lung area with attenuation from –700Hu to –200 Hu to the total lung volume), and pulmonary peripheral vascular index (ratio TAV/TNV, the number of blood vessels TNV, the cross-sectional area of blood vessels TAV). Statistical comparisons between groups utilized Mann-Whitney U or t-tests. Correlations between Hemoglobin A1c (HbA1c) levels and CT parameters were assessed via Pearson or Spearman correlations. Parameters showing statistical significance were further examined through receiver operating characteristic (ROC) analysis.

The T2DM-ILAs cohort displayed a significantly higher LAA-700~-200% compared to controls (Z = -7.639, P< 0.001), indicative of increased fibrotic changes. Conversely, TLV (Z =-3.120, P=0.002), TAV/TNV (Z = -9.564, P< 0.001), and LAA-950% (Z = -4.926, P < 0.001) were reduced in T2DM-ILAs patients. The correlation between HbA1c and various CT quantitative indicators was not significant, HbA1c and TLV (r=-0.043, P=0.618), HbA1c and TAV (r=0.143, P=0.099), HbA1c and TNV (r=0.064, P=0.461), HbA1c and LAA-700~-200% (r=0.102, P=0.239), HbA1c and LAA-950% (r=-0.170, P=0.049), HbA1c and TAV/TNV (r=0.175, P=0.043). The peripheral vascular marker, TAV/TNV, excelled in distinguishing T2DM-related lung changes (AUC=0.84, P<0.001), outperforming LAA-700~-200% (AUC=0.77,P<0.001). A composite index incorporating multiple quantitative parameters achieved the highest diagnostic accuracy (AUC = 0.91, P< 0.001).

Quantitative CT parameters distinguish T2DM complicated with ILAs from non-diabetic individuals, suggesting a distinct pattern of lung injury. Our findings imply a particular susceptibility of small pulmonary blood vessels to injury in T2DM.

Non-gestational Ovarian Choriocarcinoma (NGOC) is an extremely rare and highly malignant ovarian germ cell tumor with nonspecific clinical manifestations, making early diagnosis challenging. At present, detailed reports on the clinical and imaging characteristics of NGOC are scarce. This case report discusses a rare instance of NGOC in a prepubertal adolescent, complemented by a literature review to enhance clinicians’ understanding of its presentation, diagnosis, and treatment.

A 10-year-old female with no history of menstruation or sexual activity presented with persistent lower abdominal pain and vaginal bleeding. Preoperative imaging revealed a large pelvic mass with heterogeneous echogenicity and vascularity. Serum Human Chorionic Gonadotropin (hCG) levels were markedly elevated (>297,000 IU/L).

Ultrasonography and CT demonstrated a large, heterogeneous, hypervascular adnexal mass with features of necrosis and cystic changes, suggesting malignancy.

The mass, originating from the right adnexa, was removed via laparotomy. Histopathology confirmed NGOC, supported by immunohistochemistry, showing strong positivity for markers like CD146, CK18, HCG, and HPL, along with a high Ki-67 index (>90%).

In young females with no sexual life, significantly elevated HCG levels and imaging findings of a large heterogeneous adnexal mass should raise suspicion for NGOC. Early recognition and multimodal diagnostic approaches, including imaging, biochemical, and pathological assessments, are essential for timely intervention, reducing metastatic risk and improving prognosis. This report contributes to the understanding of NGOC and emphasizes the importance of accurate diagnosis for better patient outcomes.

Pain with a persistent and recurrent onset is one of the most important symptoms of temporomandibular disorders (TMD). Recent evidence indicated the dysfunction of the central nervous system was more linked to TMD pain. This study aimed to explore the abnormal structural and perfusion alterations in patients with painful TMD (p-TMD) to understand the comprehension of neuro-pathophysiological mechanisms.

Forty-one p-TMD patients and 33 normal controls (NC) were recruited, and high-resolution structural brain and 3D PCASL data were obtained from a 3.0T MR scanner. The voxel-based analysis of the whole cerebral gray matter (GMV) was performed, and the GMV and cerebral blood flow (CBF) value of the altered positive areas were extracted to investigate the significant correlation with clinical variables.

The brain regions with significantly increased GMV in p-TMD group were listed as follows: right putamen, right superior frontal gyrus, left superior frontal gyrus medial segment, right supplementary motor cortex, left postcentral gyrus, right middle temporal gyrus, right postcentral gyrus medial segment, right temporal pole, right inferior temporal gyrus and right opercular part of the inferior frontal gyrus (Punc<0.001, cluster>39). However, there were no brain regions with significantly decreased GMV in the p-TMD group. Cerebral perfusion analysis identified that only the right postcentral gyrus medial segment presented significantly higher CBF value in the p-TMD group than in the NC group over all the brain regions with increased GMV. Within the p-TMD group, pain intensity, anxiety, depression, and jaw functional limitation scores were differentially associated with GMV and CBF value.

The voxel-based morphometric and perfusion findings collectively implicate maladaptive plasticity in both the sensory-discriminative and affective-motivational dimensions of pain processing in p-TMD pathophysiology.

Modic changes (MCs) are a common manifestation of lumbar degenerative disease, classified into three types. However, the relationship between Bone Mineral Density (BMD) and each type of MC at the vertebral lesion sites remains unclear.

This study included 144 patients who had both lumbar MR and CT images. The classification and grading of MCs were evaluated using MR images. On the CT images, BMD values, T-scores, and Z-scores were obtained from the normal T12 vertebrae, the corresponding lumbar Modic lesion sites, and the adjacent healthy regions at the same vertebra on the axial plane.

A total of 370 vertebrae (226 MCs and 144 normal T12 vertebrae) were assessed. No significant difference was found in the BMD of normal T12 vertebrae between males and females in the study. MCs were more commonly found in the lumbar 4 and 5 vertebrae. Of the MCs, 80 (36%) were classified as type I, 130 (57%) as type II, and 16 (7%) as type III. The BMD value, T-score, and Z-score of each Modic type lesion site were higher than those of adjacent healthy regions and normal T12 vertebrae. A strong correlation was found between the different Modic types, though no significant differences were observed between grades within the same Modic type.

The presence of any MCs was significantly associated with an increase in BMD in the corresponding lesion sites, with more severe MCs showing a stronger association with higher BMD. This is the first study to explore the relationship between all types of MCs and their BMD values.

Intrauterine growth restriction (IUGR) is associated with long-term metabolic disturbances, including obesity. Changes in hepatic lipid metabolism and adipose tissue function, mediated by lipin-1 and lipin-2, may contribute to these outcomes.

This study aimed to investigate the correlation between lipin-1 in visceral adipose tissues (VATs) and lipin-2 in the liver. It also examined hepatic T1 values using T1 mapping in IUGR rats.

The objective of this study was to explore the metabolic mechanisms linking IUGR and adult obesity by analyzing molecular and imaging markers.

Pregnant rats were fed either a low-protein diet (10%) to induce IUGR or a normal-protein diet (21%) as a control. Male offspring underwent conventional magnetic resonance imaging and native T1 mapping using a 3.0 T whole-body MR scanner at days 21, 56, and 84 post-birth. Liver tissues and VATs were collected for analysis. Lipin-1 and lipin-2 expression levels were measured using Western blot and real-time quantitative PCR.

The IUGR group exhibited significantly higher mRNA and protein expression levels of lipin-1 and lipin-2 compared to the control group at days 21, 56, and 84 after birth. Additionally, the IUGR group demonstrated significantly higher hepatic T1 values than the control group at the corresponding time points. Positive correlations were observed between the protein and mRNA expression levels of lipin-1 and hepatic T1 values. Similarly, the protein and mRNA expression levels of lipin-2 were positively correlated with hepatic T1 values. All results were statistically significant (P<0.05).

The upregulation of lipin-1 and lipin-2 expressions was found to be linked to elevated hepatic T1 values, potentially contributing to adult obesity in IUGR rats.

Semantic segmentation algorithms are essential for identifying and segmenting human organs and lesions in medical images. However, as U-Net variants enhance segmentation accuracy, they often increase in parameter count, demanding more sophisticated and costly hardware for training.

This study aims to introduce a lightweight U-Net that optimizes the trade-off between network parameters and segmentation accuracy, while fully leveraging the encoder's feature extraction capabilities.

We propose a lightweight full-encoder U-shaped network, termed LFE-UNet, which employs full-encoder skip connections, encompassing all encoder layers. This model is designed with a reduced number of basic channels—specifically, 8 instead of the typical 64 or 32—to achieve a more efficient architecture.

The LFE-UNet, when integrated with ResNet34, achieved a Dice score of 0.97385 on the ISBI LiTS 2017 liver dataset. For the BraTS 2018 brain tumor dataset, it obtained 0.87510, 0.93759, 0.87301, and 0.81469 on average, WT, TC, and ET, respectively. The paper also discusses the impact of varying basic channel numbers n and encoder layer counts N on the network's parameter efficiency, as well as the model's robustness to different levels of Gaussian noise in images and salt and pepper noise in labels. Additionally, the influence of different loss functions is explored.

The LFE-UNet proves that high segmentation accuracy can be attained with a markedly lower parameters, fully utilizing the full-scale encoder's feature extraction. It also highlights the significance of loss function selection and the effects of noise on segmentation accuracy.

The fundamental problem with the transmission and storage of medical images is their inherent redundancy and large size necessitating higher bandwidth and a significant amount of storage space.

The main objective is to enhance the compression efficiency through accurate segmentation followed by non-uniform compression through a cascade of encoders.

Due to a sharp growth in digital imaging data, it is highly desirable to reduce the size of medical images by a significant amount, without losing clinically important diagnostic information. The majority of the compression techniques reported in the literature use either manual or traditional segmentation techniques to extract the informative parts of the images. The methods based upon non-uniform compression require accurate extraction of the informative part of the image to achieve higher compression rate.

This research proposes unsupervised machine learning modified fuzzy c-means (FCM) clustering-based segmentation for accurate extraction of informative parts of MR images. The spatial constraints of the images are extracted using an automated region-growing algorithm and incorporated into the objective function of FCM clustering (RG-FCM) to enhance the performance of the segmentation process even in the presence of noise. Further, informative and background parts are subjected to two separate series of encoders, with higher bit rates for the informative part of the image.

Empirical analysis was done on the Magnetic Resonance Imaging (MRI)dataset, and experimental results indicate that the proposed technique outperforms similar existing techniques in terms of segmentation and compression metrics.

This integration of different segmentation techniques exhibits improvement in Jaccard and dice indexes, and cascade of different encoders endorse the superior performance of the proposed compression technique. The proposed technique can help in achieving higher compression of medical images without compromising clinically significant information.

Gastric schwannoma is a rare gastrointestinal mesenchymal tumor with Schwann cell differentiation. In the past, most of the published cases were single gastric schwannoma. Multiple gastric schwannoma is exceedingly rare. We herein report a case of multiple gastric schwannomas.

A 55-year-old male presented with postprandial vomiting of unclear etiology, accompanied by epigastric pain and bloating. Computed tomography revealed marked thickening of the gastric wall at the fundus-body junction along the greater curvature and gastric angle, with intraluminal nodular projections. Multiphase contrast-enhanced computed tomography demonstrated moderate progressive enhancement. The patient was misdiagnosed as having a gastric stromal tumor before the operation and subsequently underwent laparoscopic partial gastrectomy. However, pathological and immunohistochemical analysis confirmed multiple gastric schwannomas. The patient recovered uneventfully and was discharged without complications.

Gastric schwannoma is rare in clinical practice, especially gastric multiple schwannomas, which are easily confused with gastric stromal tumors, as illustrated in this case, where a preoperative misdiagnosis occurred. Clinicians should enhance their recognition of characteristic imaging features (including Computed tomography, Magnetic resonance imaging, and Positron emission tomography) and employ multimodal diagnostic approaches to optimize preoperative diagnosis.

Small cell neuroendocrine carcinoma (SCNEC) of the ureter is extremely rare, and tends to show a mixed histologic profile. Literature on its imaging features is limited.

We herein report the case of a 68-year-old woman who presented with two days of left flank pain. Ultrasound and CT scan revealed a lesion in the left distal ureter. The lesion exhibited intensive tracer activity on ¹⁸F-FDG PET/CT scan, corresponding to a malignant tumor, most likely a high-grade urothelial carcinoma, and no metastases were observed. Then, the patient underwent a radical left nephroureterectomy. Pathology revealed a carcinoma composed of SCNEC (approximately 83%) and urothelial carcinoma (approximately 17%). During one year of follow-up, the patient underwent six cycles of adjuvant chemotherapy (etoposide 100mg d1-3 + cisplatin 30mg d1-3, q3w), and no recurrence or metastases were found on the CT scan.

This case report has presented a case of ureteral SCNEC and explored the value of ¹⁸F-FDG PET/CT in the diagnosis and staging of the disease.

A transverse mesocolic internal hernia is a phenomenon in which a small intestinal loop protrudes through the natural orifice in the transverse colon mesentery. This type of internal hernia in adults, although rare, is one of the causes of closed-loop intestinal obstruction, which requires prompt diagnosis and treatment.

We report two cases of transverse mesocolic internal hernia that were examined and subsequently treated at Hospital 108, Hanoi, Vietnam. Both patients (53 and 66 years old) had atypical clinical symptoms, mainly dull epigastric pain. Upon admission, they were initially examined clinically, followed by blood testing and chest and abdominal X-ray radiography. Diagnostic imaging was mainly based on subsequent Multidetector-Row Computed Tomography (MDCT). Laparoscopic/surgical release of the hernia and closure of the natural orifice in the transverse colon mesentery were performed. The clinical symptoms and laboratory and radiographic findings did not suggest a causal diagnosis. However, MDCT provided several images suggestive of an internal hernia, including a closed intestinal loop passing through the transverse colon mesentery and located posteriorly in the left abdominal cavity near the Treitz angle, displacement of the mesenteric vascular bundle, and colon displacement. These displacements were the causes of intestinal inflammation/obstruction. Additionally, laparoscopic/surgical results confirmed the MDCT diagnosis.

Thin-slice thickness, high spatial resolution, multiplanar reconstruction MDCT was effective for diagnosing transverse mesocolic internal hernia. In our two cases, MDCT helped determine the cause and assess the state of intestinal ischemia.

The study investigates the creation and assessment of Machine Learning (ML) models using different classifiers such as Support Vector Machine (SVM), logistic regression, decision tree, k-nearest neighbour (kNN), and Artificial Neural Network (ANN) for the automated identification of tuberculosis (TB) from chest X-ray (CXR) images.

As a persistent worldwide health concern, TB requires early detection for effective treatment and control of the infection. The differential diagnosis of TB is a challenge, even for experienced radiologists. With the use of automated processing of CXR images which are reasonable and frequently used for TB diagnosis, employing Artificial Intelligence (AI) techniques provides novel possibilities.

The objective of the study was to identify respiratory disorders, radiologists devote a lot of time reviewing each of the CXR images. As such, they can identify the type of disease using automated methods based on AI algorithms. This work advances the diagnosis of TB via machine learning, which may result in early treatment options and enhanced outcomes for patients.

The disease was classified using distinct parameters like edge, shape, and Gray Level Difference Statistics (GLDS) on splitting of the dataset at 70:30 and 80:20.

It was observed that authors attained 93.5% accuracy using SVM with linear kernel for a 70:30 data split considering hybrid parameters. The comparison was made considering different feature extraction techniques, different dataset splitting, existing work, and another dataset.

The designed model using SVM, decision tree, kNN, ANN, and logistic regression was compared using other state-of-the-art techniques, other datasets, different feature extraction techniques, and different splitting of data. AI has great promise for enhancing tuberculosis detection, which will ultimately lead to an earlier diagnosis and improved disease management.

This study aimed to analyze the composition of renal staghorn calculi and their characteristics using spectral CT.

This study enrolled 111 cases of renal staghorn calculi from 94 patients (48 males and 46 females, aged 28–76 years; median age: 56 years). Using spectral CT, average Zeff and CT values were analyzed. The water/iodine-based images were generated by the material separation module. All stones were detected by FTIR spectroscopy.

111 cases of renal staghorn calculi included 53 cases of single composition (47.8%) and 58 cases of mixed composition (52.2%). In staghorn calculi of a single composition, urate (23 cases) and calcium oxalate monohydrate (16 cases) were more prevalent than struvite (5 cases) and brushite (5 cases). Mixed compositions included metabolic-metabolic (36 cases, 62.1%), metabolic-infectious (14 cases, 24.1%), and infectious-infectious (8 cases, 13.8%) cases, respectively. The average Zeff values showed some characteristics of carbapatite and urate. However, average Zeff and CT values had many overlappings among other compositions. All stones appeared homogeneous in water-based images. In iodine-based images, calcium oxalate monohydrate displayed homogeneous high density, but struvite and brushite showed heterogeneous high density. Single compositions of carbapatite, calcium oxalate monohydrate, and cystine exhibited homogeneous high density, similar to mixed compositions of carbapatite and calcium oxalate monohydrate. Furthermore, urate demonstrated homogeneous low density. Moreover, the mixture of struvite and brushite/urate showed heterogeneous high density.

In staghorn calculi of a single composition, the metabolic type was common, while metabolic-metabolic and metabolic-infectious types frequently occurred in staghorn calculi with mixed compositions. Except for average Zeff values, water-iodine material separation performed an important auxiliary function in differentiating stones’ compositions using spectral CT.

Optic nerve hemangioblastoma (ONH) is a rare benign tumor. It can be sporadic or associated with Von-Hippel Lindau (VHL) syndrome. Magnetic resonance imaging (MRI) is the most commonly used diagnostic technique for the tumor. However, an accurate diagnosis can be challenging due to the rarity of ONH and its similarity to glioma and meningioma.

A 49-year-old female experienced progressive vision loss for ten years in the right eye, accompanied by proptosis over two years. The ophthalmological examination found her visual acuity of the right eye to have no light perception. Optical coherence tomography showed decreased thickness of the right retinal ganglion cell layer. MRI revealed an oval solid mass within the right retrobulbar space, with isointensity on T1-weighted (T1WI) imaging and heterogeneous hyperintensity on T2-weighted imaging (T2WI). Heterogeneous enhancement was found on gadolinium-enhanced T1WI and dynamic contrast-enhanced MRI. At internal and marginal areas of the mass, multiple flow voids were observed on various sequences, especially on T2WI. Furthermore, the superior, inferior, medial, and lateral rectus muscles of the right eye distinctly atrophied, showing a lower signal intensity on T2WI and less apparent enhancement than the left normal ones. Postoperative pathological diagnosis was hemangioblastoma of the right optic nerve.

Hemangioblastoma should be considered as a differential diagnosis for the space-occupying mass of the optic nerve if there is the presence of flow voids, vivid enhancement, and absence of a dural attachment, regardless of VHL syndrome. Of note, this is the first reported case to consider altered extraocular muscles as a potential point to prompt the diagnosis on MRI.

The study aims to investigate the prognostic value of deep learning based pericoronary adipose tissue attenuation computed tomography (PCAT) and plaque volume beyond coronary computed tomography angiography (CTA) -derived fractional flow reserve (CT-FFR) in patients with percutaneous coronary intervention (PCI).

A total of 183 patients with PCI who underwent coronary CTA were included in this retrospective study. Imaging assessment included PCAT, plaque volume, and CT-FFR, which were performed using an artificial intelligence (AI) assisted workstation. Kaplan-Meier survival curves analysis and multivariate Cox regression were used to estimate major adverse cardiovascular events (MACE), including non-fatal myocardial infraction (MI), stroke, and mortality.

In total, 22 (12%) MACE occurred during a median follow-up period of 38.0 months (34.6-54.6 months). Kaplan-Meier analysis revealed that right coronary artery (RCA) PCAT (p = 0.007) and plaque volume (p = 0.008) were significantly associated with the increase in MACE. Multivariable Cox regression indicated that RCA PCAT (hazard ratios (HR): 7.05, 95%CI: 1.44-34.63, p = 0.016) and plaque volume (HR: 3.84, 95%CI: 1.44-10.27, p = 0.007) were independent predictors of MACE after adjustment by clinical risk factors. However, CT-FFR was not independently associated with MACE in multivariable Cox regression (p = 0.150).

Deep learning based RCA PCAT and plaque volume derived from coronary CTA were found to be more strongly associated with MACE than CT-FFR in patients with PCI.

Lung cancer is one of the main threats to global health, among lung diseases. Low-Dose Computed Tomography (LDCT) provides significant benefits for its screening but also brings new diagnostic challenges that require close attention.

By searching the Web of Science core collection, we selected articles and reviews published in English between 2005 and June 2024 on topics such as “Low-dose”, “CT image”, and “Lung”. These literatures were analyzed by bibliometric method, and CiteSpace software was used to explore the cooperation between countries, the cooperative relationship between authors, highly cited literature, and the distribution of keywords to reveal the research hotspots and trends in this field.

The number of LDCT research articles show a trend of continuous growth between 2019 and 2022. The United States is at the forefront of research in this field, with a centrality of 0.31; China has also rapidly conducted research with a centrality of 0.26. The authors' co-occurrence map shows that research teams in this field are highly cooperative, and their research questions are closely related. The analysis of highly cited literature and keywords confirmed the significant advantages of LDCT in lung cancer screening, which can help reduce the mortality of lung cancer patients and improve the prognosis. “Lung cancer” and “CT” have always been high-frequency keywords, while “image quality” and “low dose CT” have become new hot keywords, indicating that LDCT using deep learning techniques has become a hot topic in early lung cancer research.

The study revealed that advancements in CT technology have driven in-depth research from application challenges to image processing, with the research trajectory evolving from technical improvements to health risk assessments and subsequently to AI-assisted diagnosis. Currently, the research focus has shifted toward integrating deep learning with LDCT technology to address complex diagnostic challenges. The study also presents global research trends and geographical distributions of LDCT technology, along with the influence of key research institutions and authors. The comprehensive analysis aims to promote the development and application of LDCT technology in pulmonary disease diagnosis and enhance diagnostic accuracy and patient management efficiency.

The future will focus on LDCT reconstruction algorithms to balance image noise and radiation dose. AI-assisted multimodal imaging supports remote diagnosis and personalized health management by providing dynamic analysis, risk assessment, and follow-up recommendations to support early diagnosis.

Epithelioid Hemangioendothelioma (EHE) is a rare vascular neoplasm that typically occurs in the bone, soft tissue, liver, and lung but rarely in the mediastinum. Multimodal imaging of EHE is poorly understood, often leading to misdiagnosis as other mediastinal tumors.

Two female cases with incidental mediastinal masses were retrospectively analysed, focusing on multimodal presentations. For both cases, CT studies showed well-defined, low-density oval masses in the right anterior superior mediastinum with the Superior Vena Cava (SVC) invasion. Intralesional punctate calcifications were observed in Case 2. MRI revealed hypointense masses on T1WI and slightly hyperintense on T2WI, with partial diffusion restriction on DWI. Case 1 had mild enhancement, while Case 2 had significant enhancement. PET-CT showed significant FDG uptake with maximum standardized uptake values (SUVmax) of 9.2 and 5.1, respectively. Both patients underwent surgical resection, with pathology confirming mediastinal EHEs.

Mediastinal EHE presents as a well-defined soft-tissue mass with punctate calcifications and heterogeneous enhancement, typically located in the anterior mediastinum with invasion into medium or large veins. Moreover, it should be considered in the differential diagnosis of mediastinal tumors.

This study aimed to investigate the imaging features of primary fallopian tube carcinoma (PFTC).

Imaging findings of 12 PFTC patients were retrospectively studied. Multi-slice computed tomography (CT, MSCT) was performed to investigate tumor location, size, density, appearance (cystic/solid), enhancement pattern, and metastasis.

Twelve women aged 34–67 (mean=54.3) years were presented with pelvic pain (n=6), vaginal discharge (n=5), and incidental pelvic masses (n=3). The tumor diameters of PFTC varied from 3.3 to 6.8 cm (mean=4.7 cm). Ten cases were unilateral, and two were bilateral. The lesions were adnexal tubular-shaped cystic masses with mucosal papillary nodes in six cases, irregular cystic and solid masses in four cases, and sausage-shaped solid masses in two cases. The plain CT values ranged from 15 to 35 HU (mean, 28 HU). On enhanced CT, the enhancement of the solid composition was lower than that of the myometrium in all phases. CT values in arterial and venous phases were 55-62 and 60-63 HU, respectively, with average values of 58.6 and 61 HU. The metastasis sites included the ovary (n=2), omentum (n=3), retroperitoneal lymph nodes (n=5), pelvic lymph nodes (n=5), and inguinal lymph nodes (n=2). Seven cases exhibited pelvic fluid, and seven exhibited round ligament thickening on the lesioned side.

In patients presenting with vaginal discharge or genital bleeding and sausage-shaped or tubal-shaped cystic, solid, or solid-cystic complexes in the adnexal portion associated with hydrosalpinx and peritumoral ascites, PFTC should be considered in the diagnosis, especially in tumors associated with round ligament thickening.

Accurate determination of tumor boundaries is crucial for staging and treating central lung cancer (CLC).

This retrospective study aimed to evaluate the feasibility of contrast-free CT radiomics in discriminating CLC tumors from atelectasis.

A total of 58 patients with CLC and associated lung atelectasis, corresponding to 58 tumors and 58 atelectasis regions, were included. Radiomics features were extracted from tumor and atelectasis areas using contrast-free CT images. The least absolute shrinkage and selection operator (LASSO) identified the most differential radiomics features. A logistic regression model (LR) was established and evaluated using 5-fold cross-validation. Discrimination performance was assessed using the area under the ROC curve (AUC) and decision curve analysis (DCA). Additionally, the potential of visualizing and distinguishing tumors and atelectasis based on contrast-free CT was explored by comparing pixel-level radiomics features with contrast CT.

A total of 1561 radiomics features were extracted, with 356 showing significant statistical differences between tumor and atelectasis. LASSO identified the 10 most differential radiomics features. The LR model trained with these features achieved an AUC of 0.94 (95% CI: 0.89-0.99), sensitivity of 0.88, and specificity of 0.89 in the training group, and an AUC of 0.81 (95% CI: 0.67–0.95), sensitivity of 0.78, and specificity of 0.65 in the validation group. DCA confirmed the clinical utility, and the radiomics feature square_firstorder_10Percentile showed good performance in distinguishing tumors from atelectasis, with consistency to contrast CT.

Contrast-free CT radiomics can effectively discriminate CLC tumors from atelectasis.

This study aimed to characterize the magnetic resonance imaging (MRI) findings of juvenile suprasellar pilocytic astrocytoma (PA) in a sample of 11 children and help neuroradiologists preoperatively differentiate PAs from other suprasellar tumors.

Eleven consecutive children with pathologically confirmed suprasellar PAs in our hospital from May 2015 to November 2021 were enrolled in this study. The clinical data and preoperative MR images were retrospectively reviewed. MRI included T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), fluid-attenuated inversion recovery (FLAIR), and postcontrast T1WI. Six patients underwent diffusion-weighted imaging (DWI). The location, signal features, enhancement pattern, and apparent diffusion coefficient (ADC) of the lesions on MRI were evaluated. The clinical status of the patients 3 years after surgery was noted.

The 11 suprasellar PAs were mainly located around the optic chiasma and hypothalamus and invaded adjacent structures. The lesions showed hyperintensity or slight hyperintensity on T2WI and hypointensity on T1WI. Among the 11 patients, 5 had solid tumors with homogeneous enhancement, one had a solid tumor with heterogeneous enhancement, and five had cystic and solid tumors with heterogeneous enhancement. Cerebrospinal fluid (CSF) dissemination foci were observed in 4 patients. The solid components of the lesions were hypointense or isointense on DWI, with high ADC values at a mean of 1.77±0.36 ×10^-3 mm²/s. Gross total resection was achieved in only one patient (9.1%), and 10 (90.9%) were subtotally resected. Five patients died during the follow-up period, and the 3-year survival rate was 54.5%.

Juvenile suprasellar PAs are characterized by a solid and intermixed cystic and solid appearance, hyperintensity on T2W images, obvious enhancement of the solid component, and relatively high ADC values.

Various methods have been employed to evaluate secondary limb lymphedema, each with its own set of limitations.

To delve into a novel approach to lymphatic grading, specifically utilizing enhanced ultrasound for assessing lymphatic function, to compensate for the shortcomings of other methods to some extent.

The clinical and ultrasound data of 51 patients with secondary limb lymphedema from June 2022 to September 2023 were retrospectively analyzed. The characteristic ultrasound manifestations of all visualized lymphatic vessels were studied. A contrast-enhanced ultrasound grading of lymphatic vessels (Ceus-Clv) was formulated and applied to grade the 51 patients. The study also correlated Ceus-Clv with Campisi clinical stage, postoperative duration, and duration of edema.

Out of 51 patients, there were 19 cases of Ceus-Clv I, 10 cases of Ceus-Clv II, 19 cases of Ceus-Clv III, and 3 cases of Ceus-Clv IV. The correlation coefficient (rs) between Ceus-Clv and Campisi clinical stages was 0.958 (P < 0.001). Similarly, the correlation coefficient between Ceus-Clv and postoperative duration was 0.824 (P < 0.001), and between Ceus-Clv and duration of edema was 0.763 (P < 0.001).

Ceus-Clv grading is a safe, convenient, and effective method for assessing lymphatic vessel function in secondary limb edema. This method can accurately reflect the patient's lymphatic vessel function and the severity of edema, providing valuable guidance for the treatment of secondary limb edema.

Determination of LVSI is the recommended criterion for performing lymphatic drainage and is important for the preoperative clinical decision-making process; however, Intraoperative Frozen Section (IFS) has limitations for the analysis of LVSI, and there is an urgent need for other indirect methods to predict the presence of LVSI.

This study aimed to investigate the value of Magnetic Resonance Imaging (MRI) features in predicting Lymphovascular Space Invasion (LVSI) in endometrial cancer (EC).

The objective of this study was to analyze MRI features that may be associated with LVSI and to explore their association.

In this study, 179 patients who received treatment for EC confirmed by surgical pathology at two medical institutions from January 2017 to May 2024 were reviewed and grouped according to the presence or absence of vascular cancer embolism in the pathology. The MRI imaging features of the two groups were compared, including the maximum transverse diameter in the sagittal position, myometrial invasion, disruption of the uterine Junctional Zone (JZ), serosal surface, uterine appendages, cervical stromal invasion, lymph node enlargement, and its T2 value, and Diffusion-Weighted Imaging (DWI). The risk factors of the LVSI-positive group were determined by performing logistic regression analysis to analyze the correlation between Apparent Diffusion Coefficient (ADC) values and LVSI in EC.

There were 34 cases in the LVSI-positive group and 145 cases in the negative group. The maximum transverse diameter in sagittal position, myometrial invasion, interruption of the uterine JZ, serous surface, uterine appendages, cervical stromal invasion, lymph node enlargement, and their DWI and ADC values were statistically significant between the two groups (P < 0.05). In multivariate logistic regression analysis, lymph node enlargement (P = 0.001) and ADC value (P = 0.041) were identified as independent risk factors for positive LVSI.

Lymph node enlargement and reduced ADC values (<0.767*10-3mm²/s) in MR imaging are of high value in predicting the occurrence of LVSI in patients with EC and can be used as an important reference for preoperative clinical diagnostic and therapeutic decisions for patients.