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.