Current Medical Imaging - Volume 21, Issue 1, 2025

The objective is to develop and compare risk prediction models for Iodine Contrast Media (ICM)-related Acute Adverse Reactions (AAR) in patients without a prior history of such reactions, and to construct a nomogram based on the superior model.

546 patients without a history of ICM-related AAR who underwent ICM administration during CT contrast-enhanced scan were retrospectively enrolled, and divided into training (n=234), test (n=101), and external validation (n=211) sets. Clinical, medication information, and environmental factors were collected. Features were selected by univariate logistical analysis and least absolute shrinkage and selection operator, and four Machine Learning (ML) models, including Logistic Regression (LR), decision tree, k-nearst neighbors and linear support vector classification were used to construct ICM-related AAR risk prediction models were developed and evaluated using AUC, accuracy and F1 score. A nomogram was constructed based on the superior model.

History of ICM exposure and allergy due to other factors, hypertension, type of ICMs, ICM dose, oral metformin, hyperglycaemia, and glomerular filtration rate were selected for modeling (all p < 0.05). The LR model demonstrated superior performance, with AUCs of 0.894 (test set) and 0.814 (external validation), and was used to construct a clinically applicable nomogram.

The LR-based model effectively predicts ICM-related AAR risk using readily available clinical variables. It offers a practical tool for identifying high-risk patients prior to ICM administration, facilitating preventive measures.

LR can predict the risk of ICM-related AAR well in patients without a history of ICM-related AAR, and the corresponding nomogram is provided.

Construct and compare multiple machine learning models to predict lymph node (LN) metastasis in cervical cancer, utilizing radiomic features extracted from preoperative multi-parametric magnetic resonance imaging (MRI).

This study retrospectively enrolled 407 patients with cervical cancer who were randomly divided into a training cohort (n=284) and a validation cohort (n=123). A total of 4065 radiomic features were extracted from the tumor regions of interest on contrast-enhanced T1-weighted imaging, T2-weighted imaging, and diffusion-weighted imaging for each patient. The Mann-Whitney U test, Spearman correlation analysis, and selection operator Cox regression analysis were employed for radiomic feature selection. The relationship between MRI radiomic features and LN status was analyzed using five machine-learning algorithms. Model performance was evaluated by measuring the area under the receiver-operating characteristic curve (AUC) and accuracy (ACC). Moreover, Kaplan–Meier analysis was used to validate the prognostic value of selected clinical and radiomic characteristics.

LN metastasis was pathologically detected in 24.3% (99/407) of patients. Following a three-step feature selection, 18 radiomic features were employed for model construction. The XGBoost model exhibited superior performance compared to other models, achieving an AUC, accuracy, sensitivity, specificity, and F1 score of 0.9268, 0.8969, 0.7419, 0.9891, and 0.8364, respectively, on the validation set. Additionally, Kaplan−Meier curves indicated a significant correlation between radiomic scores and progression-free survival in cervical cancer patients (p < 0.05).

Among the machine learning models, XGBoost demonstrated the best predictive ability for LN metastasis and showed prognostic value through its radiomic score, highlighting its clinical potential.

Machine learning-based multi-parametric MRI radiomic analysis demonstrated promising performance in the preoperative prediction of LN metastasis and clinical prognosis in cervical cancer.

Microsurgical treatment of posterior circulation aneurysms remains challenging due to their deep location, complex anatomical exposure, and close proximity to critical neurovascular structures. Ensuring adequate collateral circulation is paramount for preventing ischemic complications. Indocyanine Green (ICG) and Fluorescein Video Angiography (FL-VAG) have emerged as effective intraoperative tools for assessing cerebral perfusion and guiding surgical decision-making.

We report the case of a 29-year-old male presenting with a thunderclap headache, nausea, and vomiting, subsequently diagnosed with a fusiform aneurysm at the P2-P3 junction of the left posterior cerebral artery. The patient underwent a subtemporal approach with partial posterior petrosectomy for aneurysm clipping and remodeling. Initially, an STA-P3 and PITA-P3 bypass were considered; however, intraoperative ICG and FL-VAG confirmed sufficient retrograde collateral flow, allowing the bypass procedure to be avoided. Postoperative imaging demonstrated patent circulation in the occipitotemporal region without ischemic compromise.

This case highlights the crucial role of intraoperative fluorescence imaging in refining surgical strategies for complex aneurysm clipping. ICG and FL-VAG enhance surgical precision by providing real-time perfusion assessment, reducing the need for additional vascular interventions, and improving patient outcomes.

To address insufficient segmentation accuracy in athletes' soft tissue injury analysis, this study proposes an enhanced Swin-Unet model with multi-scale feature fusion via the FPN (Feature Pyramid Network) and an adaptive window selection mechanism for dynamic receptive field adjustment.

A weighted hybrid loss function integrating Dice Loss, Cross-Entropy Loss, and boundary auxiliary loss optimizes segmentation precision and boundary recognition.

Evaluated on the OAI-ZIB dataset using 10-fold cross-validation, the model achieves a DSC (Dice Similarity Coefficient) of 0.978, outperforming baseline Swin-Unet and mainstream architectures. Superior performance is demonstrated in IoU (Intersection over Union) (0.968) and boundary Hausdorff distance (3.21), alongside significantly reduced diagnosis time (6.0 minutes vs. 16.8 minutes manually).

This framework enhances real-time medical imaging analysis for athlete injuries, offering improved accuracy, efficiency, and clinical utility in soft tissue segmentation tasks.

To evaluate the correlation between the effective cross-sectional area (eCSA) of the rotator cuff muscle measured using Dixon MRI and the outcomes of the Biodex Isokinetic Test.

The cross-sectional area (CSA) of the subscapularis (SSc), supraspinatus (SST), and infraspinatus+teres minor (ISTM) muscles of 87 patients who had undergone shoulder MRI and Biodex Isokinetic Test were measured in the oblique sagittal Y-view. The eCSA was calculated by multiplying the CSA by (1-fat fraction). Eight shoulder movements (FL60, EX60, FL180, EX180, ER60, IR60, ER180, and IR180) each assessed using four parameters (peak torque [PT], peak torque/body weight, torque at 30° [TQ30], and total work) were recorded on Biodex. Pearson correlation coefficients were calculated between eCSA and Biodex outcomes. Univariate regression analyses were conducted to identify the factors influencing the Biodex results. General linear models were applied to confirm the correlations between the eCSA and 32 Biodex parameters after adjusting for these factors.

The eCSA of the SSc, SST, and ISTM exhibited significant correlations with TQ30 at IR180 (r=0.549) and FL60 (r=0.522), PT at ER60 (r=0.656) and EX60 (r=0.575), and PT at ER60 (r=0.674) and FL180 (r=0.626), respectively. Age, sex, SST, and SSc tears were identified as factors influencing the Biodex results. FL60TQ30, EX60PT, and ER60PT exhibited significant associations with the eCSA of SSc, SST, and ISTM, respectively, after adjusting for these factors.

eCSA may be a useful quantitative imaging marker for assessing the function of the rotator cuff muscle. FL60TQ30, EX60PT, and ER60PT are useful Biodex indices for SSc, SST, and ISTM, respectively.

Liver fibrosis is a key pathological process that can progress to cirrhosis and liver failure. Although magnetic resonance elastography (MRE) is an established noninvasive method for fibrosis staging, its clinical application is limited by hardware dependence. The diagnostic utility of diffusion-weighted imaging-based virtual MRE (vMRE) and B1-corrected T1 mapping in liver fibrosis assessment remains to be further investigated.

Forty rabbits were included in the final analysis: CCl4-induced fibrosis (n=33) and control (n=7). Following Gd-EOB-DTPA administration, DWI and T1 mapping sequences were executed at 5 and 10 minutes. Diagnostic efficacy and correlations of vMRE and T1 mapping in a rabbit liver fibrosis model were evaluated.

Rabbits were classified into three groups: Control (n=7), Nonadvanced fibrosis (F1-F2, n=20), and Advanced fibrosis (F3-F4, n=13). The AUC values for T1post_5min, T1post_10min, rΔT1_10min, and μdiff in distinguishing controls from nonadvanced and advanced fibrosis groups were (0.78, 0.82, 0.71), (0.82, 0.85, 0.77), and (0.62, 0.69, 0.74), respectively, with μdiff showing (0.90, 0.93, 0.66). A significant positive correlation existed between μdiff and liver fibrosis grade (r=0.534, p<0.001).

μdiff correlated well with fibrosis severity and effectively identified fibrotic livers, but showed limited ability to distinguish fibrosis stages, likely due to overlapping tissue stiffness. B1-corrected T1 mapping offered complementary functional information, with the 10-minute post-contrast time point providing the best staging performance, thereby enhancing the overall diagnostic value.

Gd-EOB-DTPA-enhanced T1 mapping and DWI-based vMRE provide substantial noninvasive assessment of liver fibrosis.

Intracranial hemorrhage (IH) causes dementia and Alzheimer’s disease in the later stages. Until now, the accurate, early detection of IH, its prognosis, and therapeutic interventions have been a challenging task. Objective: A Multimodal Joint Fusion Sentiment Analysis (MJFSA) framework is proposed for the early detection and classification of IH, as well as sentiment analysis to support prognosis and therapeutic report generation.

MJFSA integrates radiological images and the radiological clinical narrative reports (RCNRs). In the proposed MJFSA model, MRI brain images are enhanced using the modified Contrast Limited Adaptive Histogram Equalization (M-CLAHE) algorithm. Enhanced images are processed with the proposed Tuned Temporal-GAN (Tuned-T-GAN) algorithm to generate temporal images. RCNRs are generated for temporal images using the Microsoft-Phi2 language model. Temporal images are processed with the Tuned-Vision Image Transformer (T-ViT) model to extract image features. On the other hand, the Bio-Bidirectional Encoder Representation Transformer (Bio-BERT) processes the RCNR texts for text feature extraction. Temporal image and RCNR text features are used for IH classification, such as intracerebral hemorrhage (ICH), epidural hemorrhage (EDH), subdural hemorrhage (SDH), and intraventricular hemorrhage (IVH), resulting in sentiment analysis for prognosis and therapeutic reports.

The MJFSA model has achieved an accuracy of 96.5% in prognosis sentiment analysis and 94.5% in therapeutic sentiment analysis.

The Multimodal Joint Fusion Sentiment Analysis (MJFSA) framework detects IH and classifies it using sentiment analysis for prognosis and therapeutic report generation.

The MJFSA model’s prognosis and therapeutic sentiment analysis report aims to support the early identification and management of risk factors associated with dementia and Alzheimer’s disease.

Artificial intelligence has significantly enhanced disease diagnosis in healthcare, particularly through Deep Learning (DL) and Federated Learning (FL) approaches. These technologies have shown promise in detecting ocular diseases using medical imaging while addressing challenges related to data privacy and security. FL enables collaborative learning without sharing sensitive medical data, making it an attractive solution for healthcare applications. This systematic review aims to analyze the advancements in AI-driven ocular disease detection, with a particular focus on FL-based approaches. The article evaluates the evolution, methodologies, challenges, and effectiveness of FL in enhancing diagnostic accuracy while ensuring data confidentiality.

The systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework to ensure transparency and reliability. Research articles published between 2017 and 2024 were identified using academic databases, including Web of Science, Scopus, IEEE Xplore, and PubMed. Studies focusing on DL and FL models for detecting ocular diseases were selected based on predefined inclusion and exclusion criteria. A comparative analysis of the methodologies, architectures, datasets, and performance metrics of different FL models has been presented.

The findings indicated that FL preserves data privacy while achieving diagnostic performance comparable to traditional centralized AI models. Various FL models, including FedAvg and FedProx, have been implemented for ocular disease detection, with high accuracy and efficiency. However, challenges, such as data heterogeneity, communication efficiency, and model convergence, persist.

FL represents a promising approach for ocular disease detection, balancing diagnostic accuracy with data privacy. Future research may focus on optimizing FL frameworks for improving scalability, communication efficiency, and integrating advanced privacy-preserving techniques.

This article presents a case of a patient with a broad ligament perivascular epithelioid cell tumor (PEComa), focusing on the analysis of its imaging features in CT and MRI to enhance understanding and awareness of this rare tumor.

This article reports a case of a 27-year-old married woman who was found to have a pelvic mass two years ago. After detailed examination at our hospital, imaging studies, including enhanced CT and MRI, revealed a cystic-solid lesion in the left adnexal area, with preoperative considerations of ovarian cystadenoma or uterine leiomyoma. She was referred to a specialized obstetrics and gynecology hospital for surgery, and the postoperative pathology was diagnosed as PEComa. She has been undergoing regular follow-up at our hospital post-surgery. One year after the operation, her laboratory tests showed no significant abnormalities, and imaging studies did not reveal any signs of metastasis.

Uterine broad ligament PEComa is a rare tumor, and accurate imaging features and classification criteria can aid in improving preoperative diagnosis. A deeper understanding of the clinical and imaging characteristics of this rare disease is significant for enhancing diagnostic accuracy and treatment outcomes.

Ultrasound is routinely used for thyroid nodule diagnosis, yet distinguishing benign from malignant TI-RADS category 4 nodules remains challenging. This study has integrated two-dimensional ultrasound, shear wave elastography (SWE), and contrast-enhanced ultrasound (CEUS) features via machine learning to improve diagnostic accuracy for these nodules.

A total of 117 TI-RADS 4 thyroid nodules from 108 patients were included and classified as benign or malignant based on pathological results. Two-dimensional ultrasound, CEUS, and SWE were compared. Predictive features were selected using LASSO regression. Feature importance was further validated using Random Forest, SVM, and XGBoost algorithms. A logistic regression model was constructed and visualized as a nomogram. Model performance was assessed using receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis (DCA).

Malignant nodules exhibited significantly elevated serum FT3, FT4, FT3/FT4, TSH, and TI-RADS scores compared to benign lesions. Key imaging discriminators included unclear boundaries, aspect ratio ≥1, low internal echo, microcalcifications on ultrasound; enhancement degree, circumferential enhancement, and excretion on CEUS; and elevated SWE values (Emax, Emean, Esd, etc.) and altered CEUS quantitative parameters (PE, WiR, WoR, etc.) (all P< 0.05). A nomogram integrating four optimal predictors, including Emax, FT4, TI-RADS, and ∆PE, demonstrated robust predictive performance upon validation by ROC, calibration, and DCA curve analysis.

The nomogram incorporating Emax, FT4, TI-RADS, and ∆PE showed high predictive accuracy, particularly for papillary carcinoma in TI-RADS 4 nodules. Its applicability may, however, be constrained by the single-center retrospective design and limited pathological coverage.

The multimodal ultrasound-based machine learning model effectively predicted malignancy in TI-RADS category 4 thyroid nodules.

We developed and validated a novel CT-based radiomics nomogram aimed at improving the differentiation between checkpoint inhibitor-related pneumonitis (CIP) and COVID-19 pneumonia, addressing the persistent clinical uncertainty in pneumonia diagnosis.

A total of 97 patients were enrolled. CT image segmentation was performed, extracting 1,688 radiomics features. Feature selection was conducted using variance thresholding, the least absolute shrinkage and selection operator (LASSO) regression, and the Select K Best methods, resulting in the identification of 33 optimal features. Several classification models (K-Nearest Neighbors [KNN], Support Vector Machine [SVM], and Stochastic Gradient Descent [SGD]) were trained and validated using a 70:30 split and fivefold cross-validation. A radiomics nomogram was subsequently developed, incorporating the radiomics signature (Rad-score) alongside clinical factors. It was assessed based on area under the curve (AUC), sensitivity, specificity, and decision curve analysis (DCA).

The SVM classifier exhibited the highest performance, achieving an AUC of 0.988 in the training cohort and 0.945 in the validation cohort. The constructed radiomics nomogram demonstrated a markedly improved predictive accuracy compared to the clinical model alone (AUC: 0.853 vs. 0.810 in training; 0.932 vs. 0.924 in validation). Calibration curves indicated a strong alignment of the model with observed outcomes, while DCA confirmed a greater net benefit across various threshold probabilities.

A radiomics nomogram integrated with radiomics signatures, demographics, and CT findings facilitates CIP differentiation from COVID-19, improving diagnostic efficacy.

Radiomics acts as a potential modality to supplement conventional medical examinations.

Colorectal cancer (CRC) is a leading cause of cancer-related morbidity and mortality. Accurate differentiation of tumor grade is crucial for prognosis and treatment planning. This study aimed to evaluate the diagnostic value of dual-source CT dual-energy technology parameters in distinguishing CRC differentiation grades.

A retrospective analysis was conducted on 87 surgically and pathologically confirmed CRC patients (64 with medium-high differentiation and 23 with low differentiation) who underwent dual-source CT dual-energy enhancement scanning. Normalized iodine concentration (NIC), spectral curve slope (K), and dual-energy index (DEI) of the tumor center were measured in arterial and venous phases. Differences in these parameters between differentiation groups were compared, and ROC curve analysis was performed to assess diagnostic efficacy.

The low-differentiation group exhibited significantly higher NIC, K, and DEI values in both arterial and venous phases compared to the medium-high differentiation group (P < 0.01). In the arterial phase, NIC, K, and DEI yielded AUC values of 0.920, 0.770, and 0.903, respectively, with sensitivities of 95.7%, 65.2%, and 91.3%, and specificities of 82.8%, 75.0%, and 75.0%, respectively. In the venous phase, AUC values were 0.874, 0.837, and 0.886, with sensitivities of 91.3%, 82.6%, and 91.3%, and specificities of 68.75%, 75.0%, and 73.4%. NIC in the arterial phase showed statistically superior diagnostic performance compared to K values (P < 0.05).

Dual-energy CT parameters, particularly NIC in the arterial phase, demonstrate high diagnostic accuracy in differentiating CRC grades. These findings suggest that quantitative dual-energy CT metrics can serve as valuable non-invasive tools for tumor characterization, aiding in clinical decision-making. Study limitations include its retrospective design and relatively small sample size.

NIC, K, and DEI values in dual-energy CT scans are highly effective in distinguishing CRC differentiation grades, with arterial-phase NIC showing the highest diagnostic performance. These parameters may enhance preoperative assessment and personalized treatment strategies for CRC patients.

Prenatal intervention with fetoscopic endoluminal tracheal occlusion (FETO) using a balloon can stimulate lung growth and improve neonatal survival for moderate and severe congenital diaphragmatic hernia (CDH). Quantitative parameters measured on magnetic resonance imaging (MRI) can guide the treatment of CDH and evaluate changes after FETO treatment.

We reported on five cases of isolated left congenital diaphragmatic hernia (CDH) in fetuses who underwent FETO surgery. We conducted a comparison of the MRI images before and after FETO treatment and analyzed the correlation between the observed changes and the clinical outcomes of the neonates after delivery.

MRI can precisely provide the anatomical details of CDH and quantitatively analyze changes in fetal lung volume before and after FETO surgery.

Cytotoxic lesions of the corpus callosum (CLOCC) are a rare clinical-radiological syndrome with an unclear specific pathogenesis, and cases occurring consecutively in siblings are exceptionally uncommon. This study reports two pediatric siblings with CLOCC (one experiencing two episodes), highlighting the potential role of genetic susceptibility in its pathogenesis. The findings contribute to the limited literature on familial CLOCC and recurrent cases in children.

Two brothers (aged 9 and 12) presented with sudden-onset aphasia and unilateral limb weakness, preceded by rhinorrhea. Magnetic resonance imaging (MRI) revealed reversible lesions in the splenium of the corpus callosum and bilateral frontoparietal white matter, consistent with CLOCC. Both patients received immunomodulatory therapy (e.g., corticosteroids, intravenous immunoglobulin) and symptomatic treatment, achieving full neurological recovery within approximately one week. The elder sibling had a recurrence two years later (when the patient was 14 years old) with similar imaging findings. Laboratory tests ruled out common infections, and cerebrospinal fluid analysis was unremarkable.

This case underscores CLOCC as a heterogeneous condition with possible genetic predisposition, as evidenced by its occurrence in siblings and recurrence in one sibling. While prognosis is generally favorable, the observed sibling clustering and individual recurrence suggest the need for further research into underlying genetic or immunological mechanisms.

Early detection of gastric cancer remains challenging for many of the current imaging techniques. Recent advancements in reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) have shown promise in improving the visualization of small anatomical structures. This study aimed to evaluate and compare the diagnostic performance of rFOV DWI with multi-detector computed tomography (MDCT) and conventional full field of view (fFOV) DWI for detecting early gastric cancer (EGC).

This retrospective study included 43 patients with pathologically confirmed EGC. All participants underwent pre-treatment imaging, including CT scans and MRI with a prototype rFOV DWI and conventional fFOV DWI at 3 Tesla. Quantitative (signal-to-noise ratio [SNR], contrast-to-noise ratio [CNR]) and qualitative (subjective image quality) assessments were performed. Diagnostic performance was evaluated using receiver operating characteristic (ROC) curves and area-under-the-curve (AUC) analysis.

rFOV DWI demonstrated significantly higher SNR and CNR compared with fFOV DWI (P < 0.05). Subjective image quality scores were also superior for rFOV DWI (P < 0.05). In lesion detection, rFOV DWI showed higher sensitivity (0.705) than CT (0.636) and fFOV DWI (0.523). ROC analysis revealed that rFOV DWI had a higher AUC (0.829, 95% CI [0.764, 0.882]) than fFOV DWI (0.734, 95% CI [0.661, 0.798], P = 0.02) and a modest improvement over CT (0.799, 95% CI [0.731, 0.856], P = 0.51).

The findings suggest that rFOV DWI provides superior image quality and diagnostic accuracy for EGC detection compared with conventional fFOV DWI. While it showed a trend toward better performance than CT, further studies with larger cohorts are needed to validate these results.

rFOV DWI offers improved image quality and diagnostic performance for early gastric cancer detection compared with fFOV DWI, with a potential advantage over CT. This technique may enhance early diagnosis and clinical decision-making in gastric cancer management.

This study aimed to investigate nerve fiber bundle damage associated with spinocerebellar degeneration, a dominant inherited neurological disorder, using magnetic resonance imaging (MRI) with diffusion tensor imaging (DTI).

Four cases of spinocerebellar degeneration and ten matched healthy subjects were retrospectively enrolled. DTI software was used for processing and analysis.

All patients had an abnormal spinocerebellar ataxia (SCA) type 3 gene mutation, with cerebellar and brainstem atrophy, a decreased signal in the pons and projection fibers. Significant interruption and destruction were revealed in the midline of the cerebellar peduncle, cerebellar arcuate fibers, and the spinothalamic and spinocerebellar tracts. Significant (p <0.05) decreases were detected in FA values in the cerebellar peduncle (0.51±0.04 vs. 0.68±0.02), cerebellar arcuate fibers (0.37±0.08 vs. 0.51±0.05), spinothalamic tract (0.42±0.03 vs. 0.49±0.05), and spinocerebellar tract (0.44±0.06 vs. 0.52±0.06) compared with healthy controls. Compared with healthy controls, significant (p <0.05) increases were detected in ADC values in the cerebellar peduncle (0.84±0.11 vs. 0.67±0.03), cerebellar arcuate fibers (0.87±0.12 vs. 0.66±0.05), spinothalamic tract (0.89±0.13 vs. 0.70±0.03) within the brainstem, and spinocerebellar tract (0.79±0.07 vs. 0.69±0.06).

The MRI DTI technique provides sufficient information for studying spinocerebellar degeneration and for conducting further research on its etiology and diagnosis. Some limitations were present, including the retrospective and single-center study design, a limited patient sample, and enrollment of only Chinese patients.

The MRI DTI technique can clearly demonstrate the degree of damage to nerve fiber bundles in the cerebellum and the adjacent relationship between the fiber bundles entering and exiting the cerebellum in patients with spinocerebellar degeneration.

Accurate segmentation of small and irregular pulmonary nodules remains a significant challenge in lung cancer diagnosis, particularly in complex imaging backgrounds. Traditional U-Net models often struggle to capture long-range dependencies and integrate multi-scale features, limiting their effectiveness in addressing these challenges. To overcome these limitations, this study proposes an enhanced U-Net hybrid model that integrates multiple attention mechanisms to enhance feature representation and improve the precision of segmentation outcomes.

The assessment of the proposed model was conducted using the LUNA16 dataset, which contains annotated CT scans of pulmonary nodules. Multiple attention mechanisms, including Spatial Attention (SA), Dilated Efficient Channel Attention (Dilated ECA), Convolutional Block Attention Module (CBAM), and Squeeze-and-Excitation (SE) Block, were integrated into a U-Net backbone. These modules were strategically combined to enhance both local and global feature representations. The model’s architecture and training procedures were designed to address the challenges of segmenting small and irregular pulmonary nodules.

The proposed model achieved a Dice similarity coefficient of 84.30%, significantly outperforming the baseline U-Net model. This result demonstrates improved accuracy in segmenting small and irregular pulmonary nodules.

The integration of multiple attention mechanisms significantly enhances the model’s ability to capture both local and global features, addressing key limitations of traditional U-Net architectures. SA preserves spatial features for small nodules, while Dilated ECA captures long-range dependencies. CBAM and SE further refine feature representations. Together, these modules improve segmentation performance in complex imaging backgrounds. A potential limitation is that performance may still be constrained in cases with extreme anatomical variability or low-contrast lesions, suggesting directions for future research.

The Enhanced U-Net hybrid model outperforms the traditional U-Net, effectively addressing challenges in segmenting small and irregular pulmonary nodules within complex imaging backgrounds.

Accurate liver volumetry is crucial for hepatectomy. In this study, we developed and validated a deep learning system for automated liver volumetry in patients undergoing hepatectomy, both preoperatively and at 7 days and 3 months postoperatively.

A 3D U-Net model was trained on CT images from three time points using a five-fold cross-validation approach. Model performance was assessed with standard metrics and comparatively evaluated across the time points.

The model achieved a mean Dice Similarity Coefficient (DSC) of 94.31% (preoperative: 94.91%; 7-day post-operative: 93.45%; 3-month post-operative: 94.57%) and a mean recall of 96.04%. The volumetric difference between predicted and actual volumes was 1.01 ± 0.06% preoperatively, compared to 1.04 ± 0.03% at other time points (p < 0.05).

This study demonstrates a novel capability to automatically track post-hepatectomy regeneration using AI, offering significant potential to enhance surgical planning and patient monitoring. A key limitation, however, was that the direct correlation with clinical outcomes was not assessed due to constraints of the current dataset. Therefore, future studies using larger, multi-center datasets are essential to validate the model's clinical and prognostic utility.

The developed artificial intelligence model successfully and accurately measured liver volumes across three critical post-hepatectomy time points. These findings support the use of this automated technology as a precise and reliable tool to assist in surgical decision-making and postoperative assessment, providing a strong foundation for enhancing patient care.

Heart failure (HF) is classified into three types based on left ventricular ejection fraction (LVEF). A newly developed transthoracic three-dimensional (3D) echocardiography Heart-Model (HM) offers quick analysis of the volume and function of the left atrium (LA) and left ventricle (LV). This study aimed to determine the value of the HM in HF patients.

A total of 117 patients with HF were divided into three groups according to EF: preserved EF (HFpEF, EF ≥50%), mid-range EF (HFmrEF, EF =41%–49%), and reduced EF (HFrEF, EF ≤40%). The HM was applied to analyze 3D cardiac functional parameters. LVEF was obtained using Simpson’s biplane method. The N-terminal pro-B-type natriuretic peptide (NT-proBNP) concentration was measured.

Significant differences in age, female proportion, body mass index, and comorbidities were observed among the three groups. With decreasing EF across the groups, the 3D volumetric parameters of the LA and LV increased, while LVEF decreased. The LV E/e' was significantly higher in HFrEF patients than in HFpEF patients. LVEF measurement was achieved in significantly less time with the HM compared with the conventional Simpson’s biplane method. The NT-proBNP concentration increased in the following pattern: HFrEF > HFmrEF > HFpEF. The NT-proBNP concentration correlated positively with LV volume and negatively with LVEF from both the HM and Simpson’s biplane method.

LA and LV volumes increase, and the derived LV systolic function decreases with increasing HF severity determined by the HM. The functional parameters measurements provided by the HM are associated with laboratory indicators, indicating the feasibility of using the HM in routine clinical application.

Deep learning methods were employed to perform harmonization analysis on whole-brain scans obtained from 1.5-T and 3.0-T scanners, aiming to increase comparability between different magnetic resonance imaging (MRI) scanners.

Thirty patients evaluated in Beijing Tsinghua Changgung Hospital between August 2020 and March 2023 were included in this retrospective study. Three MRI scanners were used to scan patients, and automated brain image segmentation was performed to obtain volumes of different brain regions. Differences in regional volumes across scanners were analyzed using repeated-measures analysis of variance. For regions showing significant differences, super-resolution deep learning was applied to enhance consistency, with subsequent comparison of results. For regions still exhibiting differences, the Intraclass Correlation Coefficient (ICC) was calculated and the consistency was evaluated using Cicchetti's criteria.

Average whole-brain volumes for different scanners among patients were 1152.36mm³ (SD = 95.34), 1136.92mm³ (SD = 108.21), and 1184.00mm³ (SD = 102.78), respectively. Analysis revealed significant variations in all 12 brain regions (p<0.05), indicating a lack of comparability among imaging results obtained from different magnetic field strengths. After deep learning-based consistency optimization, most brain regions showed no significant differences, except for six regions where differences remained significant. Among these, three regions demonstrated ICC values of 0.868 (95%CI 0.771-0.931), 0.776 (95%CI 0.634-0.877), and 0.893 (95%CI 0.790-0.947), indicating high reproducibility and comparability.

This study demonstrates a deep learning-based harmonization method that effectively mitigates field strength-related inconsistencies between 1.5-T and 3.0-T MRI, significantly enhancing their comparability. The high ICCs observed in key brain regions confirm the robustness of this approach, paving the way for reliable clinical application across different scanners. A noted limitation is its current focus on brain imaging, which warrants future research to extend its applicability to other anatomical areas.

This study employed a novel machine learning approach that significantly improved the comparability of imaging results from patients using different magnetic field strengths and various models of MRI scanners. Furthermore, it enhanced the consistency of central nervous system image segmentation.

This study aimed to evaluate the effectiveness of intelligent quick magnetic resonance (IQMR) for accelerating brain MRI scanning and improving image quality in patients with acute ischemic stroke.

In this prospective study, 58 patients with acute ischemic stroke underwent head MRI examinations between July 2023 and January 2024, including diffusion-weighted imaging and both conventional and accelerated T1-weighted, T2-weighted, and T2 fluid-attenuated inversion recovery fat-saturated (T2-FLAIR) sequences. Accelerated sequences were processed using IQMR, producing IQMR-T1WI, IQMR-T2WI, and IQMR-T2-FLAIR images. Image quality was assessed qualitatively by two readers using a five-point Likert scale (1 = non-diagnostic to 5 = excellent). Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of lesions and surrounding tissues were quantitatively measured. The Alberta Stroke Program Early CT Score (ASPECTS) was used to evaluate ischemia severity.

Total scan time was reduced from 5 minutes 9 seconds to 2 minutes 40 seconds, accounting for a reduction of 48.22%. IQMR significantly improved SNR/CNR in accelerated sequences (P < .05), achieving parity with routine sequences (P > .05). Qualitative scores for lesion conspicuity and internal display improved post-IQMR (P < .05).. ASPECTS showed no significant difference between IQMR and routine images (P = 0.79; ICC = 0.91–0.93).

IQMR addressed MRI’s slow scanning limitation without hardware modifications, enhancing diagnostic efficiency. The results have been found to align with advancements in deep learning. Limitations included the small sample size and the exclusion of functional sequences.

IQMR could significantly reduce brain MRI scanning time and enhance image quality in patients with acute ischemic stroke.

This case highlights the rare but life-threatening complication of carotid blowout syndrome (CBS) after radiotherapy for nasopharyngeal carcinoma (NPC). It is characterized by rupture of the carotid artery, often occurring months or years after treatment. Early diagnosis and timely intervention are essential to improve clinical outcomes.

A 45-year-old woman with NPC developed recurrent epistaxis 31 months after chemoradiotherapy. MRI and MRA ruled out tumor recurrence. High-resolution vessel wall imaging (VWI) revealed eccentric thickening, irregular enhancement, and a pseudoaneurysm in the lacerum segment of the left internal carotid artery (ICA), which was confirmed by CTA and DSA. The patient underwent embolization and remained stable at 1-year follow-up.

This case underscores the value of VWI in detecting CBS-related vascular changes. Imaging is crucial for early diagnosis and timely intervention in high-risk patients with NPC who have undergone radiotherapy.

The pool sign, an emerging MRI biomarker for differentiating brain metastases (BM) from primary neoplasms, is primarily documented in case reports. Systematic data on its prevalence and determinants in BM among patients with lung cancer are lacking. This study aims to evaluate the occurrence of the pool sign and identify factors associated with its presence.

Between January 2017 and August 2024, data from 6,004 lung cancer patients were retrospectively extracted from the electronic health records system. The clinical and demographic characteristics, along with BM MRI features, were compared between the pool sign and non-pool sign groups using univariate and multivariate analyses.

A total of 427 patients (81 women; mean age, 62.17 years) were enrolled in the study. The pool sign was observed in 29 patients (6.8%). The inter-reader reliability for the pool sign ranged from moderate to substantial (κ=0.61–0.80), while the intra-reader reliability was moderate (κ=0.6). In the univariate analysis, a statistically significant difference was observed in the volume size of metastases between the pool sign group and the non-pool sign group (median 4.8 vs. 0.5, P < 0.0001). This finding suggests that the presence of the pool sign is more likely associated with BMs exhibiting relatively larger tumor volumes. Additionally, the prevalence of solid-cystic masses was significantly higher in the pool sign group compared to the non-pool sign group, with rates of 79.3% and 44.5%, respectively (P = 0.0014). However, there were no statistically significant differences in other examined variables. In the multivariate analysis, the findings demonstrated that an increase in tumor volume (OR = 1.050, 95% CI 1.025-1.076, P < 0.001) and the presence of a solid-cystic mass (OR = 3.666, 95% CI 1.159-11.595, P = 0.027) were significantly correlated with a higher probability of pool sign occurrence.

The pool sign occurs in 6.8% of BM in patients with lung cancer and is independently associated with larger lesion volume and solid-cystic morphology. Its diagnostic utility warrants further validation.

This study aimed to explore the value of a machine learning model based on spectral computed tomography (CT) for predicting the programmed death ligand-1 (PD-L1) expression in resectable non-small cell lung cancer (NSCLC).

In this retrospective study, 131 instances of NSCLC who underwent preoperative spectral CT scanning were enrolled and divided into a training cohort (n = 92) and a test cohort (n = 39). Clinical-imaging features and quantitative parameters of spectral CT were analyzed. Variable selection was performed using univariate and multivariate logistic regression, as well as LASSO regression. We used eight machine learning algorithms to construct a PD-L1 expression predictive model. We utilized sensitivity, specificity, accuracy, calibration curve, the area under the curve (AUC), F1 score and decision curve analysis (DCA) to evaluate the predictive value of the model.

After variable selection, cavitation, ground-glass opacity, and CT40keV and CT70keV at venous phase were selected to develop eight machine learning models. In the test cohort, the extreme gradient boosting (XGBoost) model achieved the best diagnostic performance (AUC = 0.887, sensitivity = 0.696, specificity = 0.937, accuracy = 0.795 and F1 score = 0.800). The DCA indicated favorable clinical utility, and the calibration curve demonstrated the model’s high level of prediction accuracy.

Our study indicated that the machine learning model based on spectral CT could effectively evaluate the PD-L1 expression in resectable NSCLC.

The XGBoost model, integrating spectral CT quantitative parameters and imaging features, demonstrated considerable potential in predicting PD-L1 expression.

Lung cancer remains a leading cause of cancer-related mortality worldwide. While deep learning approaches show promise in medical imaging, comprehensive comparisons of classifier combinations with DenseNet architectures for lung cancer classification are limited.

The study investigates the performance of different classifier combinations, Support Vector Machine (SVM), Artificial Neural Network (ANN), and Multi-Layer Perceptron (MLP), with DenseNet architectures for lung cancer classification using chest CT scan images.

A comparative analysis was conducted on 1,000 chest CT scan images comprising Adenocarcinoma, Large Cell Carcinoma, Squamous Cell Carcinoma, and normal tissue samples. Three DenseNet variants (DenseNet-121, DenseNet-169, DenseNet-201) were combined with three classifiers: SVM, ANN, and MLP. Performance was evaluated using accuracy, Area Under the Curve (AUC), precision, recall, specificity, and F1-score with an 80-20 train-test split.

The optimal model achieved 92% training accuracy and 83% test accuracy. Performance across models ranged from 81% to 92% for training accuracy and 73% to 83% for test accuracy. The most balanced combination demonstrated robust results (training: 85% accuracy, 0.99 AUC; test: 79% accuracy, 0.95 AUC) with minimal overfitting.

Deep learning approaches effectively categorize chest CT scans for lung cancer detection. The MLP-DenseNet-169 combination's 83% test accuracy represents a promising benchmark. Limitations include retrospective design and a limited sample size from a single source.

This evaluation demonstrates the effectiveness of combining DenseNet architectures with different classifiers for lung cancer CT classification. The MLP-DenseNet-169 achieved optimal performance, while SVM-DenseNet-169 showed superior stability, providing valuable benchmarks for automated lung cancer detection systems.

Advancements in computational methods in medicine have brought about extensive improvement in the diagnosis of illness, with machine learning models such as Convolutional Neural Networks leading the charge. This work introduces PneumoNet, a novel deep-learning model designed for accurate pneumonia detection from chest X-ray images. Pneumonia detection from chest X-ray images is one of the greatest challenges in diagnostic practice and medical imaging. Proper identification of standard chest X-ray views or pneumonia-specific views is required to perform this task effectively. Contemporary methods, such as classical machine learning models and initial deep learning methods, guarantee good performance but are generally marred by accuracy, generalizability, and preprocessing issues. These techniques are generally marred by clinical usage constraints like high false positives and poor performance over a broad spectrum of datasets.

A novel deep learning architecture, PneumoNet, has been proposed as a solution to these problems. PneumoNet applies a convolutional neural network (CNN) structure specifically employed for the improvement of accuracy and precision in image classification. The model employs several layers of convolution as well as pooling, followed by fully connected dense layers, for efficient extraction of intricate features in X-ray images. The innovation of this approach lies in its advanced layer structure and its training, which are optimized to enhance feature extraction and classification performance greatly. The model proposed here, PneumoNet, has been cross-validated and trained on a well-curated dataset that includes a balanced representation of normal and pneumonia cases.

Quantitative results demonstrate the model’s performance, with an overall accuracy of 98% and precision values of 96% for normal and 98% for pneumonia cases. The recall values for normal and pneumonia cases are 96% and 98%, respectively, highlighting the consistency of the model.

These performance measures collectively indicate the promise of the proposed model to improve the diagnostic process, with a substantial advancement over current methods and paving the way for its application in clinical practice.

Accurate preoperative grading of adult-type diffuse gliomas is crucial for personalized treatment. Emerging evidence suggests tumor cell infiltration extends beyond peritumoral edema, but the predictive value of radiomics features in these regions remains underexplored.

A retrospective analysis was conducted on 180 patients from the UCSF-PDGM dataset, split into training (70%) and validation (30%) cohorts. Intratumoral volumes (VOI_I, including tumor body and edema) and peritumoral volumes (VOI_P) at 7 expansion distances (1–5, 10, 15 mm) were analyzed. Feature selection involved Levene's test, t-test, mRMR, and LASSO regression. Radiomics models (VOI_I, VOI_P, and combined intratumoral-peritumoral models) were evaluated using AUC, accuracy, sensitivity, specificity, and F1 score, with Delong tests for comparisons.

The combined radiomics models established for the intratumoral and peritumoral 1-5mm ranges (VOI_1-5mm) showed better predictive performance than the VOI_I model (AUC=0.815/0.672), among which the VOI_1 model performed the best: in the training cohort, the AUC was 0.903 (accuracy=0.880, sensitivity=0.905, specificity=0.855, F1=0.884); in the validation cohort, the AUC was 0.904 (accuracy=0.852, sensitivity=0.778, specificity=0.926, F1=0.840). This model significantly outperformed the VOI_I model (p<0.05) and the 10/15mm combined models (p<0.05).

The peritumoral regions within 5 mm beyond the edematous area contain critical grading information, likely reflecting subtle tumor infiltration. Model performance declined with larger peritumoral distances, possibly due to increased normal tissue dilution.

The radiomics features of the intratumoral region and the peritumoral region within 5 mm can optimize the preoperative grading of gliomas, providing support for surgical planning and prognostic evaluation.

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.