ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

Objective: To explore glymphatic impairment in pediatric refractory epilepsy (RE) using multi-parameter magnetic resonance imaging (MRI), assess its relationship with white-matter (WM) abnormalities and clinical indicators, and preliminarily evaluate the performance of multi-parameter MRI in discriminating RE from drug-sensitive epilepsy (DSE). Materials and Methods: We retrospectively included 70 patients with DSE (mean age, 9.7 ± 3.5 years; male:female, 37:33) and 26 patients with RE (9.0 ± 2.9 years; male:female, 12:14). The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as well as fractional anisotropy (FA), mean diffusivity (MD), and nodal efficiency values were measured and compared between patients with RE and DSE. With sex and age as covariables, differences in the FA and MD values were analyzed using tract-based spatial statistics, and nodal efficiency was analyzed using a linear model. Pearson’s partial correlation was analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the discrimination performance of the MRI-based machine-learning models through five-fold cross-validation. Results: In the RE group, FA decreased and MD increased in comparison with the corresponding values in the DSE group, and these differences mainly involved the callosum, right and left corona radiata, inferior and superior longitudinal fasciculus, and posterior thalamic radiation (threshold-free cluster enhancement, P < 0.05). The RE group also showed reduced nodal efficiency, which mainly involved the limbic system, default mode network, and visual network (false discovery rate, P < 0.05), and significantly lower DTI-ALPS index (F = 2.0, P = 0.049). The DTI-ALPS index was positively correlated with FA (0.25 ≤ r ≤ 0.32) and nodal efficiency (0.22 ≤ r ≤ 0.37), and was negatively correlated with the MD (-0.24 ≤ r≤ -0.34) and seizure frequency (r = -0.47). A machine-learning model combining DTI-ALPS, FA, MD, and nodal efficiency achieved a cross-validated ROC curve area of 0.83 (sensitivity, 78.2%; specificity, 84.8%). Conclusion Pediatric patients with RE showed impaired glymphatic function in comparison with patients with DSE, which was correlated with WM abnormalities and seizure frequency. Multi-parameter MRI may be feasible for distinguishing RE from DSE.

Objective: To explore glymphatic impairment in pediatric refractory epilepsy (RE) using multi-parameter magnetic resonance imaging (MRI), assess its relationship with white-matter (WM) abnormalities and clinical indicators, and preliminarily evaluate the performance of multi-parameter MRI in discriminating RE from drug-sensitive epilepsy (DSE). Materials and Methods: We retrospectively included 70 patients with DSE (mean age, 9.7 ± 3.5 years; male:female, 37:33) and 26 patients with RE (9.0 ± 2.9 years; male:female, 12:14). The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as well as fractional anisotropy (FA), mean diffusivity (MD), and nodal efficiency values were measured and compared between patients with RE and DSE. With sex and age as covariables, differences in the FA and MD values were analyzed using tract-based spatial statistics, and nodal efficiency was analyzed using a linear model. Pearson’s partial correlation was analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the discrimination performance of the MRI-based machine-learning models through five-fold cross-validation. Results: In the RE group, FA decreased and MD increased in comparison with the corresponding values in the DSE group, and these differences mainly involved the callosum, right and left corona radiata, inferior and superior longitudinal fasciculus, and posterior thalamic radiation (threshold-free cluster enhancement, P < 0.05). The RE group also showed reduced nodal efficiency, which mainly involved the limbic system, default mode network, and visual network (false discovery rate, P < 0.05), and significantly lower DTI-ALPS index (F = 2.0, P = 0.049). The DTI-ALPS index was positively correlated with FA (0.25 ≤ r ≤ 0.32) and nodal efficiency (0.22 ≤ r ≤ 0.37), and was negatively correlated with the MD (-0.24 ≤ r≤ -0.34) and seizure frequency (r = -0.47). A machine-learning model combining DTI-ALPS, FA, MD, and nodal efficiency achieved a cross-validated ROC curve area of 0.83 (sensitivity, 78.2%; specificity, 84.8%). Conclusion Pediatric patients with RE showed impaired glymphatic function in comparison with patients with DSE, which was correlated with WM abnormalities and seizure frequency. Multi-parameter MRI may be feasible for distinguishing RE from DSE.

Objective: To explore glymphatic impairment in pediatric refractory epilepsy (RE) using multi-parameter magnetic resonance imaging (MRI), assess its relationship with white-matter (WM) abnormalities and clinical indicators, and preliminarily evaluate the performance of multi-parameter MRI in discriminating RE from drug-sensitive epilepsy (DSE). Materials and Methods: We retrospectively included 70 patients with DSE (mean age, 9.7 ± 3.5 years; male:female, 37:33) and 26 patients with RE (9.0 ± 2.9 years; male:female, 12:14). The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as well as fractional anisotropy (FA), mean diffusivity (MD), and nodal efficiency values were measured and compared between patients with RE and DSE. With sex and age as covariables, differences in the FA and MD values were analyzed using tract-based spatial statistics, and nodal efficiency was analyzed using a linear model. Pearson’s partial correlation was analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the discrimination performance of the MRI-based machine-learning models through five-fold cross-validation. Results: In the RE group, FA decreased and MD increased in comparison with the corresponding values in the DSE group, and these differences mainly involved the callosum, right and left corona radiata, inferior and superior longitudinal fasciculus, and posterior thalamic radiation (threshold-free cluster enhancement, P < 0.05). The RE group also showed reduced nodal efficiency, which mainly involved the limbic system, default mode network, and visual network (false discovery rate, P < 0.05), and significantly lower DTI-ALPS index (F = 2.0, P = 0.049). The DTI-ALPS index was positively correlated with FA (0.25 ≤ r ≤ 0.32) and nodal efficiency (0.22 ≤ r ≤ 0.37), and was negatively correlated with the MD (-0.24 ≤ r≤ -0.34) and seizure frequency (r = -0.47). A machine-learning model combining DTI-ALPS, FA, MD, and nodal efficiency achieved a cross-validated ROC curve area of 0.83 (sensitivity, 78.2%; specificity, 84.8%). Conclusion Pediatric patients with RE showed impaired glymphatic function in comparison with patients with DSE, which was correlated with WM abnormalities and seizure frequency. Multi-parameter MRI may be feasible for distinguishing RE from DSE.

Background Per- and polyfluoroalkyl substances (PFAS), a group of persistent organic pollutants associated with adverse health effects including hepatotoxicity, immunosuppression, and carcinogenicity, have undergone risk assessments by multiple international organizations, with dietary exposure being the primary pathway. Objective To characterize the exposure to PFAS from food and drinking water sources of elderly residents in Songjiang District of Shanghai and to evaluate associated health risk and health effects. Methods A cross-sectional study was conducted from May to July 2024 in Songjiang District based on the Shanghai Suburban Adult Cohort and Biobank (SSACB) cohort. Dietary surveys were administered via face-to-face interviews among older adults aged 65 years and above, yielding 4 583 valid questionnaires. The estimated daily intake (EDI) of PFAS was calculated by integrating data from the Sixth National Dietary Survey and recent literature on PFAS concentrations in food and drinking water in Shanghai. Health risk assessment was performed using health-based guideline values (HBGV) proposed by various institutions and studies. Additionally, correlation analysis and linear regression modeling of EDI and biochemical indicators in the elderly were conducted to evaluate potential adverse health effects. Results The elderly population in Songjiang District exhibited dietary characteristics consistent with the Eastern Healthy Diet Pattern. Among PFAS compounds, PFOA showed the highest level of oral exposure [mean: 1.495 ng·(kg·d⁻¹)], followed by PFOS [mean: 0.637 ng·(kg·d⁻¹)], PFHxS [mean: 0.636 ng·(kg·d⁻¹)], and PFBS [mean: 0.273 ng·(kg·d⁻¹)]. Specifically, drinking water was the primary source of PFOA [1.415 ng·(kg·d⁻¹), accounting for 94.60%], while aquatic products were the major source of PFOS [0.278 ng·(kg·d⁻¹), accounting for 43.66%]. Using the HBGV derived by China's epidemiological studies, the mean hazard index (HI) for PFAS exposure was 1.39, indicating 54.35% of the population had potential health risks (HI>1). Following the 2024 standard established by the Food Safety Commission of Japan (FSCJ), the HI value dropped to 0.11, suggesting negligible risk. PFAS exposure was negatively associated with triglyceride levels and the indicators of liver and kidney function, but positively associated with low-density lipoprotein cholesterol (LDL-C) and lung cancer markers in the elderly residents. Conclusion PFAS exposure among the elderly residents in Songjiang District is predominantly attributed to PFOA, PFOS, PFHxS, and PFBS, with drinking water and aquatic products identified as primary exposure sources. Current exposure levels demonstrate significant associations with biomarkers of lipid metabolism and lung cancer markers, suggesting potential population health risks. These findings underscore the urgent need to establish HBGV for PFAS compounds based on Chinese population-specific metabolic characteristics.

Forensic medicine has been designated as a first-level discipline,presenting new opportunities and challenges for the development of forensic medicine.Since the 1980s,the establishment of foren-sic medicine discipline and the cultivation of high-level forensic talents have become hot topics in the development of forensic medicine in China.Since the 13th Five-Year Plan,the forensic team of Shanxi Medical University has been aiming at the forefront,proposing the development goals of"Five First-class"and the discipline development path"Six Major Achievements".It has selected benchmark disci-plines,identified gaps in disciplinary development,unified thoughts,formulated completion timelines,concentrated superior resources,assigned tasks to individuals,and created an"Organized Fill-in-the-Blank Format"forensic medicine discipline construction model with the characteristics of the new era.The construction model of forensic medicine has achieved good results in the goals,discipline frame-work,scientific research,talent cultivation,discipline team and platform construction,forming a rela-tively complete discipline construction and management system,and accumulating valuable experience for the construction of first-level discipline and high-level talent cultivation of forensic medicine.

ObjectivePrimary liver cancer, predominantly hepatocellular carcinoma (HCC), is a significant global health issue, ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality. Accurate and early diagnosis of HCC is crucial for effective treatment, as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma (ICC) exhibit different prognoses and treatment responses. Traditional diagnostic methods, including liver biopsy and contrast-enhanced ultrasound (CEUS), face limitations in applicability and objectivity. The primary objective of this study was to develop an advanced, light-weighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images. The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions. MethodsThis retrospective study encompassed a total of 161 patients, comprising 131 diagnosed with HCC and 30 with non-HCC malignancies. To achieve accurate tumor detection, the YOLOX network was employed to identify the region of interest (ROI) on both B-mode ultrasound and CEUS images. A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images. These curves provided critical data for the subsequent analysis and classification process. To analyze the extracted brightness change curves and classify the malignancies, we developed and compared several models. These included one-dimensional convolutional neural networks (1D-ResNet, 1D-ConvNeXt, and 1D-CNN), as well as traditional machine-learning methods such as support vector machine (SVM), ensemble learning (EL), k-nearest neighbor (KNN), and decision tree (DT). The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics: area under the receiver operating characteristic (AUC), accuracy (ACC), sensitivity (SE), and specificity (SP). ResultsThe evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM, 0.56 for ensemble learning, 0.63 for KNN, and 0.72 for the decision tree. These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves. In contrast, the deep learning models demonstrated significantly higher AUCs, with 1D-ResNet achieving an AUC of 0.72, 1D-ConvNeXt reaching 0.82, and 1D-CNN obtaining the highest AUC of 0.84. Moreover, under the five-fold cross-validation scheme, the 1D-CNN model outperformed other models in both accuracy and specificity. Specifically, it achieved accuracy improvements of 3.8% to 10.0% and specificity enhancements of 6.6% to 43.3% over competing approaches. The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification. ConclusionThe 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies, surpassing both traditional machine-learning methods and other deep learning models. This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’ diagnostic capabilities. By improving the accuracy and efficiency of clinical decision-making, this tool has the potential to positively impact patient care and outcomes. Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.

Objective To explore the correlation of bilateral knee joint strength asymmetry with balance,walking ability,and motor function in hemiplegic stroke patients,providing a reference for clinical assessment of stroke patients.Methods A total of 46 hemiplegic stroke patients admitted to the Rehabilitation Medicine Department of People's Hospital of Shijiazhuang from February to December 2023 were selected.According to the Berg Balance Scale(BBS)scores,patients were divided into Group A(BBS score≤20,n=23)and Group B(BBS score>20,n=23).The peak torque and differences of bilateral knee flexors and extensors were compared between two groups.Isokinetic technology was used to assess the differences in peak torque of bilateral knee joints at 60°/s and 120°/s.BBS,Functional Ambulation Classification(FAC),and Fugl-Meyer Assessment of Lower Extremity(FMA-LE)were used to evaluate patients'balance,walking ability,and lower limb motor function.The correlation between bilateral knee joint peak torque and its difference with the scores of three functional scales was analyzed.Results The peak torque of knee flexors and extensors at 60°/s in group A was significantly lower than that in group B(P<0.05).At both 60°/s and 120°/s the differences in peak torque between the healthy and affected sides of knee flexors and extensors were greater than those in group B(P<0.05).At 60°/s,the difference in peak torque of bilateral knee extensors in hemiplegic stroke patients was negatively correlated with the scores of BBS,FAC,and FMA-LE(r=-0.569,-0.582,-0.606,P<0.01),as did the knee flexors(r=-0.534,-0.386,-0.458,P<0.05).At 120°/s,similar negative correlations were observed for both knee extensors(r=-0.304,-0.304,-0.443,P<0.05)and flexors(r=-0.337,-0.349,-0.370,P<0.05).Conclusions Bilateral knee joint strength asymmetry in hemiplegic stroke patients is negatively correlated with balance and walking ability.The difference in strength between the two sides of knee joint may be one of the clinical indicators for evaluating the motor function of stroke patients.

Objective: To explore glymphatic impairment in pediatric refractory epilepsy (RE) using multi-parameter magnetic resonance imaging (MRI), assess its relationship with white-matter (WM) abnormalities and clinical indicators, and preliminarily evaluate the performance of multi-parameter MRI in discriminating RE from drug-sensitive epilepsy (DSE). Materials and Methods: We retrospectively included 70 patients with DSE (mean age, 9.7 ± 3.5 years; male:female, 37:33) and 26 patients with RE (9.0 ± 2.9 years; male:female, 12:14). The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as well as fractional anisotropy (FA), mean diffusivity (MD), and nodal efficiency values were measured and compared between patients with RE and DSE. With sex and age as covariables, differences in the FA and MD values were analyzed using tract-based spatial statistics, and nodal efficiency was analyzed using a linear model. Pearson’s partial correlation was analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the discrimination performance of the MRI-based machine-learning models through five-fold cross-validation. Results: In the RE group, FA decreased and MD increased in comparison with the corresponding values in the DSE group, and these differences mainly involved the callosum, right and left corona radiata, inferior and superior longitudinal fasciculus, and posterior thalamic radiation (threshold-free cluster enhancement, P < 0.05). The RE group also showed reduced nodal efficiency, which mainly involved the limbic system, default mode network, and visual network (false discovery rate, P < 0.05), and significantly lower DTI-ALPS index (F = 2.0, P = 0.049). The DTI-ALPS index was positively correlated with FA (0.25 ≤ r ≤ 0.32) and nodal efficiency (0.22 ≤ r ≤ 0.37), and was negatively correlated with the MD (-0.24 ≤ r≤ -0.34) and seizure frequency (r = -0.47). A machine-learning model combining DTI-ALPS, FA, MD, and nodal efficiency achieved a cross-validated ROC curve area of 0.83 (sensitivity, 78.2%; specificity, 84.8%). Conclusion Pediatric patients with RE showed impaired glymphatic function in comparison with patients with DSE, which was correlated with WM abnormalities and seizure frequency. Multi-parameter MRI may be feasible for distinguishing RE from DSE.