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 compare the ecchymosis of affected limb in the prevention of deep vein thrombosis using low molecular weight heparin sodium and enoxaparin sodium after total knee arthroplasty.Methods:A total of 160 patients (31 males and 129 females) who underwent unilateral knee replacement in Department of Orthopedics of Chengdu Second People's Hospital from Oct. 2020 to Dec. 2023 were included. According to the random number method, all patients were evenly divided into the low molecular weight heparin sodium group (16 males and 64 females) and the enoxaparin sodium group (15 males and 65 females). All patients were treated with low molecular weight heparin sodium or enoxaparin sodium to prevent deep vein thrombosis in the lower limbs after surgery. The ecchymosis area on the affected limb was observed 7 days after surgery, and the incidence and difference in ecchymosis area between the two groups of patients were statistically analyzed. Simultaneously evaluate whether there are differences in hemoglobin, platelet, and coagulation related indicators between the two groups of patients before and after surgery.Results:There were no significant differences in hemoglobin, platelet, and coagulation parameters between the low molecular weight heparin sodium group and the enoxaparin sodium group before and after surgery ( t=1.13, -0.27, -0.47, 0.27, 0.34, -0.27, -0.89, -0.46, P=0.27, 0.34, 0.64, 0.83, 0.74, 0.97, 0.24, 0.65). The incidence of ecchymosis in patients with low molecular weight heparin sodium group and enoxaparin sodium group was 61.25% and 67.50%, respectively, with no statistically significant difference in the incidence of ecchymosis between the two groups ( P=0.41). The average size of ecchymosis in the two groups of patients was (40.40 ± 60.07) cm 2 and (37.41 ± 43.21) cm 2, respectively. And there was no statistically significant difference in ecchymosis area ( P=0.61) . Conclusion:Both patients had limbs’ecchymosis in the process of preventing deep venous thrombosis of lower limbs after total knee replacement. This indicates that the two anticoagulants had a certain effect on postoperative skin ecchymosis of total knee. And the incidence rate and area of ecchymosis of affected limbs were similar in the two groups.

Body weight abnormalities, including overweight, obesity, and underweight, have become a dual public health challenge in Chinese adults: overweight and obesity lead to a variety of chronic complications, while underweight increases the risks of malnutrition, sarcopenia, and organ dysfunction. To systematically address these issues, multidisciplinary experts in endocrinology, sports science, nutrition, and psychiatry from various regions have held multiple weight management seminars. Based on the latest epidemiological data and clinical evidence, they expanded the guideline to include assessment and intervention strategies for underweight, in addition to the core content of obesity management. This guideline outlines the etiological mechanisms, evaluation methods, and multidimensional management strategies for overweight and obesity, covering key areas such as diagnosis and assessment, medical nutrition therapy, exercise prescription, pharmacological intervention, and psychological support. It is intended to provide a scientific and standardized approach to weight management across the adult population, aiming to curb the rising prevalence of obesity, mitigate complications associated with abnormal body weight, and improve nutritional status and overall quality of life.

In November 23, 2023, a patient with 9 digits traumatic crush injury by machine compression was emergently admitted to the Department of Hand and Microsurgery, Sichuan Modern Hospital. Emergency procedures included amputation the distal stumps and replantation of proximal phalanges of left ring and little fingers. Wounds in both hands were temporarily covered with bone cement. On December 4, 2023, reconstruction of 5 digits were performed. Digital defects were: Type Ⅲ defects of left index and middle fingers and right thumb and index fingers and Type IV defect of right middle finger. All 5 reconstructed digits survived. Subsequent refinements yielded favourable outcomes and all donor toes were preserved completely. At the 14-month follow-up, the reconstructed digits exhibited satisfactory appearance and length without difficulties in daily life and at work.

Objective:To compare the ecchymosis of affected limb in the prevention of deep vein thrombosis using low molecular weight heparin sodium and enoxaparin sodium after total knee arthroplasty.Methods:A total of 160 patients (31 males and 129 females) who underwent unilateral knee replacement in Department of Orthopedics of Chengdu Second People's Hospital from Oct. 2020 to Dec. 2023 were included. According to the random number method, all patients were evenly divided into the low molecular weight heparin sodium group (16 males and 64 females) and the enoxaparin sodium group (15 males and 65 females). All patients were treated with low molecular weight heparin sodium or enoxaparin sodium to prevent deep vein thrombosis in the lower limbs after surgery. The ecchymosis area on the affected limb was observed 7 days after surgery, and the incidence and difference in ecchymosis area between the two groups of patients were statistically analyzed. Simultaneously evaluate whether there are differences in hemoglobin, platelet, and coagulation related indicators between the two groups of patients before and after surgery.Results:There were no significant differences in hemoglobin, platelet, and coagulation parameters between the low molecular weight heparin sodium group and the enoxaparin sodium group before and after surgery ( t=1.13, -0.27, -0.47, 0.27, 0.34, -0.27, -0.89, -0.46, P=0.27, 0.34, 0.64, 0.83, 0.74, 0.97, 0.24, 0.65). The incidence of ecchymosis in patients with low molecular weight heparin sodium group and enoxaparin sodium group was 61.25% and 67.50%, respectively, with no statistically significant difference in the incidence of ecchymosis between the two groups ( P=0.41). The average size of ecchymosis in the two groups of patients was (40.40 ± 60.07) cm 2 and (37.41 ± 43.21) cm 2, respectively. And there was no statistically significant difference in ecchymosis area ( P=0.61) . Conclusion:Both patients had limbs’ecchymosis in the process of preventing deep venous thrombosis of lower limbs after total knee replacement. This indicates that the two anticoagulants had a certain effect on postoperative skin ecchymosis of total knee. And the incidence rate and area of ecchymosis of affected limbs were similar in the two groups.

Objective:The greater tuberosity angle(GTA)and critical shoulder angle(CSA)are commonly referred to as radiographic markers which were used to described morphology of the greater tu-berosity and acromion respectively.At present,most international studies focus on the correlation be-tween the above two parameters and rotator cuff tears(RCTs),and their diagnostic value and risk assess-ment.This study attempts to find out the trend of GTA and CSA changes and risk threshold of RCTs,as well as the protective factors and risk factors.Methods:In this study,130 individuals from May 2019 to December 2020 were recruited.According to Southern California Orthopedic Institute(SCOI)classifica-tion,the individuals were divided into four groups retrospectively:Group A,negative control group;Group B,partial tears(articular side);Group C,partial tears(bursal side);Group D,full-thickness tears.GTA and CSA were measured respectively on true anteroposterior position X-ray of shoulder with arm in neutral rotation and performed by the same trained technician team in single-blind.The correla-tions between RCTs and relevant factors were analyzed.Results:According to the area under the receiver operating characteristic curve(AUC),GTA and CSA of RCTs(Groups B,C and D)were 0.736 and 0.673 with 95％confidence interval(CI),the cut-off value of GTA and CSA of RCTs were 70.5° and 39.5° respectively.Comparing with the control group,RCTs groups had significant statistical differences in age and body mass index(BMI)(P＜0.05),especially the full-thickness RCTs(Group D),which was older than Groups A,B and C(P＜0.05,cut-off value:56.5 years old)and shorter than Groups A and B(P＜0.05,cut-off value:1.58 m).Analyzed from scatter plot and regression analysis,there was no linear correlation between GTA and CSA.There were no significant differences in gender,dominant shoulders and smoking between the RCTs groups and the control group(P＞0.05).Conclusion:Larger GTA(＞70.5°)and CSA(＞39.5°)would be highly predictive in diagnosing RCTs without linear cor-relation,and GTA has a higher diagnostic value in contrast.Subacromial impingement and shoulder de-generation occurred before RCTs.Patients with age＞56.5 years and height＜1.58 m were more likely to develop disease of full-thickness RCTs and no statistic differences in weight and BMI.Gender,domi-nant shoulder and smoking were neither risk factors nor protective factors.

Objective:To adapt the Mindful Breastfeeding Scale (MINDF-BFS) into Chinese and assess its reliability and validity among breastfeeding mothers in China.Methods:Following the Beaton cross-cultural adaptation guideline, the original scale was translated, back-translated, discussed by experts, pre-tested, culturally adapted, and revised to develop the Chinese version of the MINDF-BFS. A convenience sampling method was used to select 305 postpartum women from Guangzhou Women and Children's Medical Center, Guangzhou Medical University, who visited between March and June 2024, as the study participants. The reliability and validity of the Chinese version of MINDF-BFS were evaluated.Results:The Chinese version of MINDF-BFS consisted of nine items, with the item-level content validity index ranged from 0.900 to 1.000, and the average scale-level content validity index was 0.990. Exploratory factor analysis extracted one common factor, with a variance contribution of 73.290%. Confirmatory factor analysis showed a good model fit. The Cronbach's α coefficient for the scale was 0.923, the split-half reliability coefficient was 0.915, and the test-retest reliability coefficient was 0.926.Conclusions:The Chinese version of MINDF-BFS has good psychometric properties and is suitable for assessing the mindful breastfeeding levels of Chinese postpartum women.

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 investigate the incidence of shoulder work-related musculoskeletal disorders (WMSDs) among occupational population in China, and to explore their intrinsic association with personal and work-related factors.Methods:In April 2024, 73497 valid questionnaires of the Chinese version of the Musculoskeletal Disorders Electronic Questionnaire were retrospectively analyzed from June 2018 to December 2023 in 22 provinces and 29 key industries in China, and the general information, occurrence of WMSDs and related risk factors of key occupational populations in different regions in China were collected. By using Chi-square test and confirmatory factor analysis, the relationship between shoulder fatigue and pain in key occupational groups and individual factors, work type, work posture and work organization was discussed, and the internal relationship was analyzed based on structural equation model.Results:Higher incidence of shoulder fatigue and pain were associated with female, lack of physical exercise, uncomfortable working posture and neck leaning forward ( P<0.05). Structural equation model analysis showed that work type, work posture and work organization were strongly correlated ( r=0.58, 0.55). Work organization and work type were strongly correlated with shoulder fatigue ( r=0.65) and moderately correlated with shoulder fatigue ( r=0.21). Shoulder fatigue was moderately associated with shoulder pain ( r=0.40). Individual factors, work type, work posture and shoulder fatigue could directly affect shoulder pain ( OR=0.07, -0.09, 0.17 and 0.40), and work type and work posture could also indirectly affect shoulder pain through shoulder fatigue ( OR=0.08, 0.03). Work organization only indirectly affected shoulder pain through shoulder fatigue ( OR=0.26) . Conclusion:The main influencing factor of shoulder pain is shoulder fatigue, followed by work posture and individual factors. Structural equation model can better reflect the complex relationship between work type, work posture and work organization and shoulder WMSDs. Improving work posture and work organization may be an effective way to control the influence of shoulder fatigue on shoulder pain.