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.

Yinyang Gongji Pills have the effects of strengthening the body resistance to eliminate pathogenic factors, removing stasis, and reducing swelling, which is a commonly used traditional Chinese medicine(TCM) formula for treating intestinal accumulation. A real-world, registered, and single-arm clinical trial was conducted to observe the clinical efficacy and safety of Yinyang Gongji Pills combined with capecitabine in the treatment of advanced colorectal cancer and analyze the clinical characteristics of the patients. A total of 60 patients with advanced colorectal cancer who refused or could not tolerate standard treatment of western medicine were included in the study. They were treated with Yinyang Gongji Pills combined with capecitabine until disease progression or intolerable adverse events occurred. The main observation indicators were progression-free survival(PFS) and safety. The treatment effects of the patients under different baseline characteristics were analyzed. The clinical trial has found that the median PFS of all enrolled patients was 7.3 months, with 30.1% of patients having a PFS exceeding 12.0 months. Layered analysis showed that the median PFS of patients with the onset site being the colon and rectum were respectively 8.4 and 4.7 months. The median PFS of patients with high, medium, and low tumor burden were respectively 7.0, 4.7, and 10.8 months. The median PFS of patients with wild-type and mutant-type RAS/BRAF were respectively 7.9 and 6.9 months. The median PFS of patients with KPS scores ≥80 and ≤70 were respectively 7.9 and 6.5 months. The median PFS of patients treated with Yinyang Gongji Pills for ≥6, 3-6, and ≤3 months were respectively 8.0, 5.2, and 4.2 months. The median PFS of patients with spleen, kidney, liver, and lung syndrome differentiation in TCM were respectively 8.3, 6.7, 7.3, and 5.6 months. The median PFS of patients with TCM pathological factors including phlegm, dampness, and blood stasis were respectively 7.0, 7.3, and 6.5 months. Common adverse reactions include anemia, decreased white blood cells, decreased appetite, fatigue, and hand foot syndrome, with incidence rates being respectively 44.2%, 34.6%, 42.3%, 32.7%, and 17.3%. The results showed that the combination of Yinyang Gongji Pills and capecitabine demonstrated potential clinical efficacy and good safety in this study. The patients have clinical characteristics such as low tumor burden, onset site at the colon, KPS scores ≥ 80, long duration of oral TCM, and TCM syndrome differentiation including spleen or liver.
Humans ; Capecitabine/adverse effects* ; Colorectal Neoplasms/mortality* ; Drugs, Chinese Herbal/adverse effects* ; Male ; Middle Aged ; Female ; Aged ; Adult ; Treatment Outcome

OBJECTIVE: This study aimed to explore the association between body mass index (BMI) and mortality based on the 10-year population-based multicenter prospective study. METHODS: A general population-based multicenter prospective study was conducted at four sites in rural China between 2013 and 2023. Multivariate Cox proportional hazards models and restricted cubic spline analyses were used to assess the association between BMI and mortality. Stratified analyses were performed based on the individual characteristics of the participants. RESULTS: Overall, 19,107 participants with a sum of 163,095 person-years were included and 1,910 participants died. The underweight (< 18.5 kg/m ²) presented an increase in all-cause mortality (adjusted hazards ratio [ aHR] = 2.00, 95% confidence interval [ CI]: 1.66-2.41), while overweight (≥ 24.0 to < 28.0 kg/m ²) and obesity (≥ 28.0 kg/m ²) presented a decrease with an aHR of 0.61 (95% CI: 0.52-0.73) and 0.51 (95% CI: 0.37-0.70), respectively. Overweight ( aHR = 0.76, 95% CI: 0.67-0.86) and mild obesity ( aHR = 0.72, 95% CI: 0.59-0.87) had a positive impact on mortality in people older than 60 years. All-cause mortality decreased rapidly until reaching a BMI of 25.7 kg/m ² ( aHR = 0.95, 95% CI: 0.92-0.98) and increased slightly above that value, indicating a U-shaped association. The beneficial impact of being overweight on mortality was robust in most subgroups and sensitivity analyses. CONCLUSION This study provides additional evidence that overweight and mild obesity may be inversely related to the risk of death in individuals older than 60 years. Therefore, it is essential to consider age differences when formulating health and weight management strategies.
Humans ; Body Mass Index ; China/epidemiology* ; Male ; Female ; Middle Aged ; Prospective Studies ; Rural Population/statistics & numerical data* ; Aged ; Follow-Up Studies ; Adult ; Mortality ; Cause of Death ; Obesity/mortality* ; Overweight/mortality*

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.

Toxoplasma gondii is an intracellular protozoan pathogen with a global distribution,and dogs are considered a potential risk factor for human toxoplasmosis.This study was aimed at systematically analyzing the epidemiological characteris-tics of canine T.gondii infection in China from 1987 to 2023,to provide a scientific basis for the prevention and control of T.gondii in the country.Epidemiological data on canine T.gondii infections in China from 1987 to 2023 were retrieved from PubMed,China National Knowledge Infrastructure(CNKI),Wanfang Database,and Baidu Scholar.A database was established with Excel,and the data were visualized with ArcGIS 10.2 software.Statistical analysis was performed in SPSS 26.0 software,and group differences were analyzed with the X2 test.A P-value of＜0.05 was considered statistically significant.From 1987 to 2023,the overall seroprevalence of T.gondii antibodies in dogs in China remained stable,and the overall sero-prevalence rate was 13.97％.Yunnan Province had the highest seroprevalence,at 27.65％,whereas Shaanxi Province had the lowest seroprevalence,at 0.56％.Significant differences were observed among provinces(P＜0.05).Epidemiological data on canine T.gondii infections were not available for some regions.The seroprevalence in southwestern China was significantly higher than that in other regions(P＜0.05).A comparison of the seroprevalence between 1987-2004 and 2005-2023 revealed significant differences(P＜0.05).Canine T.gondii infection is widespread in China and shows a stable epidemic cycle.Appro-priate prevention and control measures should be implemented,along with strengthened surveillance of T.gondii outbreaks.Public education on the prevention and control of toxoplasmosis should be enhanced to decrease transmission risk and safeguard public health.

Objective:To summarize the relevant evidence of testicular cancer patients' fertility management which provides a basis for fertility guidance for young testicular cancer patients.Methods:The evidence,guidelines,expert consensus,evidence summary,systematic review and Meta-analysis on fertility-related clinical decision-making were searched from computer decision sup-port systems,relevant guideline websites,evidence-based databases,original research databases,and professional association websites at home and abroad.The search period was set dating from the establishment of the database to July 2024.Two researchers with evi-dence-based nursing research background independently completed the quality evaluation,evidence extraction and summary of the liter-ature.Results:A total of 21 articles were selected,including 4 clinical decisions,8 guidelines,4 expert consensuses,3 systematic reviews and 2 Meta-analyses.Thirty-three pieces of best evidence from six aspects were summarized,including fertility assessment,fertility counseling,fertility preservation timing,fertility preservation regimen,anti-tumor therapy and fertility,and contraceptive tim-ing.Conclusion:The best evidence summarized in this study provides a basis for clinical medical staff to carry out fertility manage-ment in testicular cancer patients.In clinical application,medical staff need to fully consider the patient's wishes in combination with the clinical situation,and promote the maximum benefit of the patient,so as to further improve the life quality of the patients.

Toxoplasma gondii is an intracellular protozoan pathogen with a global distribution,and dogs are considered a potential risk factor for human toxoplasmosis.This study was aimed at systematically analyzing the epidemiological characteris-tics of canine T.gondii infection in China from 1987 to 2023,to provide a scientific basis for the prevention and control of T.gondii in the country.Epidemiological data on canine T.gondii infections in China from 1987 to 2023 were retrieved from PubMed,China National Knowledge Infrastructure(CNKI),Wanfang Database,and Baidu Scholar.A database was established with Excel,and the data were visualized with ArcGIS 10.2 software.Statistical analysis was performed in SPSS 26.0 software,and group differences were analyzed with the X2 test.A P-value of＜0.05 was considered statistically significant.From 1987 to 2023,the overall seroprevalence of T.gondii antibodies in dogs in China remained stable,and the overall sero-prevalence rate was 13.97％.Yunnan Province had the highest seroprevalence,at 27.65％,whereas Shaanxi Province had the lowest seroprevalence,at 0.56％.Significant differences were observed among provinces(P＜0.05).Epidemiological data on canine T.gondii infections were not available for some regions.The seroprevalence in southwestern China was significantly higher than that in other regions(P＜0.05).A comparison of the seroprevalence between 1987-2004 and 2005-2023 revealed significant differences(P＜0.05).Canine T.gondii infection is widespread in China and shows a stable epidemic cycle.Appro-priate prevention and control measures should be implemented,along with strengthened surveillance of T.gondii outbreaks.Public education on the prevention and control of toxoplasmosis should be enhanced to decrease transmission risk and safeguard public health.

The application of sensors to the monitoring of spinal morphology and motion was reviewed in terms of the research object and monitoring index.The present situation of the application of sensors was introduced,such as inertial sensor,stretchable strain sensor and electromagnetic sensor.The deficiencies of sensors applied to the monitoring of spinal morphology and motion were analyzed,and the future directions of the application were pointed out.[Chinese Medical Equipment Journal,2025,46(6):105-110]

The application of sensors to the monitoring of spinal morphology and motion was reviewed in terms of the research object and monitoring index.The present situation of the application of sensors was introduced,such as inertial sensor,stretchable strain sensor and electromagnetic sensor.The deficiencies of sensors applied to the monitoring of spinal morphology and motion were analyzed,and the future directions of the application were pointed out.[Chinese Medical Equipment Journal,2025,46(6):105-110]