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 investigate the incidence, characteristics, and influencing factors of resolution discrepancies within the minipool (MP) testing model across Chinese blood station laboratories in 2024. Methods: A nationwide, multicenter, cross-sectional study was conducted, including 334 blood station laboratories that reported nucleic acid reactive data among enzyme immunoassay non-reactive samples. Of these, 296 laboratories adopted the pool resolution model, with a total of 12 536 273 samples tested. Systematic analysis was performed on resolution data, focusing on the MP-NAT reactivity rate, the pool resolution concordance rate, and the resolution discrepancy rate. Subgroup analyses were conducted based on reagent types, viral targets, and Ct values. Potential causes were further explored through laboratory surveys and re-examination of raw amplification curves. Results: In 2024, the national average MP-NAT reactivity rate was 0.15%. The overall pool resolution concordance rate was 57.86%, which showed a gradual decline as Ct values increased across all reagents. The national average resolution discrepancy rate was 0.081‱(102/12 536 273), with 17.91%(53/296) of laboratories reporting at least one discrepancy. Nine reagent types were associated with these events, exhibiting reagent-specific patterns. For Reagent A2, the predominant discrepancy was HBV reactive pools resolving as HIV (36.36%); for Reagent D1, HBV pools frequently resolved as HCV (38.89%); and for Reagent E, the most common pattern was HIV pools resolving as HBV (48.00%). These resolution discrepancies were strongly associated with high Ct values: the median pool Ct for HBV exceeded 38, while those for HCV and HIV both exceeded 40. Investigations across 16 laboratories revealed that most discrepant samples exhibited “tailing” amplification curves, with some cases linked to cross-contamination or reagent batch-specific issues. Conclusion: While the incidence of resolution discrepancies in the MP-NAT model remains low in China, variations exist across different reagents and laboratories. These discrepancies are closely associated with low viral load, reagent performance, and laboratory operational practices.

Objective To explore the clinical values of non-invasive myocardial work (MW) and tissue motion annular displacement (TMAD) in evaluation of anthracycline therapy-related cardiac dysfunction in patients with non-Hodgkin lymphoma. Methods A total of 62 patients with non-Hodgkin lymphoma who received standardized chemotherapy based on doxorubicin. Two and three dimensional transthoracic echocardiography, along with two dimensional speckle tracking echocardiography, were performed one day before chemotherapy and at 3, 6, and 9 months after chemotherapy to assess left ventricular ejection fraction, global longitudinal strain (GLS), MW parameters, and TMAD. Logistic regression analysis was used to evaluate the risk factors for cancer therapy-related cardiac dysfunction (CTRCD). The receiver operating characteristic curve was used to assess the diagnostic values of MW- and TMAD-related parameters for CTRCD. Results Compared to baseline, GLS, global work index (GWI), global constructive work (GCW), global work efficiency (GWE), TMAD at midpoint (TMADmid), and TMADmid percentage of left ventricular long-axis diameter (TMADmid%) decreased at 3 months after chemotherapy, while global wasted work (GWW) increased at 6 months after chemotherapy (P＜0.05). Logistic regression analysis showed that the relative reduction in GLS and TMADmid% at 3 months after chemotherapy were independent predictors for CTRCD （P＜0.05), while MW parameters were not independent predictors for CTRCD. GLS reduction≥10.3% and TMADmid% reduction≥15.8% at 3 months after chemotherapy predicted CTRCD with 0.866 and 0.824 of area under the curve (AUC), 92% and 75% of sensitivity, and 74% and 80% of specificity, respectively. AUC of combination of two indexes improved to 0.905, with 75% of sensitivity and 90% of specificity. Conclusions In non-Hodgkin lymphoma patients, the combination of GLS and TMADmid% is helpful of predicting CTRCD early, TMAD may be a novel diagnostic index for CTRCD, and GLS has superior predictive performance than MW for CTRCD.

To explore the advantages of traditional Chinese medicine （TCM） and integrative TCM-Western medicine approaches in the treatment of diabetic microvascular complications （DMC）， refine key pathophysiological insights and treatment principles， and promote academic innovation and strategic research planning in the prevention and treatment of DMC. The 38th session of the Expert Salon on Diseases Responding Specifically to Traditional Chinese Medicine， hosted by the China Association of Chinese Medicine， was held in Beijing， 2024. Experts in TCM， Western medicine， and interdisciplinary fields convened to conduct a systematic discussion on the pathogenesis， diagnostic and treatment challenges， and mechanism research related to DMC， ultimately forming a consensus on key directions. Four major research recommendations were proposed. The first is addressing clinical bottlenecks in the prevention and control of DMC by optimizing TCM-based evidence evaluation systems. The second is refining TCM core pathogenesis across DMC stages and establishing corresponding "disease-pattern-time" framework. The third is innovating mechanism research strategies to facilitate a shift from holistic regulation to targeted intervention in TCM. The fourth is advancing interdisciplinary collaboration to enhance the role of TCM in new drug development， research prioritization， and guideline formulation. TCM and integrative approaches offer distinct advantages in managing DMC. With a focus on the diseases responding specifically to TCM， strengthening evidence-based support and mechanism interpretation and promoting the integration of clinical care and research innovation will provide strong momentum for the modernization of TCM and the advancement of national health strategies.

To compare psychological reactance, intention to adopt sleep-management recommendations, and intention to use sleep-support resources among students in medical and health-related disciplines exposed to sleep health messages with different outcome frames and expression styles, and to provide evidence for the design of sleep health information materials.

OBJECTIVE To investigate the distribution of pathogens and epidemiological characteristics of the hospi-talized patients with lower respiratory tract infections(LRTI)so as to provide bases for clinical diagnosis and treatment as well as the public health prevention and control.METHODS The prevalence rates of 11 types of re-spiratory tract pathogens that were isolated from nasopharyngeal swab specimens of 3916 patients with LRTI who were hospitalized in Integrated Traditional Chinese and Western Medicine Hospital of Wenzhou Medical University from Jun.2023 to Nov.2024 were retrospectively analyzed.The age,sexes,seasons and characteristics of multi-ple infections were statistically analyzed.RESULTS The isolation rate of pathogens was 66.45％among the pa-tients with LRTI,rhinovirus(23.26％),Mycoplasma pneumoniae(17.29％)and respiratory syncytial virus(8.40％)were the main pathogens.The analysis of seasonal distribution indicated that coronavirus,influenza A/B viruses were highly prevalent in winter;Bocavirus and M.pneumoniae were active in autumn;parainfluenza vi-rus,respiratory syncytial virus and rhinovirus were prevalent in spring.There were significant differences in the i-solation rates of major species of pathogens rhinovirus,M pneumoniae and RSV among the different age groups of patients(P＜0.001).The isolation rate was highest(78.21％)among the children aged between 1 and 5 years old,and the incidence of multiple infections was highest(15.89％).The total isolation rates and incidence rates of multiple infec-tions were lower in summer than in winter,spring and autumn(P＜0.001).The detection rate of rhinovirus plus M.pneumoniae infections was highest(5.87％)among the combinations of multiple infections(5.87％),and the infec-tions were mainly prevalent in autumn.CONCLUSIONS Rhinovirus,M.pneumoniae and respiratory syncytial virus are the core pathogens isolated form the patients with LRTI in Wenzhou.The multiple infections are closely associated with the young age and season.It is suggested that the seasonal prevention and control strategies should be optimized,and the precise diagnosis and treatment assisted by the multiplex PCR technology should be promoted.

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.

Aim To investigate the effect of chrysoeriol on pulmonary vascular remodeling in pulmonary hyper-tension by animal experiments combined with cell ex-periments,and to explore its potential therapeutic tar-gets by network pharmacology.Methods The target of chrysoeriol was collected in Targetnet,SEA and SwissTargetPrediction database.Pulmonary arterial hy-pertension(PAH)targets were collected in the Dis-GeNET and GeneCards databases,and PPI network map was drawn in the STRING database,and key tar-gets were screened.The GO and KEGG pathway en-richment analysis was carried out through DAVID data-base and Weishengxing platform.AutoDock software was used for molecular docking of key core targets.The PAH model of rats was constructed,and the pulmo-nary hemodynamics and vascular remodeling were de-tected by echocardiography,HE and Masson staining.Primary pulmonary smooth muscle cells were extracted,and the effects of drugs on pathway proteins were de-tected in vitro.Results The results of network phar-macology showed that chrysoeriol exerted therapeutic effects on pulmonary hypertension by affecting key tar-gets such as AKT1,SRC,EGFR,MMP9 and gsk3 β,and signaling pathways such as EGFR and PI3K-AKT.Molecular docking showed that chrysoeriol had good binding ability with 5 key target genes.Animal experi-ments showed that the pulmonary hemodynamic func-tion of PAH rats was significantly improved after ad-ministration of chrysoeriol.The remodeling of small pulmonary arteries was significantly reduced.Cell ex-periments showed that chrysoeriol could inhibit the ex-pression of proliferation,migration and phenotypic transformation genes.Conclusion Chrysoeriol may play a role in the treatment of pulmonary hypertension through multiple targets.

With the development of science and technology worldwide, the blooming of artificial intelligence (AI) and big data has brought new opportunities and challenges to the promotion of the research capacity of professional master's students in oncology. The construction of the new medical education in China aims to cultivate high-level medical talents with comprehensive multidisciplinary skills and innovative abilities to flexibly solve complex problems at the frontier of medicine. In this context, professional master's students in oncology, who are facing problems such as low scientific research output and uneven quality and needing improving scientific research literacy, have been required to develop into compound talents with both clinical and research prowess. To cultivate and promote the research capacity of professional master's students in oncology, the key steps include accelerating the construction of AI education and databases, highlighting the cultivation of their scientific research capacity, implementing and fostering the cultivation of innovative ability and scientific research thinking, piloting joint cultivation models by engineering universities and medical universities, emphasizing the construction of the curriculum and teacher team for oncology, piloting the multidisciplinary mode and COME mode, and establishing a multidisciplinary cooperation network.