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 association of the interaction and combined effect of renal function and body mass index (BMI) with the risk for all-cause death in patients with type 2 diabetes mellitus (T2DM) in communities of Jiangsu Province.Methods:The study subjects were from the Comprehensive Research Project of Diabetes Prevention and Control conducted in Jiangsu from December 2013 to January 2014, and follow up was conducted for them until September 30, 2023. A total of 20 025 subjects were included in the study. Cox proportional hazards regression model was used to analyze the association of renal function with risk for death in T2DM patients, and the association of interaction between renal function and BMI and their combined effect with all-cause death risk in T2DM patients.Results:In the follow up for 198 370 person-years, a total of 4 459 deaths were recorded. Cox proportional hazards regression model analysis showed that renal dysfunction was associated with 71% risk of all-cause mortality in all T2DM patients [hazard ratio ( HR) =1.71, 95% CI: 1.59-1.84], as well as in all BMI subgroups. Likelihood ratio test indicated an interaction between renal function and BMI (interaction for P=0.030). Compared with patients with normal renal function and normal BMI, those with normal renal function and over weight or obesity had a lower risk of all-cause mortality, and those with renal dysfunction and low weight had the highest risk for death ( HR=2.78, 95% CI: 1.87-4.14). Conclusions:There is association of interaction between renal function and BMI with all-cause mortality in T2DM patients. T2DM patients with renal dysfunction and low body weight had significant higher risk for death.

OBJECTIVES: To investigate the risk factors for the occurrence of cardiopulmonary dysfunction following ligation of hemodynamically significant patent ductus arteriosus (hsPDA) in preterm infants. METHODS: A retrospective collection of clinical data was conducted on preterm infants with a gestational age of <34 weeks who were admitted to the Maternal and Child Health Hospital of Hubei Province, Tongji Medical College, Huazhong University of Science and Technology from January 2018 to August 2024. These infants underwent hsPDA ligation after 1-2 courses of failed ibuprofen treatment. Based on the occurrence of blood pressure changes and oxygenation or ventilation failure postoperatively, the infants were divided into a cardiopulmonary dysfunction group (19 cases) and a non-cardiopulmonary dysfunction group (40 cases). Binary logistic regression analysis was performed to explore risk factors for postoperative cardiopulmonary dysfunction. RESULTS: Binary logistic regression analysis indicated that a faster average weight gain rate preoperatively and low levels of free triiodothyronine (FT₃) within one week before surgery were risk factors for cardiopulmonary dysfunction following hsPDA ligation (P<0.05). Receiver operating characteristic curve analysis showed that an average weight gain rate >11.45 g/(kg·d) and FT₃ levels <2.785 pmol/L within one week before surgery had predictive value for postoperative cardiopulmonary dysfunction (P<0.05). The combination of these two indicators provided the highest predictive value (P<0.05), with an area under the curve of 0.825, a sensitivity of 79%, and a specificity of 75%. CONCLUSIONS An average weight gain rate exceeding 11.45 g/(kg·d) and FT₃ levels below 2.785 pmol/L within one week before surgery are risk factors affecting cardiopulmonary function after hsPDA ligation. Preoperative assessment and intervention should be strengthened to reduce the risk of postoperative complications.
Humans ; Ductus Arteriosus, Patent/physiopathology* ; Risk Factors ; Female ; Infant, Newborn ; Male ; Retrospective Studies ; Infant, Premature ; Ligation/adverse effects* ; Hemodynamics ; Postoperative Complications/etiology* ; Logistic Models ; Lung Diseases/etiology*

OBJECTIVES: To investigate the protective effects and underlying mechanisms of Gynostemma pentaphyllum (GP)ethanol extract on motor dysfunction in a mouse model of Parkinson's disease (PD). METHODS: Eighty C57BL/6 male mice were randomly divided into five groups: control group, model group, levodopa group (positive control group), low-dose GP group, and high-dose GP group, with 16 mice per group. The PD model was induced by injection of 6-hydroxydopamine into the substantia nigra pars reticulata of the mice. Two weeks after 6-hydroxydopamine, positive control group received intraperitoneal injection of levodopa 10 mg·kg^－1·d^－1, while low-dose GP and high-dose GP groups received GP extract 100 or 200 mg·kg^－1·d^－1 orally for three weeks. After a 3-week-treatment, the effects of GP on motor dysfunction in 6-hydroxydopamine-induced PD were assessed using open field and CatWalk gait tests, while the effects on muscle strength were evaluated by forelimb grip strength. Immunofluorescence staining was used to detect the number of tyrosine hydroxylase (TH) positive neurons. The levels of dopamine and serotonin in the midbrain were determined by enzyme-linked immunosorbent assay. In addition, Western blotting was performed to detect the expression of mitogen-activated protein kinase (MAPK) family proteins such as p-extracellular signal-regulated kinase (ERK)1/2, p-p38 and p-c-Jun N-terminal kinase (JNK)1/2, and mitochondrial apoptosis pathway proteins such as B-cell lymphoma (Bcl)-2, Bcl-2 associated X protein (Bax), and cleaved-cysteine aspartic acid specific protease (caspase)-3. RESULTS: Behavioral experiments showed that GP significantly improved the spontaneous activity and motor coordination of PD mice (P<0.05). The forelimb grip strength was also increased by GP treatment (P<0.05), compared to the PD model group. In addition, compared with the model group, the number of TH-positive neurons in substantia nigra pars reticulata region, the levels of dopamine and serotonin in midbrain and the expression of p-ERK1/2 were significantly increased by GP treatment (all P<0.05), whereas the expression of p-p38 and p-JNK1/2, the ratio of Bax/Bcl-2 and cleaved-caspase-3/caspase-3 were significantly decreased (all P<0.05). CONCLUSIONS The results indicate that GP might increase dopamine and serotonin levels in the midbrain and promote the survival of dopaminergic neurons in substantia nigra pars reticulata by regulating the expression of phosphorylation of MAPK family proteins and the expression of mitochondrial apoptosis-related proteins, thereby ameliorating motor deficits in PD mice.
Animals ; Mice ; Male ; Gynostemma/chemistry* ; Mice, Inbred C57BL ; Apoptosis/drug effects* ; Plant Extracts/therapeutic use* ; Parkinson Disease/metabolism* ; Disease Models, Animal ; Neurons/pathology*

Objective:To explore the application and guiding value of bispectral index（BIS）in postoperative ventilator weaning in infants with congenital heart disease.Methods:A retrospective analysis was conducted on 81 cases of infants with congenital heart disease treated at Xuzhou Children's Hospital affiliated with Xuzhou Medical University from January 2022 to November 2023. The infants were divided into the successful weaning group（62 cases）and the failed weaning group（19 cases）based on the success of ventilator withdrawal. Univariate and multivariate Logistic analyses were performed on the clinical data of the two groups of infants，and ROC curves were plotted to analyze the predictive value of BIS for postoperative ventilator withdrawal failure in infants with congenital heart disease.Results:The mechanical ventilation time，ICU stay time，hospitalization time，and BIS values at 1 hour，2 hours，3 hours，4 hours，and 5 hours after sedation in the two groups of infants showed statistically significant differences（ P<0.05）. The results of the multivariate Logistic regression analysis indicated that BIS values at 1 hour，2 hours，3 hours，4 hours，and 5 hours after sedation are factors affecting the failure of postoperative ventilator weaning in infants with congenital heart disease（ P<0.05）. The ROC curve analysis revealed that the AUCs for predicting postoperative ventilator weaning failure in infants with congenital heart disease were 0.886，0.877，0.873，0.907，0.925，and 0.954 for BIS at 1 hour，2 hours，3 hours，4 hours，and 5 hours after sedation，and the combined prediction，respectively. The sensitivities and specificities were as follows：for BIS at 1 hour after sedation，94.7% and 67.7%；for BIS at 2 hours after sedation，84.2% and 93.5%；for BIS at 3 hours after sedation，84.2% and 83.9%；for BIS at 4 hours after sedation，89.5% and 79.0%；for BIS at 5 hours after sedation，84.2% and 85.5%；and for the combined prediction，100.0% and 90.3%. Conclusion:The use of BIS monitoring during the weaning of ventilators in infants after congenital heart disease surgery has certain predictive value for the success of the weaning process.

Complex liver resection (CLR) is a collective term for surgical procedures addre-ssing complex invasion of intrahepatic vasculobiliary structures that cannot be radically resected through conventional methods. The ex vivo liver resection and autotransplantation (ELRA) and its modified techniques have significantly enhanced the technical feasibility of CLR implementation. In recent years, advancements in modified ELRA techniques and derivative procedures, including conversion resection, in-situ hypothermic perfusion, and auxiliary liver transplantation, have further diversified CLR methodologies, offering more personalized treatment options for CLR candidates. Given the complexity of such cases and substantial variations in surgical approach selection, improving procedural safety and scalability remains a critical challenge in CLR practice. The authors review the current application of modified techniques based on ELRA in CLR, evaluate the clinical significance based on institutional experiences, and propose future directions and individual selection for advancing the safe implementation of CLR.

Objective:To explore the application and guiding value of bispectral index（BIS）in postoperative ventilator weaning in infants with congenital heart disease.Methods:A retrospective analysis was conducted on 81 cases of infants with congenital heart disease treated at Xuzhou Children's Hospital affiliated with Xuzhou Medical University from January 2022 to November 2023. The infants were divided into the successful weaning group（62 cases）and the failed weaning group（19 cases）based on the success of ventilator withdrawal. Univariate and multivariate Logistic analyses were performed on the clinical data of the two groups of infants，and ROC curves were plotted to analyze the predictive value of BIS for postoperative ventilator withdrawal failure in infants with congenital heart disease.Results:The mechanical ventilation time，ICU stay time，hospitalization time，and BIS values at 1 hour，2 hours，3 hours，4 hours，and 5 hours after sedation in the two groups of infants showed statistically significant differences（ P<0.05）. The results of the multivariate Logistic regression analysis indicated that BIS values at 1 hour，2 hours，3 hours，4 hours，and 5 hours after sedation are factors affecting the failure of postoperative ventilator weaning in infants with congenital heart disease（ P<0.05）. The ROC curve analysis revealed that the AUCs for predicting postoperative ventilator weaning failure in infants with congenital heart disease were 0.886，0.877，0.873，0.907，0.925，and 0.954 for BIS at 1 hour，2 hours，3 hours，4 hours，and 5 hours after sedation，and the combined prediction，respectively. The sensitivities and specificities were as follows：for BIS at 1 hour after sedation，94.7% and 67.7%；for BIS at 2 hours after sedation，84.2% and 93.5%；for BIS at 3 hours after sedation，84.2% and 83.9%；for BIS at 4 hours after sedation，89.5% and 79.0%；for BIS at 5 hours after sedation，84.2% and 85.5%；and for the combined prediction，100.0% and 90.3%. Conclusion:The use of BIS monitoring during the weaning of ventilators in infants after congenital heart disease surgery has certain predictive value for the success of the weaning process.

Complex liver resection (CLR) is a collective term for surgical procedures addre-ssing complex invasion of intrahepatic vasculobiliary structures that cannot be radically resected through conventional methods. The ex vivo liver resection and autotransplantation (ELRA) and its modified techniques have significantly enhanced the technical feasibility of CLR implementation. In recent years, advancements in modified ELRA techniques and derivative procedures, including conversion resection, in-situ hypothermic perfusion, and auxiliary liver transplantation, have further diversified CLR methodologies, offering more personalized treatment options for CLR candidates. Given the complexity of such cases and substantial variations in surgical approach selection, improving procedural safety and scalability remains a critical challenge in CLR practice. The authors review the current application of modified techniques based on ELRA in CLR, evaluate the clinical significance based on institutional experiences, and propose future directions and individual selection for advancing the safe implementation of CLR.