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 analyze the factors affecting the prevalence of hyperuricemia(HUA)in an island troop.Methods A total of 1 113 soldiers stationed on an island from December 2021 to December 2022 were selected as research objects by cluster sampling.Their lifestyle and health information were collected.Physical examination and laboratory detection were conducted.Multivariate logistic regression was used to analyze the influencing factors of HUA.Results The prevalence rate of HUA was 21.02%(234/1 113).There were significant differences in the body mass index(BMI),waist-to-hip ratio,triglyceride,alanine aminotransferase,and creatinine between the soldiers with hyperuricemia and the soldiers with normal blood uric acid(P<0.05).Multivariate logistic regression analysis showed that BMI≥24(OR=1.49,95%CI:1.09-2.05),abnormal liver function(OR=2.26,95%CI:1.31-3.92),and dyslipidemia(OR=1.46,95%CI:1.01-2.12)were positively correlated with hyperuricemia;age>30 years old(OR=0.59,95%CI:0.37-0.93)and exercise time>1 h per week(OR=0.46,95%CI:0.22-0.97)were negatively correlated with HUA.Conclusion The prevalence rate of hyperuricemia is at a high level in an island troop.BMI≥24,age≤30 years old,exercise time≤1 h per week,abnormal liver function,and dyslipidemia are the risk factors for HUA.Prevention and control measures should be taken as early as possible for the soldiers with these risk factors.

OBJECTIVE: The relationship between fish consumption and stroke is inconsistent, and it is uncertain whether this association varies across predicted stroke risks. METHODS: A cohort study comprising 95,800 participants from the Prediction for Atherosclerotic Cardiovascular Disease Risk in China project was conducted. A standardized questionnaire was used to collect data on fish consumption. Participants were stratified into low- and moderate-to-high-risk categories based on their 10-year stroke risk prediction scores. Hazard ratios ( HRs) and 95% confidence intervals ( CIs) were estimated using Cox proportional hazard models and additive interaction by relative excess risk due to interaction (RERI), attributable proportion (AP), and synergy index (SI). RESULTS: During 703,869 person-years of follow-up, 2,773 incident stroke events were identified. Higher fish consumption was associated with a lower risk of stroke, particularly among moderate-to-high-risk individuals ( HR = 0.53, 95% CI: 0.47-0.60) than among low-risk individuals ( HR = 0.64, 95% CI: 0.49-0.85). A significant additive interaction between fish consumption and predicted stroke risk was observed (RERI = 4.08, 95% CI: 2.80-5.36; SI = 1.64, 95% CI: 1.42-1.89; AP = 0.36, 95% CI: 0.28-0.43). CONCLUSION Higher fish consumption was associated with a lower risk of stroke, and this beneficial association was more pronounced in individuals with moderate-to-high stroke risk.
Humans ; China/epidemiology* ; Male ; Female ; Stroke/etiology* ; Middle Aged ; Prospective Studies ; Incidence ; Aged ; Animals ; Fishes ; Risk Factors ; Diet ; Seafood ; Adult ; Cohort Studies

Pregnancy complicated with acute myeloid leukemia is uncommon,requiring the collaborative management by specialists from departments of hematology,obstetrics,anesthesiology,and neonatology for both the parturient and the neonate.This article reports an anesthesic management process of a parturient woman with acute myeloid leukemia and reviews relevant literature published in recent years to systematically summarize the approach for anesthesia-related perinatal management of such patients.
Humans ; Female ; Pregnancy ; Leukemia, Myeloid, Acute/complications* ; Pregnancy Complications, Neoplastic ; Adult ; Anesthesia, Obstetrical/methods*

Objective To characterize the expression patterns of serum microRNA-497(miR-497)in patients with colorectal cancer(CRC)and to investigate its associations with clinicopathological characteristics,diagnostic performance,and long-term prognostic outcomes.Methods This study retrospectively analyzed data from 122 patients with CRC admitted to the hospital between March 2020 and March 2022(CRC group),and enrolled 100 healthy individuals undergoing routine physical examinations(healthy control group)for comparison.Serum samples were collected from all participants prior to any surgical intervention,and the expression levels of miR-497 in serum were quantified using real-time quantitative polymerase chain reaction(qRT-PCR).Simulta-neously,the levels of carcinoembryonic antigen(CEA)and carbohydrate antigen 199(CA199)were measured.To investigate the association between miR-497 expression and clinicopathological characteristics,we evaluated its diagnostic performance using receiver operating characteristic(ROC)curve analysis.Furthermore,Kaplan-Meier survival analysis and Cox proportional hazards regression models were employed to assess its impact on patient prognosis.Results Compared to healthy individuals,CRC patients exhibited significantly lower serum miR-497 expression levels(P<0.001).Notably,miR-497 expression was strongly correlated with TNM stage progression and lymph node metastasis(P<0.001),but showed no significant association with tumor location,patient sex,or age.Diagnostic evaluation using ROC curves demonstrated that miR-497 achieved an AUC of 0.845 for CRC detection,outperforming CEA(AUC=0.748)and CA19-9(AUC=0.702),with DeLong's test confirming the statistically significant differences(P<0.05).Kaplan-Meier survival analysis revealed a significantly higher 3-year DFS rate among patients with high miR-497 expression(84.06%)compared to those with low expression(64.58%),with median DFS not reached in the high-expression group versus 36 months in the low-expression group(P=0.015).Multivariate Cox regression analysis confirmed that reduced miR-497 expression(HR=1.923,95%CI:1.184～3.125),advanced TNM stage(HR=2.511,95%CI:1.421～4.437),and lymph node metastasis(HR=1.753,95%CI:1.151～2.664)were independently associated with poorer disease-free survival outcomes.Conclusions Serum miR-497 is downregulated in patients with CRC and is significantly associated with tumor progression and poor prognosis.It demonstrates high diagnostic accuracy and strong potential for prognostic evalua-tion,highlighting its promise as a biomarker for auxiliary diagnosis and outcome prediction in CRC.

Objective To characterize the expression patterns of serum microRNA-497(miR-497)in patients with colorectal cancer(CRC)and to investigate its associations with clinicopathological characteristics,diagnostic performance,and long-term prognostic outcomes.Methods This study retrospectively analyzed data from 122 patients with CRC admitted to the hospital between March 2020 and March 2022(CRC group),and enrolled 100 healthy individuals undergoing routine physical examinations(healthy control group)for comparison.Serum samples were collected from all participants prior to any surgical intervention,and the expression levels of miR-497 in serum were quantified using real-time quantitative polymerase chain reaction(qRT-PCR).Simulta-neously,the levels of carcinoembryonic antigen(CEA)and carbohydrate antigen 199(CA199)were measured.To investigate the association between miR-497 expression and clinicopathological characteristics,we evaluated its diagnostic performance using receiver operating characteristic(ROC)curve analysis.Furthermore,Kaplan-Meier survival analysis and Cox proportional hazards regression models were employed to assess its impact on patient prognosis.Results Compared to healthy individuals,CRC patients exhibited significantly lower serum miR-497 expression levels(P<0.001).Notably,miR-497 expression was strongly correlated with TNM stage progression and lymph node metastasis(P<0.001),but showed no significant association with tumor location,patient sex,or age.Diagnostic evaluation using ROC curves demonstrated that miR-497 achieved an AUC of 0.845 for CRC detection,outperforming CEA(AUC=0.748)and CA19-9(AUC=0.702),with DeLong's test confirming the statistically significant differences(P<0.05).Kaplan-Meier survival analysis revealed a significantly higher 3-year DFS rate among patients with high miR-497 expression(84.06%)compared to those with low expression(64.58%),with median DFS not reached in the high-expression group versus 36 months in the low-expression group(P=0.015).Multivariate Cox regression analysis confirmed that reduced miR-497 expression(HR=1.923,95%CI:1.184～3.125),advanced TNM stage(HR=2.511,95%CI:1.421～4.437),and lymph node metastasis(HR=1.753,95%CI:1.151～2.664)were independently associated with poorer disease-free survival outcomes.Conclusions Serum miR-497 is downregulated in patients with CRC and is significantly associated with tumor progression and poor prognosis.It demonstrates high diagnostic accuracy and strong potential for prognostic evalua-tion,highlighting its promise as a biomarker for auxiliary diagnosis and outcome prediction in CRC.

Background/Aims: Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1–3% of hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted a nationwide study to investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied to discriminate subjects who may fail to respond to DAA therapy. Methods: We analyzed the Taiwan HCV Registry Program database to explore predictors of DAA failure in HCV patients. Fifty-five host and virological features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and artificial neural network. The primary outcome was undetectable HCV RNA at 12 weeks after the end of treatment. Results: The training (n=23,955) and validation (n=10,346) datasets had similar baseline demographics, with an overall DAA failure rate of 1.6% (n=538). Multivariate logistic regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor DAA adherence, and higher hemoglobin A1c were significantly associated with virological failure. XGBoost outperformed the other algorithms and logistic regression models, with an area under the receiver operating characteristic curve of 1.000 in the training dataset and 0.803 in the validation dataset. The top five predictors of treatment failure were HCV RNA, body mass index, α-fetoprotein, platelets, and FIB-4 index. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model (cutoff value=0.5) were 99.5%, 69.7%, 99.9%, 97.4%, and 99.5%, respectively, for the entire dataset. Conclusions Machine learning algorithms effectively provide risk stratification for DAA failure and additional information on the factors associated with DAA failure.

Objective To investigate the regulatory effect of Jianpi Huayu Prescription(Ginseng Radix et Rhizoma,Poria,Atractylodis Macrocephalae Rhizoma,Salviae Miltiorrhizae Radix et Rhizoma,etc.)on epithelial-mesenchymal transition(EMT)and angiogenesis of hepatocellular carcinoma through TGF-β1/Smad7 pathway.Methods(1)Hep3B tumor-bearing mouse model was established by BALB/C-nu nude mice.The mice were randomly divided into control group and Jianpi Huayu Prescription low-,medium-and high-dose groups(3.844,7.689,15.378 g·kg-1·d-1),with five mice in each group.Intragastric administration was performed once a day for 21 days.(2)Hep3B cells were divided into blank group,model group(10 ng·mL-1 TGF-β1),low-concentration group(10 ng·mL-1 TGF-β1+4 mg·mL-1 Jianpi Huayu Prescription),and high-concentration group(10 ng·mL-1 TGF-β1+6 mg·mL-1 Jianpi Huayu Prescription).After 48 hours of TGF-β1 induction,the cells were replaced with the corresponding concentration of Jianpi Huayu Prescription complete culture medium(0,4,6 mg·mL-1)and cultured for 24 hours.(3)HUVEC cells were divided into normal group,model group,Chinese medicine group,model plus Chinese medicine group.The cells in the normal group were cultured with conditioned medium without TGF-β1;the cells in the model group were cultured with conditioned medium containing TGF-β1.The cells in the Chinese medicine group were cultured in conditioned medium containing 4 mg·mL-1 Jianpi Huayu Prescription without TGF-β 1.The cells in the model plus Chinese medicine group were cultured with conditioned medium containing 4 mg·mL-1 Jianpi Huayu Prescription and TGF-β1.After 24 hours of continuous culture,the cells were collected for subsequent experiments.(4)The tumor mass index and tumor inhibition rate of subcutaneous transplantation tumor of Hep3B tumor-bearing nude mice were calculated.The expression of CD31 in subcutaneous xenografts of tumor-bearing nude mice was detected by immunofluorescence.The microvessel density of subcutaneous transplanted tumor in nude mice was detected by immunohistochemistry.The migration ability of Hep3B cells was detected by cell scratch test.Transwell assay was used to detect the invasion ability of Hep3B/HUVEC cells.The tube formation ability of HUVEC cells was detected.The expression levels of related proteins in subcutaneous transplanted tumors,Hep3B and HUVEC cells of tumor-bearing nude mice were detected by Western Blot.Results(1)Compared with the control group,the weight and tumor mass index of subcutaneous transplanted tumor in nude mice in the medium-and high-dose groups of Jianpi Huayu Prescription were significantly decreased(P＜0.01).The expression of CD31 and microvessel density in subcutaneous transplanted tumors of nude mice in low-,medium-and high-dose groups were significantly decreased(P＜0.05,P＜0.01),the protein expressions of VE-cadherin,EphA2 and N-cadherin were significantly down-regulated(P＜0.05,P＜0.01),and the protein expressions of E-cadherin and Smad7 was significantly up-regulated(P＜0.01).(2)Compared with the blank group,the relative migration rate of Hep3B cells in the model group was significantly increased(P＜0.05),and the number of invasive cells was significantly increased(P＜0.01).The protein expressions of Vimentin and N-cadherin were significantly up-regulated(P＜0.01),and the protein expressions of E-cadherin and Smad7 was significantly down-regulated(P＜0.01).Compared with the model group,the relative migration rate of Hep3B cells in the low-and high-concentration groups of Jianpi Huayu Prescription was significantly decreased(P＜0.01),and the number of invasive cells was significantly decreased(P＜0.01).The protein expressions of Vimentin and N-cadherin was significantly down-regulated(P＜0.01),and the protein expressions of E-cadherin and Smad7 were significantly up-regulated(P＜0.01).(3)Compared with the normal group,the number of tubular branching points formed by HUVEC cells in the model group was significantly increased(P＜0.01),the length of tubular branching was significantly increased(P＜0.01),and the number of invasive cells was significantly increased(P＜0.01).The protein expressions of VE-cadherin and EphA2 were significantly up-regulated(P＜0.01),and the protein expression of Smad7 was significantly down-regulated(P＜0.01).Compared with the model group,the number of tubular branching points formed by HUVEC cells in the model plus Chinese medicine group was significantly reduced(P＜0.01),the length of tubular branching was significantly shortened(P＜0.01),and the number of invasive cells was significantly reduced(P＜0.01).The protein expressions of VE-cadherin and EphA2 were significantly down-regulated(P＜0.01),and the protein expression of Smad7 was significantly up-regulated(P＜0.01).Conclusion Jianpi Huayu Prescription can significantly inhibit the growth,invasion and migration of hepatocellular carcinoma,which may be related to the regulation of EMT and angiogenesis mediated by TGF-β1/Smad7 pathway.

Objective Viral encephalitis is an infectious disease severely affecting human health.It is caused by a wide variety of viral pathogens,including herpes viruses,flaviviruses,enteroviruses,and other viruses.The laboratory diagnosis of viral encephalitis is a worldwide challenge.Recently,high-throughput sequencing technology has provided new tools for diagnosing central nervous system infections.Thus,In this study,we established a multipathogen detection platform for viral encephalitis based on amplicon sequencing. Methods We designed nine pairs of specific polymerase chain reaction(PCR)primers for the 12 viruses by reviewing the relevant literature.The detection ability of the primers was verified by software simulation and the detection of known positive samples.Amplicon sequencing was used to validate the samples,and consistency was compared with Sanger sequencing. Results The results showed that the target sequences of various pathogens were obtained at a coverage depth level greater than 20×,and the sequence lengths were consistent with the sizes of the predicted amplicons.The sequences were verified using the National Center for Biotechnology Information BLAST,and all results were consistent with the results of Sanger sequencing. Conclusion Amplicon-based high-throughput sequencing technology is feasible as a supplementary method for the pathogenic detection of viral encephalitis.It is also a useful tool for the high-volume screening of clinical samples.