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.

To report two cases of psychiatric symptoms associated with zonisamide, an antiepileptic drug, and raise clinical awareness of this potential adverse effect. Two male patients with epilepsy treated with zonisamide were retrospectively analyzed. Case 1 (25 years old) developed acute emotional and behavioral abnormalities (e.g., insomnia, aggression, incoherent speech) after switching from sodium valproate to zonisamide (200 mg/day). Case 2 (48 years old) had long-term zonisamide use (≥5 years) with persistent treatment-resistant psychotic symptoms (e.g., delusions, command hallucinations). Clinical courses, medication adjustments, and symptom responses were documented. In Case 1, psychiatric symptoms resolved after discontinuing zonisamide and switching to sodium valproate, with improved mood stability and reduced impulsivity. In Case 2, despite escalating antipsychotic medications (risperidone, clozapine), psychotic symptoms persisted, likely due to ongoing zonisamide use. Both cases highlighted zonisamide’s potential to exacerbate or induce psychiatric manifestations, possibly via mechanisms involving sodium/calcium channel inhibition and neurotransmitter dysregulation (e.g., dopamine, serotonin). Zonisamide can cause or worsen psychiatric symptoms, particularly in vulnerable individuals. Clinicians should monitor for mental health changes during zonisamide treatment and consider drug discontinuation or substitution with alternative antiepileptics (e.g., sodium valproate) if psychiatric adverse effects emerge. Awareness of this association is crucial to avoid misdiagnosis and optimize epilepsy management.

Objective To understand the distribution, species composition, seasonal fluctuations, and presence of Dabie bandavirus in ticks in Tai'an City, providing a basis for assessing tick-borne disease risks and formulating prevention strategies. Methods Free-living ticks were monitored using the flagging method, whereas parasitic ticks were monitored through host surface examination. Reverse transcription-polymerase chain reaction (RT-qPCR) was used to detect the presence of Bandavirus dabieense in tick specimens. Results The density of free-living ticks in Tai'an City showed a continuous decreasing trend over the 3 years from 2021 to 2023, with an average tick density of 0.43 ticks/(flag·100 m). The dominant habitats were scenic areas and forests, and the seasonal fluctuations exhibited a bimodal pattern, peaking in March and August. The only free-living tick species captured was Haemaphysalis longicornis. Over the 3 years, the average tick index for parasitic ticks was 1.85, with sheep as the primary host. Seasonal fluctuations also followed a bimodal pattern, peaking in March and August. The primary parasitic tick species captured were H. longicornis and Rhipicephalus sanguineus. No Dabie bandavirus was detected in the tick specimens. Conclusions Tick density in Tai'an City remains relatively high, necessitating continued efforts to enhance tick surveillance and implement targeted prevention measures in rural environments to further reduce the health risks posed by tick-borne diseases.

Background:Bushen Zhuanggu Formula(BZF),derived from the classic Yougui Pills,has shown favorable clinical efficacy in treating advanced nontraumatic osteonecrosis of the femoral head(NONFH),particularly by promoting bone repair.However,its underlying mechanisms remain unclear.Objective:This study aimed to explore the mechanisms by which BZF promotes bone repair in advanced NONFH.Materials and methods:A total of 518 potential BZF targets were identified from the ETCM v2.0 database.Transcriptomic profiling of clinical cohorts revealed 485 differentially expressed genes in advanced NONFH patients compared to healthy controls.A drug target-disease gene interaction network was constructed to identify candidate BZF targets involved in NONFH pathogenesis.In vivo experiments were conducted to validate the effects of BZF in a rat model of advanced NONFH.Results:Network analysis identified key pathways associated with blood circulation obstruction,immune-inflammatory imbalance,and abnormal bone metabolism.Protein kinase C alpha(PKCA),Ras proto-oncogene(RAS),mitogen-activated protein kinase 3(ERK),ETS proto-oncogene 1(ETS1),and receptor activator of nuclear factor-κB ligand(RANKL)formed a signaling axis implicated in NONFH pathogenesis.BZF treatment alleviated joint inflammation,preserved trabecular bone morphology,reduced bone loss,and promoted bone repair.Mechanistically,BZF significantly downregulated the expression of PKCA,RAS,ERK,ETS1,and RANKL,improved blood circulation,and inhibited osteoclast activation while promoting osteoblast activation.Conclusion:BZF may promote bone repair in advanced NONFH by enhancing blood circulation and modulating the PKC-RAS-ERK-ETS1-RANKL signaling axis,thereby reversing dysregulated bone metabolism.

AIM To investigate the effects of Modified Baitouweng Decoction and Lizhong Decoction on mouse ulcerative colitis(UC).METHODS The mouse model of UC was established by 3％dextran sulfate sodium(DSS)induction.The C57BL/6 mice were randomly divided into the blank group,the model group,the low,medium and high dose Modified Baitouweng Decoction and Lizhong Decoction groups(3,6,12 g/kg),and sulfasalazine group(300 mg/kg),for 7 days gavage of the appropriate drugs,with 10 mice in each group.The mice had their disease activity index(DAI)and colonic mucosal damage index(CMDI)calculated;their colonic length and unit colonic weight measured;their histopathologic changes of colon observed by HE;their colonic ROS,MDA levels and GSH-Px,SOD activities detected by superoxide anion fluorescent probes and kits;their colonic levels of TNF-α,IL-6 and IL-1β detected by ELISA;their colonic LC3 expression detected by immunofluorescence method;and their colonic AMPK,mTOR and p70S6K protein expressions detected by Western blot method.RESULTS Compared with the blank group,the model group displayed significantly higher DAI score,CMDI score,unit colon weight,pathology score,ROS and MDA content,TNF-α,IL-6,and IL-1β levels,and mTOR and p70S6K protein expression(P＜0.01);and significantly lower colon length,GSH-Px and SOD activity,LC3 level,and phosphorylated AMPK protein expression(P＜0.01).Compared with the model group,the groups intervened with Modified Baitouweng Decoction and Lizhong Decoction or sulfasalazine shared decreased DAI score,CMDI score,unit colon mass,pathology score,ROS,MDA,TNF-α,IL-6,IL-1β levels,mTOR,p70S6K protein expressions(P＜0.01);and significantly improved symptomsin terms of the elevated colonic length,GSH-Px,SOD activities,LC3 level,AMPK protein expression(P＜0.01).CONCLUSION Modified Baitouweng Decoction and Lizhong Decoction may attenuate inflammatory response and oxidative damage in UC mouse models via AMPK/mTOR/p70S6K signaling pathway.

Objective:The predictive value of oxidized low density lipoprotein(ox-LDL)and electrocardiogram(ECG)ischaemia grade for major adverse cardiovascular events(MACE)in patients with ST elevation myocardial infarction(STEMI)after percutaneous coronary intervention(PCI)was assessed by a retrospective cohort study de-sign.Methods:A total of 336 STEMI patients admitted to Cangzhou People's Hospital between October 2019 and May 2022 were selected,and the medical record information was obtained through the hospital medical record sys-tem,and all patients received PCI and physician-recommended basic treatment.With occurrence of MACE with in 12-month follow-up as the evaluation index,they were divided into MACE group(n=65)and no MACE group(n=271).Multifactorial Logistic regression model was used to study the influencing factors of MACE after PCI in STEMI patients,and Spearman test for association of ox-LDL level,ECG ischaemia grade with MACE after PCI.ROC curve was used to evaluate the predictive efficacy of ox-LDL,ECG ischaemia grade and their combination for MACE after PCI.Results:The overall MACE incidence was 19.35％.Compared with patients in no MACE group,those in MACE group had significant higher ox-LDL level[46.34(29.46,66.29)U/L vs.33.00(23.02,50.03)U/L]and proportion of ECG grade Ⅲ ischaemia(64.62％vs.42.80％)(P＜0.01 all).Multifactorial Logistic re-gression analysis showed that ox-LDL(OR=1.022,95％CI 1.011～1.033,P=0.001)and ECG grade Ⅲ ischae-mia(OR=1.878,95％CI 1.007～3.504,P=0.048)were the independent risk factors of post-PCI MACE in STEMI patients.Spearman test showed that ox-LDL and ECG grade Ⅲ ischaemia were positively correlated with post-PCI MACE(r=0.209,0.173,P＜0.001 all).ROC curve analysis showed that the AUCs of ox-LDL,ECG grade Ⅲ ischaemia and their combination in predicting post-PCI MACE were respectively 0.653(95％CI 0.599～0.704),0.609(95％CI 0.555～0.662)and 0.758(95％CI 0.709～0.803),in which the predictive value of the combination of the two was significantly higher than any single detection(Z=2.030,3.097,P=0.042,0.002).Conclusion:ox-LDL combined with ECG ischaemia grading has a high predictive value for the occurrence of MACE with in 12 months after PCI in STEMI patients.

OBJECTIVE: To investigate chronic hepatitis C virus (HCV) infection's effect on gestational liver function, pregnancy and delivery complications, and neonatal development. METHODS: A total of 157 HCV antibody-positive (anti-HCV[+]) and HCV RNA(+) patients (Group C) and 121 anti-HCV(+) and HCV RNA(-) patients (Group B) were included as study participants, while 142 anti-HCV(-) and HCV RNA(-) patients (Group A) were the control group. Data on biochemical indices during pregnancy, pregnancy complications, delivery-related information, and neonatal complications were also collected. RESULTS: Elevated alanine aminotransferase (ALT) rates in Group C during early, middle, and late pregnancy were 59.87%, 43.95%, and 42.04%, respectively-significantly higher than Groups B (26.45%, 15.70%, 10.74%) and A (23.94%, 19.01%, 6.34%) ( P < 0.05). Median ALT levels in Group C were significantly higher than in Groups A and B at all pregnancy stages ( P < 0.05). No significant differences were found in neonatal malformation rates across groups ( P > 0.05). However, neonatal jaundice incidence was significantly greater in Group C (75.16%) compared to Groups A (42.25%) and B (57.02%) ( χ ² = 33.552, P < 0.001). HCV RNA positivity during pregnancy was an independent risk factor for neonatal jaundice ( OR = 2.111, 95% CI 1.242-3.588, P = 0.006). CONCLUSIONS Chronic HCV infection can affect the liver function of pregnant women, but does not increase the pregnancy or delivery complication risks. HCV RNA(+) is an independent risk factor for neonatal jaundice.
Humans ; Female ; Pregnancy ; Adult ; Pregnancy Complications, Infectious/epidemiology* ; Retrospective Studies ; Pregnancy Outcome ; Infant, Newborn ; Viremia/virology* ; Hepatitis C ; Hepacivirus/physiology* ; Hepatitis C, Chronic/virology* ; Young Adult ; Alanine Transaminase/blood*

OBJECTIVE: To identify the key features of facial and tongue images associated with anemia in female populations, establish anemia risk-screening models, and evaluate their performance. METHODS: A total of 533 female participants (anemic and healthy) were recruited from Shuguang Hospital. Facial and tongue images were collected using the TFDA-1 tongue and face diagnosis instrument. Color and texture features from various parts of facial and tongue images were extracted using Face Diagnosis Analysis System (FDAS) and Tongue Diagnosis Analysis System version 2.0 (TDAS v2.0). Least Absolute Shrinkage and Selection Operator (LASSO) regression was used for feature selection. Ten machine learning models and one deep learning model (ResNet50V2 + Conv1D) were developed and evaluated. RESULTS: Anemic women showed lower a-values, higher L- and b-values across all age groups. Texture features analysis showed that women aged 30-39 with anemia had higher angular second moment (ASM)and lower entropy (ENT) values in facial images, while those aged 40-49 had lower contrast (CON), ENT, and MEAN values in tongue images but higher ASM. Anemic women exhibited age-related trends similar to healthy women, with decreasing L-values and increasing a-, b-, and ASM-values. LASSO identified 19 key features from 62. Among classifiers, the Artificial Neural Network (ANN) model achieved the best performance [area under the curve (AUC): 0.849, accuracy: 0.781]. The ResNet50V2 model achieved comparable results [AUC: 0.846, accuracy: 0.818]. CONCLUSION Differences in facial and tongue images suggest that color and texture features can serve as potential TCM phenotype and auxiliary diagnostic indicators for female anemia.
Humans ; Female ; Tongue/diagnostic imaging* ; Adult ; Anemia/diagnosis* ; Middle Aged ; Face/diagnostic imaging* ; Young Adult ; Machine Learning