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.

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.

Aim To investigate the effects of Agrimonia pilosa(AP)on the proliferation and apoptosis of non-small cell lung cancer(NSCLC)H1299 cells using non-targeted metabolomics and other methods,and to explore the underlying molecular mechanisms.Meth-ods Taking H1299 cells as the research object,the effect of AP on cell proliferation and apoptosis was de-tected through CCK-8 method,colony formation,LDH,Hoechst 33258 staining,AO/EB staining,flow cytometry detection,RT qPCR and other experiments.The main differential metabolites were detected by the metabolomics method of ultra-high phase liquid chro-matography and mass spectrometry(UHPLC-Q-Orbi-trap MS),and related metabolic pathways were ana-lyzed.Results Compared with the control group,AP treatment was able to significantly inhibit the prolifera-tion and colony formation of H1299 cells,while the re-lease of LDH increased in a dose-dependent manner.Fluorescence microscopy and flow cytometry and RT-qPCR analysis revealed that H1299 cells underwent crumpling and increased nuclear fragmentation after AP administration,blocked in G0/G1 phase,up-regulated apoptotic genes caspase-3 and Bax,and down-regulated apoptosis-inducing effects of Bcl-2.Metabolomics anal-ysis screened 35 differential metabolites,which were PC(O-30∶1),D-Glutamic acid,PE(18∶0/15∶0),etc.The main metabolic pathways involved includ-ed amino acid metabolism,glycerophospholipid metabo-lism and purine metabolism so on.Conclusions AP may exert its pharmacological effects by interfering with multiple metabolic pathways in H1299 cells,inhibiting cell proliferation and promoting apoptosis.

With the rapid development of generative artificial intelligence(GAI)technologies,their widespread application in academic research and writing is continuously expanding the boundaries of sci-entific inquiry.However,this trend has also raised a series of ethical and regulatory challenges,inclu-ding issues related to authorship,content authenticity,citation accuracy,and accountability.In light of the growing involvement of AI in generating academic content,establishing an open,controllable,and trustworthy ethical governance framework has become a key task for safeguarding research integrity and maintaining trust within the academic community.This expert consensus outlines ethical requirements across key stages of AI-assisted academic writing-including topic selection,data management,citation practices,and authorship attribution.It aims to clarify the boundaries and ethical obligations surrounding AI use in academic writing,ensuring that technological tools enhance efficiency without compromising in-tegrity.The goal is to provide guidance and institutional support for building a responsible and sustainable research ecosystem.

Aim To investigate the effects of Agrimonia pilosa(AP)on the proliferation and apoptosis of non-small cell lung cancer(NSCLC)H1299 cells using non-targeted metabolomics and other methods,and to explore the underlying molecular mechanisms.Meth-ods Taking H1299 cells as the research object,the effect of AP on cell proliferation and apoptosis was de-tected through CCK-8 method,colony formation,LDH,Hoechst 33258 staining,AO/EB staining,flow cytometry detection,RT qPCR and other experiments.The main differential metabolites were detected by the metabolomics method of ultra-high phase liquid chro-matography and mass spectrometry(UHPLC-Q-Orbi-trap MS),and related metabolic pathways were ana-lyzed.Results Compared with the control group,AP treatment was able to significantly inhibit the prolifera-tion and colony formation of H1299 cells,while the re-lease of LDH increased in a dose-dependent manner.Fluorescence microscopy and flow cytometry and RT-qPCR analysis revealed that H1299 cells underwent crumpling and increased nuclear fragmentation after AP administration,blocked in G0/G1 phase,up-regulated apoptotic genes caspase-3 and Bax,and down-regulated apoptosis-inducing effects of Bcl-2.Metabolomics anal-ysis screened 35 differential metabolites,which were PC(O-30∶1),D-Glutamic acid,PE(18∶0/15∶0),etc.The main metabolic pathways involved includ-ed amino acid metabolism,glycerophospholipid metabo-lism and purine metabolism so on.Conclusions AP may exert its pharmacological effects by interfering with multiple metabolic pathways in H1299 cells,inhibiting cell proliferation and promoting apoptosis.

Objective:To analyze the genetic characteristics of the VWF gene c.7332G＞A nonsense mutation and explore its molecular pathogenesis.Methods:Phenotypic diagnosis of the proband was performed using VWF:Ag,VWF:RCo,FⅧ:C and multimeric analysis.The probands were genotyped by NGS whole-exome sequencing,and the sequencing results were validated by sanger sequencing.The family members were genotyped by Sanger sequencing.The VWF gene c.7332G＞A nonsense mutant plasmid was constructed.After transfection,the function of VWF gene c.7332G＞A mutant plasmid was verified at cell level in vitro.The mRNA level was detected by qRT-PCR,and the expression level of protein was detected by Western blot,the function of multimerization was verified by the multimeric analysis.Results:VWF:Ag and VWF:RCo were all less than 3％in the proband,and the multimeric analysis showed multimer deficiency.The proband was diagnosed as type 3 VWD.The homozygous nonsense mutation of VWF gene c.7332G＞A was detected by gene sequencing.The VWF mRNA level of the mutant plasmid was decreased,and the VWF protein expression in the cell supernatant was decreased,the mutant protein was truncated and the function of VWF multimerization was impaired.Conclusion:A homozygous mutation in exon 43 of VWF gene,c.7332G＞A,was responsible for the probands type 3 VWD in the proband.The mutation caused a decrease in the relative level of VWF mRNA and protein,and impaired the function of VWF multimerization.

To explore the anti-depression effect of Suanzaoren Decoction(SZRD), the regulatory effects on endogenous metabolites in the liver of rats with depression induced by chronic unpredictable mild stress(CUMS) were analyzed by using LC-MS metabolomics. The rats were randomly divided into normal control group, model group, low-dose SZRD group, high-dose SZRD group, and positive drug group. The CUMS depression model was replicated by applying a variety of stimuli, such as fasting and water deprivation, ice water swimming, hot water swimming, day and night reversal, tail clamping, and restraint for rats. Modeling and treatment were conducted for 56 days. The behavioral indexes of rats in each group, including body weight, open field test, sucrose preference test, and tail suspension test, were observed. Plasma samples and liver tissue samples were collected, and the contents of 5-hydroxytryptamine(5-HT), dopamine(DA), and norepinephrine(NE) in plasma were measured using enzyme-linked immunosorbent assay(ELISA). Meanwhile, the regulatory effects of SZRD on the liver metabolic profile of CUMS model rats were analyzed by the LC-MS metabolomics method. The results show that SZRD can significantly improve the depression-like behavior of CUMS model rats and increase the neurotransmitter levels of 5-HT, DA, and NE in plasma. A total of 24 different metabolites in the rats' liver are identified using the LC-MS metabolomics method, and SZRD can reverse 13 of these metabolites. Metabolic pathway analysis indicates that nine metabolic pathways are found to be significantly associated with depression, and in the low-dose SZRD group, four pathways can be regulated, including pentose phosphate pathway, purine metabolism, inositol phosphate metabolism, and sphingolipid metabolism. In the high-dose SZRD group, two metabolic pathways can be regulated, including sphingolipid metabolism and glycerol glycerophospholipid metabolism. Sphingolipid metabolism is a metabolic pathway that can be regulated by SZRD at different doses, so it is speculated that it may be the primary pathway through which SZRD can alleviate metabolic disturbances in the liver of CUMS model rats.
Animals ; Rats ; Drugs, Chinese Herbal/administration & dosage* ; Metabolomics ; Depression/metabolism* ; Male ; Liver/drug effects* ; Rats, Sprague-Dawley ; Antidepressive Agents/administration & dosage* ; Serotonin/blood* ; Humans ; Disease Models, Animal ; Behavior, Animal/drug effects*

Asthma is a chronic inflammatory disease involving multiple inflammatory cells and cytokines. Its pathogenesis is complex, involving various cells and cytokines. Traditional Chinese medicine(TCM) theory suggests that the pathogenesis of asthma is closely related to the dysfunction of internal organs such as the lungs, spleen, and kidneys. In contrast, modern immunological studies have revealed the central role of T helper 1(Th1)/T helper 2(Th2) and T helper 17(Th17)/regulatory T(Treg) cellular immune imbalance in the pathogenesis of asthma. Th1/Th2 imbalance is manifested as hyperfunction of Th2 cells, which promotes the synthesis of immunoglobulin E(IgE) and the activation of eosinophil granulocytes, leading to airway hyperresponsiveness and inflammation.Meanwhile, Th17/Treg imbalance exacerbates the inflammatory response in the airways, further contributing to asthma pathology.Currently, therapeutic strategies for asthma are actively exploring potential targets for regulating the balance of Th1/Th2 and Th17/Treg immune responses. These targets include cytokines, transcription factors, key proteins, and non-coding RNAs. Precisely regulating the expression and function of these targets can effectively modulate the activation and differentiation of immune cells. In recent years,traditional Chinese medicine active ingredients have shown unique potential and prospects in the field of asthma treatment. Based on this, the present study systematically summarizes the efficacy and specific mechanisms of TCM active ingredients in treating asthma by regulating Th1/Th2 and Th17/Treg immune balance through literature review and analysis. These active ingredients, including flavonoids, terpenoids, polysaccharides, alkaloids, and phenolic acids, exert their effects through various mechanisms, such as inhibiting the activation of inflammatory cells, reducing the release of cytokines, and promoting the normal differentiation of immune cells. This study aims to provide a solid foundation for the widespread application and in-depth development of TCM in asthma treatment and to offer new ideas for clinical research and drug development of asthma.
Asthma/genetics* ; Humans ; Drugs, Chinese Herbal/chemistry* ; Th2 Cells/drug effects* ; Th17 Cells/drug effects* ; T-Lymphocytes, Regulatory/drug effects* ; Th1 Cells/drug effects* ; Animals ; Cytokines/immunology* ; Medicine, Chinese Traditional

This study aims to reveal the effect and mechanism of Gentianella turkestanorum total extract(GTI) in ameliorating non-alcoholic steatohepatitis(NASH). UPLC-Q-TOF-MS was employed to identify the chemical components in GTI. SwissTarget-Prediction, GeneCards, OMIM, and TTD were utilized to screen the targets of GTI components and NASH. The common targets shared by GTI components and NASH were filtered through the STRING database and Cytoscape 3.9.0 to identify core targets, followed by GO and KEGG enrichment analysis. AutoDock was used for molecular docking of key components with core targets. A mouse model of NASH was established with a methionine-choline-deficient high-fat diet. A 4-week drug intervention was conducted, during which mouse weight was monitored, and the liver-to-brain ratio was measured at the end. Hematoxylin-eosin staining, Sirius red staining, and oil red O staining were employed to observe the pathological changes in the liver tissue. The levels of various biomarkers, including aspartate aminotransferase(AST), alanine aminotransferase(ALT), hydroxyproline(HYP), total cholesterol(TC), triglycerides(TG), low-density lipoprotein cholesterol(LDL-C), high-density lipoprotein cholesterol(HDL-C), malondialdehyde(MDA), superoxide dismutase(SOD), and glutathione(GSH), in the serum and liver tissue were determined. RT-qPCR was conducted to measure the mRNA levels of interleukin 1β(IL-1β), interleukin 6(IL-6), tumor necrosis factor α(TNF-α), collagen type I α1 chain(COL1A1), and α-smooth muscle actin(α-SMA). Western blotting was conducted to determine the protein levels of IL-1β, IL-6, TNF-α, and potential drug targets identified through network pharmacology. UPLC-Q-TOF/MS identified 581 chemical components of GTI, and 534 targets of GTI and 1 157 targets of NASH were screened out. The topological analysis of the common targets shared by GTI and NASH identified core targets such as IL-1β, IL-6, protein kinase B(AKT), TNF, and peroxisome proliferator activated receptor gamma(PPARG). GO and KEGG analyses indicated that the ameliorating effect of GTI on NASH was related to inflammatory responses and the phosphoinositide 3-kinase(PI3K)/AKT pathway. The staining results demonstrated that GTI ameliorated hepatocyte vacuolation, swelling, ballooning, and lipid accumulation in NASH mice. Compared with the model group, high doses of GTI reduced the AST, ALT, HYP, TC, and TG levels(P<0.01) while increasing the HDL-C, SOD, and GSH levels(P<0.01). RT-qPCR results showed that GTI down-regulated the mRNA levels of IL-1β, IL-6, TNF-α, COL1A1, and α-SMA(P<0.01). Western blot results indicated that GTI down-regulated the protein levels of IL-1β, IL-6, TNF-α, phosphorylated PI3K(p-PI3K), phosphorylated AKT(p-AKT), phosphorylated inhibitor of nuclear factor kappa B alpha(p-IκBα), and nuclear factor kappa B(NF-κB)(P<0.01). In summary, GTI ameliorates inflammation, dyslipidemia, and oxidative stress associated with NASH by regulating the PI3K/AKT/NF-κB signaling pathway.
Animals ; Non-alcoholic Fatty Liver Disease/genetics* ; Mice ; Network Pharmacology ; Male ; Drugs, Chinese Herbal/administration & dosage* ; Chromatography, High Pressure Liquid ; Liver/metabolism* ; Mice, Inbred C57BL ; Humans ; Mass Spectrometry ; Tumor Necrosis Factor-alpha/metabolism* ; Disease Models, Animal ; Molecular Docking Simulation