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 promote the effective implementation of China's Essential Public Health Services Program(EPHSP)and ensure the secure and efficient utilization of project funds,China officially initiated the performance evaluation of EPHSP in 2011.This performance evaluation has evolved through three distinct phases:initial exploration(2011-2014),steady advancement(2015-2018),and reform and enhancement(2019—present).The evaluation objectives have progressively expanded from an initial focus on fund security and service coverage to a broader emphasis on enhancing service quality,improving residents'health status and sense of benefit,and facilitating the refinement of policy frameworks and the implementation of primary responsibilities.Performance evaluation has emerged as a critical instrument for strengthening project governance and optimizing resource allocation,gradually establishing a performance-driven incentive mechanism that aligns rewards with both the quantity and quality of work.This approach has effectively contributed to the continuous improvement of service quality.To further advance the high-quality development of EPHSP,future efforts should optimize the performance evaluation system,prioritize the adoption of a full-cycle performance management approach and the integration of health outcome-based indicators.Additionally,it is essential to deepen the application of information technologies to enhance the precision and efficiency of evaluations,and to innovate mechanisms for utilizing evaluation results to reinforce accountability at the local level.These measures will collectively strengthen project performance management capabilities.

To promote the effective implementation of China's Essential Public Health Services Program(EPHSP)and ensure the secure and efficient utilization of project funds,China officially initiated the performance evaluation of EPHSP in 2011.This performance evaluation has evolved through three distinct phases:initial exploration(2011-2014),steady advancement(2015-2018),and reform and enhancement(2019—present).The evaluation objectives have progressively expanded from an initial focus on fund security and service coverage to a broader emphasis on enhancing service quality,improving residents'health status and sense of benefit,and facilitating the refinement of policy frameworks and the implementation of primary responsibilities.Performance evaluation has emerged as a critical instrument for strengthening project governance and optimizing resource allocation,gradually establishing a performance-driven incentive mechanism that aligns rewards with both the quantity and quality of work.This approach has effectively contributed to the continuous improvement of service quality.To further advance the high-quality development of EPHSP,future efforts should optimize the performance evaluation system,prioritize the adoption of a full-cycle performance management approach and the integration of health outcome-based indicators.Additionally,it is essential to deepen the application of information technologies to enhance the precision and efficiency of evaluations,and to innovate mechanisms for utilizing evaluation results to reinforce accountability at the local level.These measures will collectively strengthen project performance management capabilities.

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.

The prelimbic cortex (PL) plays a critical role in processing both the sensory and affective components of pain. However, the underlying molecular mechanisms remain poorly understood. In this study, we observed a reduction in hyperpolarization-activated cation current (I_h) in layer V pyramidal neurons of the contralateral PL in a mouse model of spared nerve injury (SNI). The expression of hyperpolarization-activated cyclic nucleotide-gated 2 (HCN2) channels was also decreased in the contralateral PL. Conversely, microinjection of fisetin, a partial agonist of HCN2, produced both analgesic and anxiolytic effects. Additionally, we found that cyclin-dependent kinase 5 (CDK5) was activated in the contralateral PL, where it formed a complex with HCN2 and phosphorylated its C-terminus. Knockdown of CDK5 restored HCN2 expression and alleviated both pain hypersensitivity and anxiety-like behaviors. Collectively, these results indicate that CDK5-mediated dysfunction of HCN2 in the PL underlies nerve injury-induced mechanical hypersensitivity and anxiety.
Animals ; Hyperpolarization-Activated Cyclic Nucleotide-Gated Channels/metabolism* ; Hyperalgesia/metabolism* ; Cyclin-Dependent Kinase 5/metabolism* ; Neuralgia/metabolism* ; Male ; Anxiety/metabolism* ; Mice ; Potassium Channels/metabolism* ; Mice, Inbred C57BL ; Disease Models, Animal ; Pyramidal Cells/metabolism*

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.

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.

Based on the interleukin-17(IL-17) signaling pathway, this study explores the effect and mechanism of Bufei Decoction on Klebsiella pneumoniae pneumonia in rats. SD rats were randomly divided into the control group, model group, Bufei Decoction low-dose group(6.68 g·kg~(-1)·d~(-1)), Bufei Decoction high-dose group(13.36 g·kg~(-1)·d~(-1)), and dexamethasone group(1.04 mg·kg~(-1)·d~(-1)), with 10 rats in each group. A pneumonia model was established by tracheal drip injection of K. pneumoniae. After successful model establishment, the improvement in lung tissue damage was observed following drug administration. Core targets and signaling pathways were screened using transcriptomics techniques. Real-time fluorescence quantitative polymerase chain reaction was used to detect the mRNA expression of core targets interleukin-6(IL-6), interleukin-1β(IL-1β), tumor necrosis factor-α(TNF-α), and chemokine CXC ligand 6(CXCL6). Western blot was used to assess key proteins in the IL-17 signaling pathway, including interleukin-17A(IL-17A), nuclear transcription factor-κB activator 1(Act1), tumor necrosis factor receptor-associated factor 6(TRAF6), and downstream phosphorylated p38 mitogen-activated protein kinase(p-p38 MAPK), and phosphorylated nuclear factor-κB p65(p-NF-κB p65). Apoptosis of lung tissue cells was detected by terminal deoxynucleotidyl transferase-mediated dUTP-biotin nick end labeling(TUNEL). The results showed that, compared with the control group, the model group exhibited significant pathological damage in lung tissue. The mRNA expression of IL-6, IL-1β, TNF-α, and CXCL6, as well as the protein levels of IL-17A, Act1, TRAF6, p-p38 MAPK/p38 MAPK, and p-NF-κB p65/NF-κB p65, were significantly increased, and the number of apoptotic cells was notably higher, indicating successful model establishment. Compared with the model group, both low-and high-dose groups of Bufei Decoction showed reduced pathological damage in lung tissue. The mRNA expression levels of IL-6, IL-1β, TNF-α, and CXCL6, and the protein levels of IL-17A, Act1, TRAF6, p-p38 MAPK/p38 MAPK, and p-NF-κB p65/NF-κB p65, were significantly decreased, with a significant reduction in apoptotic cells in the high-dose group. In conclusion, Bufei Decoction can effectively improve lung tissue damage and reduce inflammation in rats with K. pneumoniae. The mechanism may involve the regulation of the IL-17 signaling pathway and the reduction of apoptosis.
Animals ; Interleukin-17/metabolism* ; Drugs, Chinese Herbal/administration & dosage* ; Rats, Sprague-Dawley ; Signal Transduction/drug effects* ; Rats ; Male ; Klebsiella pneumoniae/physiology* ; Klebsiella Infections/immunology* ; Humans ; Lung/drug effects*