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.

Aim To investigate the effects of dimethyl-arginine dimethylamino hydrolase 1(DDAH1)on high glucose-induced mitochondrial dysfunction and mitoph-agy in vascular endothelial cells.Methods JC-1 stai-ning was used to detect mitochondrial membrane poten-tial.DCFH-DA fluorescent probe was employed to measure reactive oxygen species(ROS)levels.Ho-echst staining was used to assess cell apoptosis.Real-time PCR was conducted to detect DDAH1 mRNA lev-els.Western blot was performed to analyze the expres-sion of DDAH1,LC3-Ⅰ and LC3-Ⅱ proteins.Mitochon-drial probe Mitotracker and autophagosome marker pro-tein LC3 were used in cell immunofluorescence co-lo-calization to assess mitochondrial autophagy,and high-performance liquid chromatography was utilized to measure the levels of asymmetric dimethylarginine(ADMA)in cell supernatant.Results High glucose treatment for 48 h significantly reduced mitochondrial membrane potential,increased ROS production,and promoted apoptosis in human umbilical vein endothelial cells(HUVECs).High glucose downregulated the ex-pression of LC3-Ⅱ/LC3-Ⅰ proteins,reduced the co-lo-calization of Mitotracker and LC3,and inhibited mito-chondrial autophagy.Autophagy inhibitors 3-MA or CQ exacerbated high glucose-induced mitochondrial dam-age and apoptosis in HUVECs,while autophagy activa-tor RAPA alleviated these effects.High glucose signifi-cantly downregulated DDAH1 protein expression in HUVECs and increased ADMA levels in cell superna-tant.DDAH1 siRNA inhibited mitochondrial autoph-agy,reduced mitochondrial membrane potential,and promoted apoptosis,whereas DDAH1 overexpression enhanced mitochondrial autophagy and alleviated high glucose-induced apoptosis in HUVECs.Conclusion High glucose-induced endothelial mitochondrial dys-function is associated with the suppression of DDAH1 expression,the increase of ADMA levels,and thereduc-tion of mitochondrial autophagy.

Aim To investigate the neuroprotective effect of dioscin(DIO)on hippocampal neurons(HT22)after oxygen glucose deprivation/reoxygen-ation(OGD/R)and its possible mechanism.Methods HT22 cells were treated with 0,2.5,5,10,20,40,80,160,and 320 mg·L-1DIO for 24 h,and the cell proliferation rate was detected by CCK-8 method.The concentration that was non-toxic to HT 2 2 cells was se-lected for subsequent experiments.After OGD for 2 h,HT22 cells were randomly divided into the OGD/R group,1.25,2.5,and 5 mg·L-1DIO group,and posi-tive control group.HT22 cells were taken as the con-trol group.After drug intervention for 24 h,the cell proliferation rate was detected by CCK-8 method;the LDH release was detected by colorimetry;the cell ap-optosis rate was detected by TUNEL method;the ex-pression of proteins related to PARP-1/AIF pathway and caspase pathway was detected by Western blot.Results DIO intervention significantly upregulated the expression of AIF protein in mitochondria and PAR protein in nucleus of HT22 cells after OGD/R,and sig-nificantly downregulated the release of LDH,neuronal apoptosis rate,total protein expression of AIF and PAR,PARP-1,AIF in nucleus and protein expression of PAR protein in mitochondria,while the expression of Bax and caspase-3 proteins was not significantly differ-ent from that in the OGD/R group.Conclusion DIO can alleviate the apoptosis of HT22 cells induced by OGD/R by regulating the expression and translocation of proteins related to the PARP-1/AIF pathway,thus playing a neuroprotective role.

Objective To propose a method for mass spectrometry imaging(MSI)super-resolution reconstruction based on a spatially multi-level and self-supervised deep learning network(SMSDL-Net),aiming to improve the resolution of mass spectrometry images.Methods SMSDL-Net firstly registered histological and mass spectrometry images using a nonlinear transformation.Then a multi-branch Vision Transformer(ViT)was utilized to extract hierarchical features of high-resolution histological images in a self-supervised manner.These features were subsequently combined with the paired low-resolution mass spectrometry data to construct a regression network,which could realize the prediction of high-resolution mass spectrometry information.To validate the performance of the proposed method,the results by the method were compared with those of the traditional bicubic interpolation(BI)methods based on interpolation processing and the deepFERE method based on convolution neural network(CNN)for super-resolution reconstruction of magnesium elemental image of metal mass spectrometry of human liver cancer samples,and the method was also applied to a mouse renal adenocarcinoma metabolite mass spectrometry imaging dataset.Results Compared with the traditional BI methods and the deepFERE multimodal method,the method proposed demonstrated the lowest root mean square error(RMSE=0.015),the highest structural similarity index measure(SSIM=0.84)and the highest R-squared value(R2=0.853)in reconstructing mass spectrometry images.The effectiveness of the method and its potential for precise tissue-specific distinction were validated using the mouse renal adenocarcinoma metabolite MSI dataset.Conclusion Compared with traditional single-modal and pixel-wise regression deep learning methods,the method proposed enhances the quality of high-resolution mass spectrometry image reconstruction and can serve as a novel method for super-resolution reconstruction in the field of mass spectrometry imaging.[Chinese Medical Equipment Journal,2025,46(4):1-8]

Aim To study the mechanism of salidro-side combined with rosavin in rats with ischemic stroke.Methods The MCAO rats was established by using thread-embolic method.The rats were divided into the sham group,MCAO group,salidroside com-bined with rosavin group,and positive control group;the drug was given continuously for seven days.Western blot was used to detect apoptosis indicators.Proteomics was used to analyse differential proteins(DEPs).STEP receptor inhibitor was injected into the lateral ventricles,the rats were administered for seven days,then the apoptosis indicators were detected.Re-sults Salidroside combined with rosavin could reduce neurological function scores in MCAO rats and inhibit cell apoptosis.Quantitative proteomics identified 496 DEPs in brain tissue and discovered core proteins STEP,p38,and CRTC1.Salidroside combined with rosavin could promote the STEP and CRTC1 while in-hibiting p38 protein.After treatment with STEP inhibi-tor,those effects were reversed.Conclusion Salidro-side combined with rosavin can inhibit cell apoptosis in MCAO rats,which is closely related to the regulation of the STEP/p38/CRTC1 signaling pathway.

Spinal cord injury(SCI)is a central nervous system disease with high morbidity and disability rates,bringing serious economic and psychological burdens to families and society worldwide.AMP-activated protein kinase(AMPK)is an important sensor in the energy metabolism process in living organisms,which plays a central role in maintaining energy balance.It is currently considered a key target for the prevention and treatment of multiple diseases.Studies have shown that AMPK signaling can regulate autophagy,neuroinflammation,oxidative stress,mitochondrial function and other processes after SCI,thus affecting the pathological process of SCI.This review summarizes the research progress on AMPK signaling pathway involved in the regulation of SCI,in order to provide new ideas for the treatment and drug development of SCI.

Objective To investigate the status of population dynamics and distribution changes of Aedes aegypti in Guangdong Province.Methods Continuous monitoring was conducted from May 2018 to July 2024 in Wushi Town and Qishui Town,Leizhou City,Zhanjiang City,Guangdong Province.Additionally,a survey of the distribution of Ae.aegypti along the Leizhou Peninsula coast was carried out.Results The density of Ae.aegypti in Zhanjiang showed a gradual decline from 2018 to 2024.The last detection of adult Ae.aegypti in Wushi Town was in September 2021,and the last larva was found in October 2023.No Ae.aegypti was detected in Qishui Town during surveys from 2021 to 2024.A survey of 18 coastal villages in the Leizhou Peninsula revealed no detections of Ae.aegypti.Conclusions This study provides a basis for understanding the distribution and population density fluctuations of Ae.aegypti,assessing its invasion risk,and scientifically conducting relevant prevention and control efforts.

Aim To study the mechanism of salidro-side combined with rosavin in rats with ischemic stroke.Methods The MCAO rats was established by using thread-embolic method.The rats were divided into the sham group,MCAO group,salidroside com-bined with rosavin group,and positive control group;the drug was given continuously for seven days.Western blot was used to detect apoptosis indicators.Proteomics was used to analyse differential proteins(DEPs).STEP receptor inhibitor was injected into the lateral ventricles,the rats were administered for seven days,then the apoptosis indicators were detected.Re-sults Salidroside combined with rosavin could reduce neurological function scores in MCAO rats and inhibit cell apoptosis.Quantitative proteomics identified 496 DEPs in brain tissue and discovered core proteins STEP,p38,and CRTC1.Salidroside combined with rosavin could promote the STEP and CRTC1 while in-hibiting p38 protein.After treatment with STEP inhibi-tor,those effects were reversed.Conclusion Salidro-side combined with rosavin can inhibit cell apoptosis in MCAO rats,which is closely related to the regulation of the STEP/p38/CRTC1 signaling pathway.

Objective To propose a method for mass spectrometry imaging(MSI)super-resolution reconstruction based on a spatially multi-level and self-supervised deep learning network(SMSDL-Net),aiming to improve the resolution of mass spectrometry images.Methods SMSDL-Net firstly registered histological and mass spectrometry images using a nonlinear transformation.Then a multi-branch Vision Transformer(ViT)was utilized to extract hierarchical features of high-resolution histological images in a self-supervised manner.These features were subsequently combined with the paired low-resolution mass spectrometry data to construct a regression network,which could realize the prediction of high-resolution mass spectrometry information.To validate the performance of the proposed method,the results by the method were compared with those of the traditional bicubic interpolation(BI)methods based on interpolation processing and the deepFERE method based on convolution neural network(CNN)for super-resolution reconstruction of magnesium elemental image of metal mass spectrometry of human liver cancer samples,and the method was also applied to a mouse renal adenocarcinoma metabolite mass spectrometry imaging dataset.Results Compared with the traditional BI methods and the deepFERE multimodal method,the method proposed demonstrated the lowest root mean square error(RMSE=0.015),the highest structural similarity index measure(SSIM=0.84)and the highest R-squared value(R2=0.853)in reconstructing mass spectrometry images.The effectiveness of the method and its potential for precise tissue-specific distinction were validated using the mouse renal adenocarcinoma metabolite MSI dataset.Conclusion Compared with traditional single-modal and pixel-wise regression deep learning methods,the method proposed enhances the quality of high-resolution mass spectrometry image reconstruction and can serve as a novel method for super-resolution reconstruction in the field of mass spectrometry imaging.[Chinese Medical Equipment Journal,2025,46(4):1-8]