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 investigate the effect of thrombocytopenia and coagulation dysfunction on bleeding complications in patients undergoing percutaneous liver biopsy.Methods:The clinical, laboratory, and demographic data of patients undergoing percutaneous liver biopsy at the First Affiliated Hospital of Air Force Medical University from January 2005 to January 2024 were retrospectively analyzed. The incidence of bleeding was recorded. Univariate and multivariate logistic regression analyses were used to assess the effects of thrombocytopenia and coagulation dysfunction on the risk of postoperative bleeding. Furthermore, we assessed the bleeding risk in patients with autoimmune hepatitis.Results:A total of 2 885 liver perforations were performed in 2 364 patients, 98.4% of whom had an autoimmune liver disease. There were 27 cases of postoperative bleeding (0.9%). The univariate logistic regression analysis showed that platelet count (PLT)( P<0.05, OR=0.975), coagulation dysfunction (international normalized ratio; INR)( P<0.05, OR=6.954), and cirrhosis ( P<0.05, OR=3.857) were associated with bleeding. The multivariate logistic regression analysis showed that PLT was an independent risk factor for bleeding ( P<0.05, OR=0.975). PLT scores of 40×10 9/L and 65×10 9/L can classify the bleeding risk of patients with thrombocytopenia into high, medium, and low risk. There was no difference in the risk of bleeding between the 40×10 9/L0.05, χ2=0.10). The risk of bleeding in the 31×10 9/L≤PLT≤40×10 9/L group was higher than that in the 40×10 9/L0.05, χ2=0.10). Furthermore, the bleeding cases were considered mild as the bleeding stopped after pressure hemostasis. Conclusions:PLT is an independent risk factor for bleeding after hepatocentesis. When the PLT is >40×10 9/L, hepatocentesis can still be performed safely with appropriate management measures.

Objective:To evaluate the quality of information on autoimmune liver disease in videos on the TikTok short video platform.Methods:The keyword "autoimmune liver disease" was used to search the top 200 videos on TikTok in the default sorting order. Using the DISCERN video quality assessment tool and the structured content integrity evaluation tool, we assessed the quality of the information in each video in relation to the pertinent disease guidelines. Furthermore, we investigated any relationships between the quality of the videos and their characteristics (likes, comments, retweets, days and duration of uploading).Results:A total of 140 videos were included, 96.4% of which were provided by medical professionals. The content completeness scores for each dimension were as follows: definition, 1.0 (0.0, 1.0); symptoms, 0.0 (0.0, 1.0); risk factors, 0.0 (0.0, 0.5); assessment, 0.5 (0.0, 1.5); management, 0.5 (0.0, 1.0); and outcome, 0.0 (0.0, 1.0). Furthermore, 91.4% of videos with DISCERN scores of ≤50 were of "fair" quality or below. Additionally, the difference in DISCERN scores between videos from different publishers was not statistically significant ( P>0.05). The number of likes, comments, favorites, retweets, and video duration had a strong positive correlation with the overall DISCERN score ( r=0.17, 0.18, 0.25, 0.26, 0.44, all P<0.05). Conclusions:The overall quality of videos related to autoimmune liver disease on the TikTok video platform is low. Therefore, publishers should focus on the comprehensiveness and accuracy of the information. Additionally, the TikTok platform should optimize its video review mechanism to provide the public with more accurate and reliable health information.

Objective To establish a highly sensitive and specific method for detecting human DNA based on real time quantitative PCR(qPCR)technique for the rapid detection of potential DNA con-tamination sources in DNA laboratories.Methods Primers and probes were designed with Primer Ex-pressTM software using the reference sequence of human 18S rRNA gene as a template,and the opti-mal prime-probe combination was screened by matrix method.The PCR products of the target se-quence of human 18S rRNA gene were used to construct the plasmid,and a plasmid standard was used to draw the standard curve of the qPCR system.According to the Minimum Information for Pub-lication of Quantitative Real-time PCR Experiments(MIQE)guidelines,the specificity,sensitivity,re-peatability and application effect of the qPCR system were evaluated.Results The sensitivity of the qPCR system established in this study was 5.3×10-5 ng/μL,which showed good specificity for human DNA samples.The correlation coefficient of the qPCR system was-0.999,and amplification efficiency was 100％.Both the intra-batch and inter-batch variation coefficients were less than 2％.Conclusion The established human DNA detection method based on qPCR technique has good specificity,high sen-sitivity,and robust stability.It can be used for rapid detection of DNA contamination and daily moni-toring of the accumulated human DNA in the laboratory environment.

Objective To compare and analyze the germicidal efficacy of continuous ultraviolet and pulsed ultravio-let(UV)lasers on pathogenic microorganisms.Methods Spore slides of Escherichia coli and Bacillus atrophaeus were irradiated using a 254 nm ultraviolet mercury lamp and UV laser.The carrier quantitative germicidal test was conducted to determine the disinfection efficacy at different irradiation doses.Results When the irradiation dose of the ultraviolet mercury lamp was 245.52 mJ/cm2,the logarithmic killing values of Escherichia coli and Bacillus atro-phaeus spores were 5.00 and 2.92,respectively,and the mean logarithmic killing doses were 49.10 and 84.08 mJ/cm2,respectively;When the UV laser irradiation doses were 208.39 and 206.80 mJ/cm2,the logarithmic killing values for the two microorganisms were 6.29 and 3.32,respectively,and the mean logarithmic killing doses were 33.13 and 62.29 mJ/cm2,respectively.Conclusion Compared with continuous UV radiation,pulsed UV laser has stron-ger penetration ability,better killing efficacy on pathogenic microorganisms at the same radiation dose,and can con-duct targeted disinfection and sterilization on the surface of objects directionally.

Turning to critical illness is a common stage of various diseases and injuries before death. Patients usually have complex health conditions, while the treatment process involves a wide range of content, along with high requirements for doctor′s professionalism and multi-specialty teamwork, as well as a great demand for time-sensitive treatments. However, this is not matched with critical care professionals and the current state of medical care in China. Telemedicine, which shortens the distance of medical professionals and the gap of disease diagnosis and treatments in various regions through electronic information, can effectively solve the current problem. Therefore, there is an urgent need to develop a standardized, high-quality visualization telemedicine round system .Therefore, experts have been organized to search domestic and foreign literature on telemedicine round for critically ill patients and to form this consensus based on clinical experiences so as to further improve the level of critical care treatments in regions.

Objective:To investigate the effect of thrombocytopenia and coagulation dysfunction on bleeding complications in patients undergoing percutaneous liver biopsy.Methods:The clinical, laboratory, and demographic data of patients undergoing percutaneous liver biopsy at the First Affiliated Hospital of Air Force Medical University from January 2005 to January 2024 were retrospectively analyzed. The incidence of bleeding was recorded. Univariate and multivariate logistic regression analyses were used to assess the effects of thrombocytopenia and coagulation dysfunction on the risk of postoperative bleeding. Furthermore, we assessed the bleeding risk in patients with autoimmune hepatitis.Results:A total of 2 885 liver perforations were performed in 2 364 patients, 98.4% of whom had an autoimmune liver disease. There were 27 cases of postoperative bleeding (0.9%). The univariate logistic regression analysis showed that platelet count (PLT)( P<0.05, OR=0.975), coagulation dysfunction (international normalized ratio; INR)( P<0.05, OR=6.954), and cirrhosis ( P<0.05, OR=3.857) were associated with bleeding. The multivariate logistic regression analysis showed that PLT was an independent risk factor for bleeding ( P<0.05, OR=0.975). PLT scores of 40×10 9/L and 65×10 9/L can classify the bleeding risk of patients with thrombocytopenia into high, medium, and low risk. There was no difference in the risk of bleeding between the 40×10 9/L0.05, χ2=0.10). The risk of bleeding in the 31×10 9/L≤PLT≤40×10 9/L group was higher than that in the 40×10 9/L0.05, χ2=0.10). Furthermore, the bleeding cases were considered mild as the bleeding stopped after pressure hemostasis. Conclusions:PLT is an independent risk factor for bleeding after hepatocentesis. When the PLT is >40×10 9/L, hepatocentesis can still be performed safely with appropriate management measures.

Objective:To evaluate the quality of information on autoimmune liver disease in videos on the TikTok short video platform.Methods:The keyword "autoimmune liver disease" was used to search the top 200 videos on TikTok in the default sorting order. Using the DISCERN video quality assessment tool and the structured content integrity evaluation tool, we assessed the quality of the information in each video in relation to the pertinent disease guidelines. Furthermore, we investigated any relationships between the quality of the videos and their characteristics (likes, comments, retweets, days and duration of uploading).Results:A total of 140 videos were included, 96.4% of which were provided by medical professionals. The content completeness scores for each dimension were as follows: definition, 1.0 (0.0, 1.0); symptoms, 0.0 (0.0, 1.0); risk factors, 0.0 (0.0, 0.5); assessment, 0.5 (0.0, 1.5); management, 0.5 (0.0, 1.0); and outcome, 0.0 (0.0, 1.0). Furthermore, 91.4% of videos with DISCERN scores of ≤50 were of "fair" quality or below. Additionally, the difference in DISCERN scores between videos from different publishers was not statistically significant ( P>0.05). The number of likes, comments, favorites, retweets, and video duration had a strong positive correlation with the overall DISCERN score ( r=0.17, 0.18, 0.25, 0.26, 0.44, all P<0.05). Conclusions:The overall quality of videos related to autoimmune liver disease on the TikTok video platform is low. Therefore, publishers should focus on the comprehensiveness and accuracy of the information. Additionally, the TikTok platform should optimize its video review mechanism to provide the public with more accurate and reliable health information.

Multimodal precision nursing intervention enhances cognitive function and quality of life through multisensory collabo-rative stimulation by integrating multidimensional data of patients.As one of the most common complications after radical prostatecto-my,urinary incontinence seriously affects the quality of life of prostate cancer patients after surgery which has a negative impact on multidimensional health in the"physiological-psychological-social"aspects.This paper summarizes the clinical manifestations,influ-encing factors,and nursing interventions of urinary incontinence after radical prostatectomy,and focuses on the key points of nursing based on multimodal theory,in order to provide nursing strategies for improving urinary incontinence after prostate cancer surgery.