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.

PURPOSE: Intertrochanteric fracture (ITF) classification is crucial for surgical decision-making. However, orthopedic trauma surgeons have shown lower accuracy in ITF classification than expected. The objective of this study was to utilize an artificial intelligence (AI) method to improve the accuracy of ITF classification. METHODS: We trained a network called YOLOX-SwinT, which is based on the You Only Look Once X (YOLOX) object detection network with Swin Transformer (SwinT) as the backbone architecture, using 762 radiographic ITF examinations as the training set. Subsequently, we recruited 5 senior orthopedic trauma surgeons (SOTS) and 5 junior orthopedic trauma surgeons (JOTS) to classify the 85 original images in the test set, as well as the images with the prediction results of the network model in sequence. Statistical analysis was performed using the SPSS 20.0 (IBM Corp., Armonk, NY, USA) to compare the differences among the SOTS, JOTS, SOTS + AI, JOTS + AI, SOTS + JOTS, and SOTS + JOTS + AI groups. All images were classified according to the AO/OTA 2018 classification system by 2 experienced trauma surgeons and verified by another expert in this field. Based on the actual clinical needs, after discussion, we integrated 8 subgroups into 5 new subgroups, and the dataset was divided into training, validation, and test sets by the ratio of 8:1:1. RESULTS: The mean average precision at the intersection over union (IoU) of 0.5 (mAP50) for subgroup detection reached 90.29%. The classification accuracy values of SOTS, JOTS, SOTS + AI, and JOTS + AI groups were 56.24% ± 4.02%, 35.29% ± 18.07%, 79.53% ± 7.14%, and 71.53% ± 5.22%, respectively. The paired t-test results showed that the difference between the SOTS and SOTS + AI groups was statistically significant, as well as the difference between the JOTS and JOTS + AI groups, and the SOTS + JOTS and SOTS + JOTS + AI groups. Moreover, the difference between the SOTS + JOTS and SOTS + JOTS + AI groups in each subgroup was statistically significant, with all p < 0.05. The independent samples t-test results showed that the difference between the SOTS and JOTS groups was statistically significant, while the difference between the SOTS + AI and JOTS + AI groups was not statistically significant. With the assistance of AI, the subgroup classification accuracy of both SOTS and JOTS was significantly improved, and JOTS achieved the same level as SOTS. CONCLUSION In conclusion, the YOLOX-SwinT network algorithm enhances the accuracy of AO/OTA subgroups classification of ITF by orthopedic trauma surgeons.
Humans ; Hip Fractures/diagnostic imaging* ; Orthopedic Surgeons ; Algorithms ; Artificial Intelligence

OBJECTIVE: To investigate the therapeutic efficacy of cinnamaldehyde (CA) on systemic Candida albicans infection in mice and to provide supportive data for the development of novel antifungal drugs. METHODS: Ninety BALB/c mice were randomly divided into 3 groups according to a random number table: CA treatment group, fluconazole (positive control) group, and Tween saline (negative control) group, with 30 mice in each group. Initially, all groups of mice received consecutive intraperitoneal injections of cyclophosphamide at 200 mg/kg for 2 days, followed by intraperitoneal injection of 0.25 mL C. albicans fungal suspension (concentration of 1.0 × 10⁷ CFU/mL) on the 4th day, to establish an immunosuppressed systemic Candida albicans infection animal model. Subsequently, the mice were orally administered CA, fluconazole and Tween saline, at 240, 240 mg/kg and 0.25 mL/kg respectively for 14 days. After a 48-h discontinuation of treatment, the liver, small intestine, and kidney tissues of mice were collected for fungal direct microscopic examination, culture, and histopathological examination. Additionally, renal tissues from each group of mice were collected for (1,3)- β -D-glucan detection. The survival status of mice in all groups was monitored for 14 days of drug administration. RESULTS: The CA group exhibited a fungal clearance rate of C. albicans above 86.7% (26/30), significantly higher than the fluconazole group (60.0%, 18/30, P<0.01) and the Tween saline group (30.0%, 9/30, P<0.01). Furthermore, histopathological examination in the CA group revealed the disappearance of inflammatory cells and near-normal restoration of tissue structure. The (1,3)-β-D-glucan detection value in the CA group (860.55 ± 126.73 pg/mL) was significantly lower than that in the fluconazole group (1985.13 ± 203.56 pg/mL, P<0.01) and the Tween saline group (5910.20 ± 320.56 pg/mL, P<0.01). The mouse survival rate reached 90.0% (27/30), higher than the fluconazole group (60.0%, 18/30) and the Tween saline group (30.0%, 9/30), with a significant difference between the two groups (both P<0.01). CONCLUSIONS CA treatment exhibited significant therapeutic efficacy in mice with systemic C. albicans infection. Therefore, CA holds potential as a novel antifungal agent for targeted treatment of C. albicans infection.
Animals ; Acrolein/pharmacology* ; Candida albicans/physiology* ; Mice, Inbred BALB C ; Candidiasis/pathology* ; Antifungal Agents/therapeutic use* ; Mice ; Fluconazole/therapeutic use* ; Kidney/drug effects* ; Female

OBJECTIVE: To explore the mechanism of colon dialysis with Yishen Decoction (YS) in improving the autophagy disorder of intestinal epithelial cells in chronic renal failure (CRF) in vivo and in vitro. METHODS: Thirty male SD rats were randomly divided into normal, CRF, and colonic dialysis with YS groups by a random number table method (n=10). The CRF model was established by orally gavage of adenine 200 mg/(kg•d) for 4 weeks. CRF rats in the YS group were treated with colonic dialysis using YS 20 g/(kg•d) for 14 consecutive days. The serum creatinine (SCr) and urea nitrogen (BUN) levels were detected by enzyme-linked immunosorbent assay. Pathological changes of kidney and colon tissues were observed by hematoxylin and eosin staining. Autophagosome changes in colonic epithelial cells was observed with electron microscopy. In vitro experiments, human colon cancer epithelial cells (T84) were cultured and divided into normal, urea model (74U), YS colon dialysis, autophagy activator rapamycin (Ra), autophagy inhibitor 3-methyladenine (3-MA), and SIRT1 activator resveratrol (Re) groups. RT-PCR and Western blot were used to detect the mRNA and protein expressions of zonula occludens-1 (ZO-1), Claudin-1, silent information regulator sirtuin 1 (SIRT1), LC3, and Beclin-1 both in vitro and in vivo. RESULTS: Colonic dialysis with YS decreased SCr and BUN levels in CRF rats (P<0.05), and alleviated the pathological changes of renal and colon tissues. Expressions of SIRT1, ZO-1, Claudin-1, Beclin-1, and LC3II/I were increased in the YS group compared with the CRF group in vivo (P<0.05). In in vitro study, compared with normal group, the expressions of SIRT1, ZO-1, and Claudin-1 were decreased, and expressions of Beclin-1, and LC3II/I were increased in the 74U group (P<0.05). Compared with the 74U group, expressions of SIRT1, ZO-1, and Claudin-1 were increased, whereas Beclin-1, and LC3II/I were decreased in the YS group (P<0.05). The treatment of 3-MA and rapamycin regulated autophagy and the expression of SIRT1. SIRT1 activator intervention up-regulated autophagy as well as the expressions of ZO-1 and Claudin-1 compared with the 74U group (P<0.05). CONCLUSION Colonic dialysis with YS could improve autophagy disorder and repair CRF intestinal mucosal barrier injury by regulating SIRT1 expression in intestinal epithelial cells.
Animals ; Sirtuin 1/metabolism* ; Drugs, Chinese Herbal/therapeutic use* ; Autophagy/drug effects* ; Male ; Intestinal Mucosa/drug effects* ; Rats, Sprague-Dawley ; Epithelial Cells/metabolism* ; Colon/drug effects* ; Humans ; Kidney Failure, Chronic/drug therapy* ; Signal Transduction/drug effects* ; Renal Dialysis ; Rats ; Kidney/drug effects*

Objective To analyze the epidemiological distribution,microbiological characteristics,drug-resistance status,and risk factors for mortality in adult intensive care unit(ICU)patients with Klebsiella pneumoniae infection.Methods This multi-center prospective cohort study included ICU patients with suspected infection from 67 hospitals across 16 Chinese provinces/municipalities between July 1,2021 and December 31,2022.Clinical data and microbiological results were collected,and patients were divided into survival and non-survival groups according to their survival status and drug-resistance situation.Risk factors for mortality and drug resistance in ICU patients with Klebsiella pneumonia infection were determined through univariate and multivariate logistic regression analyses.Results A total of 2964 ICU-infected patients were enrolled,with 12 175 microbial specimens submitted for testing.Among these,487 specimens tested positive for Klebsiella pneumoniae.Ultimately,314 patients with Klebsiella pneumoniae infection were identified,primarily from lung infections,with a drug-resistance rate of 78.3%.The in-hospital mortality rate of ICU patients infected with Klebsiella pneumoniae was 19.8%.Univariate and multivariate logistic regression analyses revealed that older age(P=0.027),high drug-resistance rate(P=0.028),and low clinical-effectiveness rate(P<0.001)were independent risk factors for mortality in ICU patients infected with Klebsiella pneumoniae.Drug-resistance analysis showed that,compared with non-resistant cases,ICU patients with drug-resistant Klebsiella pneumoniae infection had lower pathogen-clearance rates(P=0.003),clinical-effectiveness rates(P=0.004),and antibiotic-effectiveness rates(P<0.010),and higher mortality rates(P=0.006).Patients with Klebsiella pneumoniae abdominal infection(P=0.003)and urinary tract infection(P=0.007)had higher drug-resistance incidences.There were no statistically significant differences in clinical-effectiveness rate,Klebsiella pneumoniae clearance,drug-resistance incidence,mortality rate,or hospital-stay length between patients with lung infection and those with non-lung infection of Klebsiella pneumoniae(P>0.05).Compared with patients with non-bloodstream infection,patients with bloodstream infection of Klebsiella pneumoniae had lower clinical-effectiveness rates(P=0.027)and higher mortality rates(P=0.021).Conclusions Older age,high drug-resistance rate,and low clinical-effectiveness rate are independent risk factors for mortality in ICU patients infected with Klebsiella pneumoniae.ICU patients with bloodstream infection of Klebsiella pneumoniae may have lower clinical-effectiveness rates and higher mortality rates.ICU patients with abdominal and urinary tract infections caused by Klebsiella pneumoniae are more likely to develop drug resistance.

Objective To explore an experimental protocol for differentiating human-induced pluripotent stem cells(iPSCs)into highly pure midbrain dopaminergic(DA)neurons.Methods By optimizing a blend of small molecules and recombinant human growth factors,iPSCs were induced to differentiate into ventral midbrain floor plate DA progenitor cells and subsequently into mature substantia nigra pars compacta DA neurons.Throughout the differentiation process,Real-time PCR and immunofluorescent staining were utilized as a method for quality assessment.Results iPSCs firstly differentiate into dopaminergic precursor cells,and then gradually differentiate into DA neurons expressing tyrosine hydroxylase(TH).Conclusion The protocol successfully yields approximately high purity tyrosine hydroxylase-positive(TH+)DA neurons.This differentiation technique offers an effective cellular model for studying the physiological mechanisms and pathogenesis of Parkinson's disease,providing valuable insights for future research and potential therapeutic strategies.

Facing of mounting resource constraints and rising demands for personalization in medical education,regional anatomy teaching urgently requires transformation.In this paper,we focus on the regional anatomy of the thoracic wall,in order to explore a novel AI-driven teaching paradigm.Anchored in the core principle of"virtual-real integration with cadaveric dissection as the cornerstone,"the paradigm redefines educational objective and constructs an intelligent,closed-loop teaching model integrating students,computers,and instructors.Leveraging the robust support of digital intelligence(e.g.,DeepSeek),this paradigm incorporates interactive method including group collaboration,branching instruction,and gamified assessments.It achieves a comprehensive intelligent transformation of the entire teaching process-from goal setting and plan customization to activity implementation,task completion,outcome exchange,multidimensional evaluation,and reflective iteration.This new paradigm centers on medical students and leverages digital intelligence to activate deep personalized learning potential.It seamlessly integrates fundamental anatomical knowledge with clinical scenarios(e.g.,key anatomy in breast cancer surgery,flap design in breast reconstruction),and significantly enhances clinical decision-making abilities,scientific research and innovative thinking,as well as medical humanistic literacy,paving a new path for intelligent medical education.

Objective To explore how to organically integrate the human anatomy curriculum with medical imaging,thereby enhancing medical students' spatial understanding and 3D reconstruction skills,and strengthening their anatomical foundation and clinical competence.This approach aims to bridge the gap between basic science and clinical practice while cultivating clinical thinking abilities.Methods In this study,the medical imaging knowledge was introduced into the anatomy curriculum in Peking University,enabling students to better understand the human body structure and its relationship to the clinical practice with aid of the ultrasound and MRI method.After the course concluded,we evaluated the examination result and learning satisfaction data from the anatomy course.Results The result showed that students provided positive feedback,showing increased interest in learning,enhanced initiative,significant improvement in their anatomy grades(P＜0.01),and a notable enhancement in their ability to apply basic knowledge to solve clinical problems(P＜0.05).Conclusion The integrated teaching approach of medical imaging and human anatomy courses provides innovative ideas and practical method for medical students to learn the basic medical course and enhance their clinical skills in the future.

Objective To understand the implementation status of"Diagnosis of Ascariasis"(WS/T 565-2017)and provide a scientific basis for promoting,revising,and improving the Standard.Methods Using the convenient sampling method,the investigation targeted professional and technical personnel at the provincial,city,county,and township levels engaged in parasitic disease prevention,control,or diagnosis and treatment in Anhui and Sichuan provinces.No less than 150 individuals were included in each province.The implementation survey of Diagnosis of Ascariasis(WS/T 565-2017)was conducted by the subjects completing a questionnaire by themselves.Results The response rate to the questionnaire was 91.90%(386/420).The awareness and utilization rates of the Standard were 81.87%and 49.22%,respectively and both increased with age(χ2 trend=7.977 and 19.016,respectively,P＜0.01).Respondents with college degrees(90.72%)had a higher awareness rate(χ2=8.619,P＜0.05).In terms of utilization rate,males(58.38%),those with college degrees(67.01%),staff members of provincial-level units(77.78%),and personnel in medical institutions(71.43%)had higher utilization rates(χ2=13.486,17.166,8.426,and 5.956,respectively,all P＜0.05).The survey indicated that 57.77%of the work units of respondents have conducted promotional activities,and 53.89%of the work units of respondents have sent personnel to participate in training.Moreover,this proportion tended to increase as the unit level decreased(χ2 trend=9.403 and 14.729,P＜0.01).The level of participation in publicity and training by medical institutions(89.29%)was significantly higher than that of disease control institutions(55.31%and 51.12%,respectively,χ2=12.290 and 15.225,P＜0.01).Furthermore,training participation is a crucial factor in enhancing awareness rates.A total of 368 respondents(95.34%)reported that their work units have conducted testing for ascariasis.Additionally,378 individuals(97.92%)believe that the Standard is"applicable"or"basically applicable,"while 369(95.60%)felt that no revisions were needed.Conclusions The results indicated that"Diagnosis of Ascariasis"(WS/T 565-2017)remains applicable to the diagnostic needs of ascariasis and it is recommended to strengthen its promotion and implementation.