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 investigate whether Tasquinimod can influence cisplatin resistance in drug-resistant ovarian cancer (OC) cell lines by regulating histone deacetylase 4 (HDAC4) or p21, we explored its effects on the cell cycle, and associated mechanisms.RT-PCR and Western blot analyses, flow cytometry, CCK8 assay, and immunofluorescence were utilized to investigate the effects of Tasquinimod on gene expression, cell cycle, apoptosis, viability, and protein levels in OC cells. The results showed that Tasquinimod inhibited cell viability and promoted apoptosis in SKOV3/DDP (cisplatin) and A2780/DDP cells more effectively than DDP alone. In combination with cisplatin, Tasquinimod further enhanced cell apoptosis and reduced cell viability in these cell lines, an effect that could be reversed following HDAC4 overexpression. Tasquinimod treatment down-regulated HDAC4, Bcl-2, and cyclin D1, and CDK4 expression and up-regulated the cleaved-Caspase-3, and p21 expression in SKOV3/DDP and A2780/ DDP cells. Additionally, Tasquinimod inhibited DDP resistance in OC/DDP cells. These effects were similarly observed in OC mouse models treated with Tasquinimod. In conclusion, Tasquinimod can improve OC cells' sensitivity to DDP by down-regulating the HDAC4/p21 axis, offering insights into potential strategies for overcoming cisplatin resistance in OC.

Fear of disease progression(FoP)is a common psychological state among patients with coronary heart dis-ease(CHD),which exists throughout the course of disease and seriously affects the prognosis.High level of FoP not only harms the mental health of patients but also do not benefit their rehabilitation after discharge.This concept was first proposed by foreign researchers studying the psychological state of cancer patients.In recent years,there have been numerous studies on the influencing factors and qualitative aspects of FoP in CHD patients,while related inter-vention studies remain few.This paper reviews the concept,scales and related influencing factors of FoP,providing ideas for medical staff to provide targeted interventions for CHD patients.

Pulmonary hypertension (PH) is a group of progressive diseases characterized by pulmonary vascular remodeling,and some patients already have right heart insufficiency at the time of diagnosis. Therefore,early diagnosis of PH is essential to improve patients' quality of life and prolong survival. Biomarkers are an important indicator for early diagnosis of the disease,and there are many traditional biomarkers for PH diagnosis,but the sensitivity and specificity are low. With the progress of research,some new biomarkers have been shown to predict disease progression in early PH and play an important role in the early diagnosis of PH. This study reviews the research progress of biomarkers of PH from the aspects of right heart insufficiency,endothelial dysfunction,pulmonary artery smooth muscle dysfunction,inflammation,and in situ thrombosis to provide exploration direction and reference value for early diagnosis of PH.

Fear of disease progression(FoP)is a common psychological state among patients with coronary heart dis-ease(CHD),which exists throughout the course of disease and seriously affects the prognosis.High level of FoP not only harms the mental health of patients but also do not benefit their rehabilitation after discharge.This concept was first proposed by foreign researchers studying the psychological state of cancer patients.In recent years,there have been numerous studies on the influencing factors and qualitative aspects of FoP in CHD patients,while related inter-vention studies remain few.This paper reviews the concept,scales and related influencing factors of FoP,providing ideas for medical staff to provide targeted interventions for CHD patients.

Objective To understand the current status of work-related musculoskeletal disorders (WMSDs) among operating room doctors,thereby analyzing its effect on mental health. Methods A total of 1013 doctors in the operating rooms of 30 hospitals in 24 provinces from September to December 2022 were selected by cross-sectional survey method. The domestic musculoskeletal disease questionnaire was used to investigate the occurrence of WMSDs in operating room doctors,the symptom check list-90 (SCL-90) was used to evaluate the psychological status of operating room doctors,the relationship between WMSDs related items and SCL-90 scores was analyzed,the correla-tion between the rest time of each shift and SCL-90 factors was analyzed by Pearson method,and the influencing factors of mental health of operating room doctors were analyzed by multivariate Logistic regression.Results A total of 1100 questionnaires were distributed and 1013 valid questionnaires were recovered,with an effective rate of 92.10％. The incidence of WMSDs among operating room doctors in the past 1 year was 95.06％. The body parts with incidences of WMSDs from high to low were as follows:waist (36.92％),neck (35.54％),shoulder (33.56％),and upper back (32.77％). In the past 1 year,the SCL-90 scores and total scores of patients with musculoskeletal pain in various body parts,keeping the same back posture for a long time while work,bending the back at the same time of turning frequently while working,bowing the head for a long time while working,and bending the knee for a long time while working were significantly higher than those who were without the above conditions (P<0.05). Shorter rest time of each shift and longer periods of keeping the same back posture were the risk factors for the development of mental illness in operating room doctors. Conclusion The incidence of WMSDs in operating room doctors is high,which can influence the mental health of operating room doctors. Therefore,operating room doctors should avoid keeping the same back posture for a long time,bending the back at the same time of turning frequently,bowing the head for a long time,and bending the knee for a long time while working,and increase the rest time of each shift,in order to improve the mental condition of the operating room doctors.

To investigate whether Tasquinimod can influence cisplatin resistance in drug-resistant ovarian cancer (OC) cell lines by regulating histone deacetylase 4 (HDAC4) or p21, we explored its effects on the cell cycle, and associated mechanisms.RT-PCR and Western blot analyses, flow cytometry, CCK8 assay, and immunofluorescence were utilized to investigate the effects of Tasquinimod on gene expression, cell cycle, apoptosis, viability, and protein levels in OC cells. The results showed that Tasquinimod inhibited cell viability and promoted apoptosis in SKOV3/DDP (cisplatin) and A2780/DDP cells more effectively than DDP alone. In combination with cisplatin, Tasquinimod further enhanced cell apoptosis and reduced cell viability in these cell lines, an effect that could be reversed following HDAC4 overexpression. Tasquinimod treatment down-regulated HDAC4, Bcl-2, and cyclin D1, and CDK4 expression and up-regulated the cleaved-Caspase-3, and p21 expression in SKOV3/DDP and A2780/ DDP cells. Additionally, Tasquinimod inhibited DDP resistance in OC/DDP cells. These effects were similarly observed in OC mouse models treated with Tasquinimod. In conclusion, Tasquinimod can improve OC cells' sensitivity to DDP by down-regulating the HDAC4/p21 axis, offering insights into potential strategies for overcoming cisplatin resistance in OC.

Pulmonary hypertension (PH) is a group of progressive diseases characterized by pulmonary vascular remodeling,and some patients already have right heart insufficiency at the time of diagnosis. Therefore,early diagnosis of PH is essential to improve patients' quality of life and prolong survival. Biomarkers are an important indicator for early diagnosis of the disease,and there are many traditional biomarkers for PH diagnosis,but the sensitivity and specificity are low. With the progress of research,some new biomarkers have been shown to predict disease progression in early PH and play an important role in the early diagnosis of PH. This study reviews the research progress of biomarkers of PH from the aspects of right heart insufficiency,endothelial dysfunction,pulmonary artery smooth muscle dysfunction,inflammation,and in situ thrombosis to provide exploration direction and reference value for early diagnosis of PH.

To investigate whether Tasquinimod can influence cisplatin resistance in drug-resistant ovarian cancer (OC) cell lines by regulating histone deacetylase 4 (HDAC4) or p21, we explored its effects on the cell cycle, and associated mechanisms.RT-PCR and Western blot analyses, flow cytometry, CCK8 assay, and immunofluorescence were utilized to investigate the effects of Tasquinimod on gene expression, cell cycle, apoptosis, viability, and protein levels in OC cells. The results showed that Tasquinimod inhibited cell viability and promoted apoptosis in SKOV3/DDP (cisplatin) and A2780/DDP cells more effectively than DDP alone. In combination with cisplatin, Tasquinimod further enhanced cell apoptosis and reduced cell viability in these cell lines, an effect that could be reversed following HDAC4 overexpression. Tasquinimod treatment down-regulated HDAC4, Bcl-2, and cyclin D1, and CDK4 expression and up-regulated the cleaved-Caspase-3, and p21 expression in SKOV3/DDP and A2780/ DDP cells. Additionally, Tasquinimod inhibited DDP resistance in OC/DDP cells. These effects were similarly observed in OC mouse models treated with Tasquinimod. In conclusion, Tasquinimod can improve OC cells' sensitivity to DDP by down-regulating the HDAC4/p21 axis, offering insights into potential strategies for overcoming cisplatin resistance in OC.