Objective To investigate the mortality and risk factors of HIV-infected patients complicated with progressive multifocal leukoencephalopathy(PML)to inform the outcomes of these patients.Methods The clinical data of people living with HIV related PML who were treated at Chongqing Public Health Medical Treatment Center from January 1,2019 to December 31,2023 were retrospectively analyzed.Kaplan-Meier method was used for survival analysis.Log-rank test was performed.Cox regression model was used for multivariate analysis.Results A total of 42 people living with HIV related PML were enrolled,including 34 males(81.0％).The median age was 44.5(36.3,51.0)years.PML was confirmed in 76.2％(32/42)of patients,and possible PML was diagnosed in 23.8％(10/42)of patients.The median time to diagnosis was 32.5(14.8,58.3)days.The median CD4+T cell count was 69.0(39.8,112.0)cells/μL.The median HIV viral load was 5.05(2.62,5.77)log10 copies/mL.The overall mortality rate was 54.8％(23/42)for patients with HIV related PML.CD4+T cell count ≤50 cells/μL and initial modified Rankin scale(mRS)score ≥4 points were independent risk factors for the overall mortality of people living with HIV related PML(P＜0.05).Conclusions People living with HIV related PML have a high mortality rate.Low CD4+T cell count and high initial mRS score were independent risk factors for the mortality of patients with HIV related PML.Currently,no definitive and effective drug treatment is available for PML.Early detection,diagnosis and initiation of antiretroviral therapy may improve the outcomes of patients.

Gastroblastoma (GB) is a rare gastric epithelial tumor without special clinical manifestations, whose histologic origin and pathogenesis remain unclear due to less related reports.Low-grade cell forms with biphasic differentiation are typical histological characteristics of GB.Immunohistochemistry and molecular tests can help with its differential diagnosis.GB is an invasive low-grade malignant tumor and the first treatment is surgical resection.However, there is no uniform standard treatment plan at present and most patients have a good prognosis.In this article, the histopathology, diagnosis and identification diagnosis of GB was reviewed to provide a theoretical basis for its origin, development, treatment and patient prognosis.

Objective To investigate the mortality and risk factors of HIV-infected patients complicated with progressive multifocal leukoencephalopathy(PML)to inform the outcomes of these patients.Methods The clinical data of people living with HIV related PML who were treated at Chongqing Public Health Medical Treatment Center from January 1,2019 to December 31,2023 were retrospectively analyzed.Kaplan-Meier method was used for survival analysis.Log-rank test was performed.Cox regression model was used for multivariate analysis.Results A total of 42 people living with HIV related PML were enrolled,including 34 males(81.0％).The median age was 44.5(36.3,51.0)years.PML was confirmed in 76.2％(32/42)of patients,and possible PML was diagnosed in 23.8％(10/42)of patients.The median time to diagnosis was 32.5(14.8,58.3)days.The median CD4+T cell count was 69.0(39.8,112.0)cells/μL.The median HIV viral load was 5.05(2.62,5.77)log10 copies/mL.The overall mortality rate was 54.8％(23/42)for patients with HIV related PML.CD4+T cell count ≤50 cells/μL and initial modified Rankin scale(mRS)score ≥4 points were independent risk factors for the overall mortality of people living with HIV related PML(P＜0.05).Conclusions People living with HIV related PML have a high mortality rate.Low CD4+T cell count and high initial mRS score were independent risk factors for the mortality of patients with HIV related PML.Currently,no definitive and effective drug treatment is available for PML.Early detection,diagnosis and initiation of antiretroviral therapy may improve the outcomes of patients.

Objective:To evaluate the elastic characteristics of the pulmonary trunk and its distal branches in fetuses with tetralogy of Fallot（TOF）by Doppler echocardiography.Methods:A total of 42 fetuses with TOF（TOF group）and 84 gestational age-matched normal fetuses（control group）were prospectively collected from the Second Xiangya Hospital of Central South University from August 2022 to January 2023. The severity of TOF was classified into mild TOF（Z-score≥-2），moderate TOF（-40.05）. Conclusions:Fetuses with TOF present with increased MPA-PAS and decreased stiffness in the distal PA. Histological abnormalities of the pulmonary artery wall in fetuses with TOF have been observed during pregnancy.

Objective:To investigate the feasibility of the ultrasound "triangular method" in evaluating the morphology of the aortic arch in normal mid-to-late trimester fetuses，establish the gestational age-specific reference ranges for its morphological parameters，and to analyze their correlations with gestational age（GA）and cardiac valve annulus diameters.Methods:A prospective study was conducted on 317 normal singleton fetuses at 20-38 +6 weeks of gestation from the Second Xiangya Hospital of Central South University. Morphological parameters including arch length（a+b），arch width（w），arch height（h）and arch angle（θ）were measured using the "triangular method" in the aortic arch long-axis view. Arch tortuosity（a+b/w）and height-to-width ratio（h/w）were calculated. Linear regression was used to analyze correlations between arch length，width，height and GA，the reference intervals were established. Pearson correlation was applied to assess relationships between angle，tortuosity，height-to-width ratio and GA，cardiac valve annulus diameters（aortic，pulmonary，mitral，tricuspid）. Results:Aortic arch length，width and height showed strong positive correlations with GA（ r = 0.88，0.88，0.85；all P < 0.001）. The arch angle，tortuosity，and height-to-width ratio were independent of GA（all P > 0.05），with reference values of（69.2 ± 6.1）°，1.7 ± 0.1，and 0.7 ± 0.1，respectively. These parameters also showed no significant correlations with cardiac valve annulus diameters（all P > 0.05）. Conclusions:The ultrasound "triangular method" systematically quantifies fetal aortic arch morphology. The stability of arch angle，tortuosity and height-to-width ratio during mid-to-late gestation may provide a morphological benchmark for prenatal screening of aortic arch anomalies.

Objective:To evaluate the value of the proposed interpretable denoising deep learning model-grouped sharing convolutional attention-visual transformer（GSCAViT）for classifying normal fetal echocardiograms.Methods:A total of 2 501 images from 358 fetuses who underwent cardiac ultrasound examinations at Xiangya Second Hospital of Central South University from January to November 2024 were retrospectively analyzed. GSCAViT was constructed based on fetal echocardiograms from the three-vessel and trachea view，apical four-chamber view，long-axis view of the aortic arch，bicaval view，left ventricular outflow tract view，three-vessel view and right ventricular outflow tract view were compared with both baseline and improved models in the validation set to assess the performance of the classification echocardiography in terms of accuracy，precision，recall and F1-score. Its generalizability across test sets was assessed using the area under the ROC curve（AUC），sensitivity，specificity and F1-score. The impact of image features was interpreted using SHapley Additive exPlanations（SHAP）.The effectiveness of the GSCA module was compared through visual analysis，image parameter metrics and classification performance.Results:The GSCAViT model achieved classification performance for fetal echocardiograms second only to MaxViT，with an accuracy of 97.1%，precision of 97.1%，recall of 97.0%，and an F1-score of 97.0%. In the E10，E20 and E8 test sets，the AUCs of GSCAViT for the prediction of 7 types of fetal echocardiograms were 0.994，0.928 and 0.932，the sensitivities were 99.4%，81.3% and 72.9%，the specificities were 99.7%，96.8% and 94.8%，the F1-scores were 99.4%，81.3% and 67.6%，respectively. SHAP visualization indicated that the model could identify key structural features within the images. Images processed by the denoising-guided group-sharing convolutional attention module best captured and enhanced important regional features，achieving the highest contrast-to-noise ratio，peak signal-to-noise ratio and optimal classification performance，which demonstrated the module's effectiveness.Conclusions:The proposed GSCAViT model exhibits superior performance in classifying seven types of normal fetal echocardiograms compared to the baseline and some improved models. Furthermore，SHAP visualization enhances the interpretability of the classification results，and visual comparisons，image parameter analyses，as well as classification performance metrics confirming the effectiveness of the denoising-guided group-sharing convolutional attention module in the visual transformer model.

Objective:To propose a processing method of medical image segmentation based on U-Net network with residual connection under single source domain environment,so as to improve the limited diversity of data samples of medical image in the single-source domain environment.Methods:The medical image data under the single-source domain environment were amplified through image transformation,contrast adjustment,and noise addition.The U-Net network was used as the basic structure,and multiple residual connection modules were introduced to achieve reuse of feature.And then,the features at shallow layer were directly transmitted to deep layer,and features at different levels were utilized for segmentation.The input features were added to the features that were processed by partial network layers,thus better learned the features in the data,and constructed medical image segmentation model based on the U-Net network with residual connection.The segmentation model was trained by using the gradient descent method,and the combination of that and the Generalized Dice Loss(GDL)function.Results:The processing method of medical image segmentation based on the U-Net network can effectively achieve segmentation of medical image.Even under low signal-to-noise ratio conditions and facing to different types of segmentation tasks of medical image,the DSC value was greater than 0.90.Conclusion:The processing method of medical image segmentation based on the U-Net network in this study can effectively enhance recognition ability for the features of complex lesions,and increase the segmentation precise of medical images,and improve the accuracy of clinical diagnosis and the effectiveness of treatment.

Objective:To propose a processing method of medical image segmentation based on U-Net network with residual connection under single source domain environment,so as to improve the limited diversity of data samples of medical image in the single-source domain environment.Methods:The medical image data under the single-source domain environment were amplified through image transformation,contrast adjustment,and noise addition.The U-Net network was used as the basic structure,and multiple residual connection modules were introduced to achieve reuse of feature.And then,the features at shallow layer were directly transmitted to deep layer,and features at different levels were utilized for segmentation.The input features were added to the features that were processed by partial network layers,thus better learned the features in the data,and constructed medical image segmentation model based on the U-Net network with residual connection.The segmentation model was trained by using the gradient descent method,and the combination of that and the Generalized Dice Loss(GDL)function.Results:The processing method of medical image segmentation based on the U-Net network can effectively achieve segmentation of medical image.Even under low signal-to-noise ratio conditions and facing to different types of segmentation tasks of medical image,the DSC value was greater than 0.90.Conclusion:The processing method of medical image segmentation based on the U-Net network in this study can effectively enhance recognition ability for the features of complex lesions,and increase the segmentation precise of medical images,and improve the accuracy of clinical diagnosis and the effectiveness of treatment.

Gastroblastoma (GB) is a rare gastric epithelial tumor without special clinical manifestations, whose histologic origin and pathogenesis remain unclear due to less related reports.Low-grade cell forms with biphasic differentiation are typical histological characteristics of GB.Immunohistochemistry and molecular tests can help with its differential diagnosis.GB is an invasive low-grade malignant tumor and the first treatment is surgical resection.However, there is no uniform standard treatment plan at present and most patients have a good prognosis.In this article, the histopathology, diagnosis and identification diagnosis of GB was reviewed to provide a theoretical basis for its origin, development, treatment and patient prognosis.

Objective:To evaluate the elastic characteristics of the pulmonary trunk and its distal branches in fetuses with tetralogy of Fallot（TOF）by Doppler echocardiography.Methods:A total of 42 fetuses with TOF（TOF group）and 84 gestational age-matched normal fetuses（control group）were prospectively collected from the Second Xiangya Hospital of Central South University from August 2022 to January 2023. The severity of TOF was classified into mild TOF（Z-score≥-2），moderate TOF（-40.05）. Conclusions:Fetuses with TOF present with increased MPA-PAS and decreased stiffness in the distal PA. Histological abnormalities of the pulmonary artery wall in fetuses with TOF have been observed during pregnancy.