Objective:To investigate the predictive value of a machine learning model combining contrast-enhanced ultrasound（CEUS）parameters，radiomics features of ultrasound images，and clinical data for pathological grading in bladder urothelial carcinoma（BUC）.Methods:A retrospective analysis was conducted on 174 BUC patients from Inner Mongolia Autonomous Region People 's Hospital and the First Affiliated Hospital of Baotou Medical College from December 2017 to March 2024. One hundred and thirteen BUC patients from the former hospital were randomly divided into training group and internal test group in a ratio of 7 to 3，while 61 BUC patients from the latter hospital served as an external test group. The patients were stratified into low-grade bladder urothelial carcinoma（LGBUC）and high-grade bladder urothelial carcinoma（HGBUC）groups based on pathology. Two-dimensional grayscale ultrasound images were subjected to super-resolution（SR）reconstruction，followed by extraction and screening of radiomics features in comparison with CEUS video sequences. Selected features were input into a support vector machine（SVM）to build the radiomics model. CEUS parameters，conventional ultrasound metrics and clinical data with statistical significance between LGBUC and HGBUC groups were input into SVM to construct the clinical model. The radiomics and clinical model outputs were fused via multivariate Logistic regression to form a combined model. Model performances were evaluated using ROC curves，calibration curves，and clinical decision curves. Results:Seven radiomics features from SR images were used to build the radiomics model，while CEUS parameters（peak intensity and time-to-peak half），age，tumor-wall interface and tumor-wall angle formed the clinical model. The combined model integrated these outputs. All 3 models exhibited respective strengths，the combined model showed superior robustness. The AUCs of the combined model in the training，internal test and external test groups were 0.92，0.84 and 0.82，respectively.Conclusions:The combined model combining CEUS parameters，ultrasound radiomics features，and clinical data accurately predicts BUC pathological grade，providing a potential tool for clinical diagnosis and treatment.

Objective:To investigate the predictive value of a machine learning model combining contrast-enhanced ultrasound（CEUS）parameters，radiomics features of ultrasound images，and clinical data for pathological grading in bladder urothelial carcinoma（BUC）.Methods:A retrospective analysis was conducted on 174 BUC patients from Inner Mongolia Autonomous Region People 's Hospital and the First Affiliated Hospital of Baotou Medical College from December 2017 to March 2024. One hundred and thirteen BUC patients from the former hospital were randomly divided into training group and internal test group in a ratio of 7 to 3，while 61 BUC patients from the latter hospital served as an external test group. The patients were stratified into low-grade bladder urothelial carcinoma（LGBUC）and high-grade bladder urothelial carcinoma（HGBUC）groups based on pathology. Two-dimensional grayscale ultrasound images were subjected to super-resolution（SR）reconstruction，followed by extraction and screening of radiomics features in comparison with CEUS video sequences. Selected features were input into a support vector machine（SVM）to build the radiomics model. CEUS parameters，conventional ultrasound metrics and clinical data with statistical significance between LGBUC and HGBUC groups were input into SVM to construct the clinical model. The radiomics and clinical model outputs were fused via multivariate Logistic regression to form a combined model. Model performances were evaluated using ROC curves，calibration curves，and clinical decision curves. Results:Seven radiomics features from SR images were used to build the radiomics model，while CEUS parameters（peak intensity and time-to-peak half），age，tumor-wall interface and tumor-wall angle formed the clinical model. The combined model integrated these outputs. All 3 models exhibited respective strengths，the combined model showed superior robustness. The AUCs of the combined model in the training，internal test and external test groups were 0.92，0.84 and 0.82，respectively.Conclusions:The combined model combining CEUS parameters，ultrasound radiomics features，and clinical data accurately predicts BUC pathological grade，providing a potential tool for clinical diagnosis and treatment.

Objective:To investigate the value of the combined ultrasound imaging radiomics model for predicting progression-free survival in endocrine therapy for prostate cancer.Methods:A total of 283 prostate cancer patients who received endocrine treatment at the Inner Mongolia Autonomous Region People′s Hospital and the First Hospital of Hohhot from July 2018 to January 2023 were retrospectively collected, of which 198 patients from the Inner Mongolia Autonomous Region People′s Hospital were randomly divided into the training set and the validation set according to the ratio of 7∶3, and 85 patients from the First Hospital of Hohhot served as an independent external test set. They were classified into a progression group and a non-progression group based on whether the patients progressed to desmoplasia-resistant prostate cancer 18 months after the start of endocrine treatment.Based on the two-dimensional ultrasound images, the imaging radiomics features were extracted and the imaging radiomics score (Rad-score) were constructed, the immunopathology and other clinical data were analysed, and three prediction models were constructed using logistic regression: the clinical model, the ultrasonography model, and the ultrasonography-clinical combined model, respectively. The predictive efficacy and clinical utility of the models were assessed by the ROC curves and clinical decision curves.Results:Five ultrasonographic features were included in the ultrasound model; the prostate-specific antigen nadir, the neutrophil-to-lymphocyte ratio before treatment, and the expression level of tumour proliferating cell nuclear antigen 67 (Ki-67) were incorporated into the clinical model; and the Rad score computed from the output of the ultrasound model for the screening features, together with the prostate-specific antigen nadir (PSA nadir), the neutrophil to lymphocyte ratio (NLR) before treatment, and the expression level of Ki-67 were used to construct the ultrasound-clinical joint model. The joint model achieved the highest predictive performance in both the training and validation sets of the three groups of models, with the area under the curve of 0.85 and 0.84, and the clinical decision curve showed good clinical benefit.Conclusions:The combined ultrasound-clinical model constructed in this study based on two-dimensional ultrasound images of prostate cancer before endocrine therapy can predict progression-free survival of endocrine therapy for prostate cancer more accurately.

Objective:To evaluate the utility of whole-exome sequencing (WES) in early diagnosis for children with language delay/disorder.Methods:Children with language delay/disorder who were admitted to the Department of Health Care, Children′s Hospital Affiliated to the Capital Pediatric Institute from January 2019 to December 2020 were analyzed retrospectively. Based on informed consent, the peripheral blood of the children and their parents was collected for WES. Combining the clinical phenotypes of the children, the candidate variants, including single nucleotide variants (SNVs) and copy number variations (CNVs), were selected for validation and family segregation analysis using Sanger sequencing, real-time PCR or CNV-Seq. The pathogenicity of variants was evaluated based on ACMG guideline following with finial genetic diagnosis. Based on whether genetic diagnosis was achieved or not, 125 children with comprehensive examination of the Children Neuropsychological and Behavioral Scale(CNBS-R2016) were sub-grouped (positive/negative group), and the total scores and the detailed scores of five developmental sections (gross motor, fine motor, adaptive ability, language and social behavior ability) between two subgroups were compared.Results:A total of 165 children with language delay/disorder were recruited, including 109 males and 56 females. The ratio of boys to girls was 1.95∶1.The age of the children was (3.2±1.2) years old, the median age was 3.0 years. 45 children carry disease-related pathogenic/likely pathogenic variants, including 36 SNVs and 9 CNVs. The genetic diagnostic yield of this cohort was 27.3% (45/165). The inheritance analysis for core family members showed de novo variant accounted for 86% of genetic diagnosis (31/36). The positive diagnosis rate in girls was 45% (25/56), which was significantly higher than that in boys (18.3%, 20/109, χ2=12.171, P<0.05). There was no significant difference in the rate of positive diagnosis among all age groups (χ2=4.349, P>0.05). Interestingly, the scores of gross motors of positive group were significantly lower than that of negative group (61.5 vs. 69.4, t=-2.610, P<0.05). Otherwise, no significant difference was seen between two groups( t=-0.933, -1.298, -0.114, -0.214, all P>0.05). Conclusions:Language delay/disorder has complex genetic heterogeneity. WES has important application value in early etiological diagnosis for children with language delay/disorder.

Objective:To evaluate the utility of whole-exome sequencing (WES) in early diagnosis for children with language delay/disorder.Methods:Children with language delay/disorder who were admitted to the Department of Health Care, Children′s Hospital Affiliated to the Capital Pediatric Institute from January 2019 to December 2020 were analyzed retrospectively. Based on informed consent, the peripheral blood of the children and their parents was collected for WES. Combining the clinical phenotypes of the children, the candidate variants, including single nucleotide variants (SNVs) and copy number variations (CNVs), were selected for validation and family segregation analysis using Sanger sequencing, real-time PCR or CNV-Seq. The pathogenicity of variants was evaluated based on ACMG guideline following with finial genetic diagnosis. Based on whether genetic diagnosis was achieved or not, 125 children with comprehensive examination of the Children Neuropsychological and Behavioral Scale(CNBS-R2016) were sub-grouped (positive/negative group), and the total scores and the detailed scores of five developmental sections (gross motor, fine motor, adaptive ability, language and social behavior ability) between two subgroups were compared.Results:A total of 165 children with language delay/disorder were recruited, including 109 males and 56 females. The ratio of boys to girls was 1.95∶1.The age of the children was (3.2±1.2) years old, the median age was 3.0 years. 45 children carry disease-related pathogenic/likely pathogenic variants, including 36 SNVs and 9 CNVs. The genetic diagnostic yield of this cohort was 27.3% (45/165). The inheritance analysis for core family members showed de novo variant accounted for 86% of genetic diagnosis (31/36). The positive diagnosis rate in girls was 45% (25/56), which was significantly higher than that in boys (18.3%, 20/109, χ2=12.171, P<0.05). There was no significant difference in the rate of positive diagnosis among all age groups (χ2=4.349, P>0.05). Interestingly, the scores of gross motors of positive group were significantly lower than that of negative group (61.5 vs. 69.4, t=-2.610, P<0.05). Otherwise, no significant difference was seen between two groups( t=-0.933, -1.298, -0.114, -0.214, all P>0.05). Conclusions:Language delay/disorder has complex genetic heterogeneity. WES has important application value in early etiological diagnosis for children with language delay/disorder.