Purpose To investigate the immunohistochemical HER2 expression in a large group of patients with urothelial carcinoma and to compare the results with the pathologic features and survival rate.Methods A total of 519 urothelial carcinoma specimens were collected from two centers.HER2 expression was measured by EnVision immuno-histochemistry.HER2 expression was compared with clinicopathological parameters,and further analyzed in relation to patient prognosis.Results The median age of the 519 patients was 66 years with a male to female ratio of 1.93∶1.Among them,160 cases were radical specimens,and 359 were transurethral resection specimens.The overall HER2 positivity rate was 61.7％(320/519),of which 148 cases(28.5％)were HER2 1+,238(45.9％)were HER2 2+,and 82(15.8％)were HER2 3+.In addition,51 cases(9.8％)were HER2-negative.HER2-positive ex-pression was associated with age,tumor location,histological grade,histological type,surgical approach,lymphovas-cular invasion,and neural invasion(all P＜0.05),but there was no significant correlation with gender,pT stage,muscular invasion,or lymph node metastasis.Univariate and multivariate logistic regression analysis showed that age≥ 66 years,higher tumor grade,and lymphovascular invasion were risk factors for positive HER2 expression,and high histological grade and lymphovascular invasion were independent risk factors affecting HER2 expression after controlling for confounders.Survival analysis showed no significant difference in recurrence-free survival between patients with HER2-positive and HER2-negative non-muscle-invasive urothelial carcinoma(P=0.274).Conclusion High histologic grade,tumor lymphovascular invasion,and neural invasion were associated with positive HER2 expression in patients with urothelial carcinoma,and higher histologic grade and lymphovascular invasion are important factors affect-ing HER2 expression.However,HER2-positive expression may not affect the prognosis of patients with non-muscle-invasive bladder urothelial carcinoma.

Objective:To investigate the prognostic value of deep learning-based automated quantification of tumor-stroma ratio (TSR) in patients undergoing neoadjuvant therapy (NAT) for breast cancer.Methods:Specimens were collected from 209 breast cancer patients who received NAT at Renmin Hospital of Wuhan University from October 2019 to June 2023. TSR levels in pre-NAT biopsy specimens were automatically computed using a deep learning algorithm and categorized into low stroma (TSR≤30%), intermediate stroma (TSR 30% to ≤60%), and high stroma (TSR>60%) groups. Residual cancer burden (RCB) grading of post-NAT surgical specimens was determined to compare the relationship between TSR expression levels and RCB grades. The correlation of TSR with NAT efficacy was analyzed, and the association between TSR expression and patient prognosis was further investigated.Results:There were 85 cases with low stroma (TSR≤30%), 93 cases with intermediate stroma (TSR 30% to ≤60%), and 31 cases with high stroma (TSR>60%). Different TSR expression levels showed significant differences between various RCB grades ( P<0.05). Logistic univariate and multivariate analyses showed that TSR was a risk factor for obtaining a complete pathological remission from neoadjuvant therapy for breast cancer when it was used as a continuous variable ( P<0.05); COX regression and survival analyses showed that the lower the percentage of tumorigenic mesenchyme was, the better the prognosis of the patient was ( P<0.05). Conclusions:The deep learning-based model enables automatic and accurate quantification of TSR. A lower pre-treatment tumoral stroma is associated with a lower RCB score and a higher rate of pathologic complete response, indicating that TSR can predict the efficacy of neoadjuvant therapy in breast cancer and thus holds prognostic significance. Therefore, TSR may serve as a biomarker for predicting therapeutic outcomes in breast cancer neoadjuvant therapy.

Purpose To investigate the immunohistochemical HER2 expression in a large group of patients with urothelial carcinoma and to compare the results with the pathologic features and survival rate.Methods A total of 519 urothelial carcinoma specimens were collected from two centers.HER2 expression was measured by EnVision immuno-histochemistry.HER2 expression was compared with clinicopathological parameters,and further analyzed in relation to patient prognosis.Results The median age of the 519 patients was 66 years with a male to female ratio of 1.93∶1.Among them,160 cases were radical specimens,and 359 were transurethral resection specimens.The overall HER2 positivity rate was 61.7％(320/519),of which 148 cases(28.5％)were HER2 1+,238(45.9％)were HER2 2+,and 82(15.8％)were HER2 3+.In addition,51 cases(9.8％)were HER2-negative.HER2-positive ex-pression was associated with age,tumor location,histological grade,histological type,surgical approach,lymphovas-cular invasion,and neural invasion(all P＜0.05),but there was no significant correlation with gender,pT stage,muscular invasion,or lymph node metastasis.Univariate and multivariate logistic regression analysis showed that age≥ 66 years,higher tumor grade,and lymphovascular invasion were risk factors for positive HER2 expression,and high histological grade and lymphovascular invasion were independent risk factors affecting HER2 expression after controlling for confounders.Survival analysis showed no significant difference in recurrence-free survival between patients with HER2-positive and HER2-negative non-muscle-invasive urothelial carcinoma(P=0.274).Conclusion High histologic grade,tumor lymphovascular invasion,and neural invasion were associated with positive HER2 expression in patients with urothelial carcinoma,and higher histologic grade and lymphovascular invasion are important factors affect-ing HER2 expression.However,HER2-positive expression may not affect the prognosis of patients with non-muscle-invasive bladder urothelial carcinoma.

Objective:To investigate the prognostic value of deep learning-based automated quantification of tumor-stroma ratio (TSR) in patients undergoing neoadjuvant therapy (NAT) for breast cancer.Methods:Specimens were collected from 209 breast cancer patients who received NAT at Renmin Hospital of Wuhan University from October 2019 to June 2023. TSR levels in pre-NAT biopsy specimens were automatically computed using a deep learning algorithm and categorized into low stroma (TSR≤30%), intermediate stroma (TSR 30% to ≤60%), and high stroma (TSR>60%) groups. Residual cancer burden (RCB) grading of post-NAT surgical specimens was determined to compare the relationship between TSR expression levels and RCB grades. The correlation of TSR with NAT efficacy was analyzed, and the association between TSR expression and patient prognosis was further investigated.Results:There were 85 cases with low stroma (TSR≤30%), 93 cases with intermediate stroma (TSR 30% to ≤60%), and 31 cases with high stroma (TSR>60%). Different TSR expression levels showed significant differences between various RCB grades ( P<0.05). Logistic univariate and multivariate analyses showed that TSR was a risk factor for obtaining a complete pathological remission from neoadjuvant therapy for breast cancer when it was used as a continuous variable ( P<0.05); COX regression and survival analyses showed that the lower the percentage of tumorigenic mesenchyme was, the better the prognosis of the patient was ( P<0.05). Conclusions:The deep learning-based model enables automatic and accurate quantification of TSR. A lower pre-treatment tumoral stroma is associated with a lower RCB score and a higher rate of pathologic complete response, indicating that TSR can predict the efficacy of neoadjuvant therapy in breast cancer and thus holds prognostic significance. Therefore, TSR may serve as a biomarker for predicting therapeutic outcomes in breast cancer neoadjuvant therapy.

Objective:To aid in the detection of thyroid cancer by using deep learning to differentiate the unique bioimpedance parameter patterns of different thyroid tissues.Methods:An electrical impedance system was designed to measure 331 ex-vivo thyroid specimens from 321 patients during surgery. The impedance data was then analyzed with one dimensional convolution neural (1D-CNN) combining with long short-term memory (LSTM) network models of deep learning. In the process of analysis, we assigned 80% of the data to training set (1072/1340) and the remaining 20% data to the test set (268/1340). The performance of final model was assessed using receiver operating characteristic (ROC) curves. In addition, sensitivity, specificity, positive predictive value, negative predictive value, Youden index were applied to compare impedance model with ultrasound results.Results:The ROC curve of the two-classification (malignant /non-malignant tissue) model showed a good performance (area-under-the-curve AUC=0.94), with an overall accuracy of 91.4%. To better fit clinical practice, we further performed a three-classification (malignant/ benign/ normal tissue) model, of which the areas under ROC curve were 0.91, 0.85, 0.92 for normal, benign, and malignant group, respectively. The results indicated that the area under micro-average ROC curve and the macro-average ROC curve were 0.91 and 0.90, respectively. Moreover, compared with ultrasound, the impedance model exhibited higher specificity.Conclusions:A deep learning model (CNN-LSTM) trained by thyroid electrical impedance spectroscopy (EIS) parameters shows an excellent performance in distinguishing among different in-vitro thyroid tissues, which is promising for applications. In future clinical utility, our study does not replace existing tests, but rather complements others, thus contributing to therapeutic decision-making and management of thyroid disease.

Purpose To explore the artificial intelligence(AI)-assisted diagnosis system of thyroid cancer based on deep transfer learning and evaluate its clinical application value.Methods The HE sections of 682 cases thyroid disease patients(including benign lesions,papillary carcinoma,follicular carci-noma,medullary carcinoma and undifferentiated carcinoma)in the Pathology Department of the Renmin Hospital of Wuhan Uni-versity were collected,scanned into digital sections,divided into training sets and internal test sets according to the ratio of 8 ∶ 2,and the training sets were labeled at the pixel level by patholo-gists.The thyroid cancer classification model was established u-sing VGG image classification algorithm model.In the process of model training,the parameters of the breast cancer region recog-nition model were taken as the initial values,and the parameters of the thyroid cancer region recognition model were optimized through the transfer learning strategy.Then the test set and 633 intraoperative frozen HE section images of thyroid disease in Jianli County People's Hospital,Jingzhou City,Hubei Province wereused as the external test set to evaluate the performance of the established AI-assisted diagnostic model.Results In the internal test set,without the use of the breast cancer region rec-ognition model transfer learning,the accuracy of the AI-assisted diagnosis model was 0.882,and the area under the Receiver op-erating characteristic(AUC)valuewas0.938;However,inthe use of the Transfer learning model,the accuracy of the AI-assis-ted diagnosis model for was 0.926,and the AUC value was 0.956.In the external test set,the accuracy of the zero learning model was 0.872,the AUC value was 0.915,and the accuracy of the Transfer learning model was 0.905,the AUC value was 0.930.Conclusion The AI-assisted diagnosis method for thy-roid cancer established in this study has good accuracy and gen-eralization.With the continuous development of pathological AI research,transfer learning can help improve the performance and generalization ability of the model,and improve the accura-cy of the diagnostic model.

Objective:The residual cancer burden (RCB) evaluation system was used to analyze the influencing factors of the efficacy of neoadjuvant therapy in breast cancer, and to explore the prognostic value of RCB evaluation in neoadjuvant therapy.Methods:Clinicopathologic data and postoperative RCB grading of 364 breast cancer patients who underwent neoadjuvant therapy in Renmin Hospital of Wuhan University from Nov. 2019 to Nov. 2022 were collected. Chi-square test was used to analyze the relationship between RCB grading and clinicopathological parameters, and Spearman’s rank correlation analysis was performed to evaluate the correlation between RCB grading and clinicopathological characteristics. Factors influencing pathologic complete response (pCR) were analyzed by Logistic regression. Kaplan-Meier survival analysis and log-rank test were used to evaluate cumulative survival.Results:Among the 364 patients who underwent neoadjuvant therapy, 129 cases of RCB grade 0 and 235 cases of RCB gradeⅠ-Ⅲ (including 46 cases of RCB gradeⅠ, 109 cases of RCB grade Ⅱ and 80 cases of RCB grade Ⅲ) were obtained after surgery. Histological classification ( χ 2=21.757, P=0.000), estrogen receptor (ER) ( χ 2=52.837, P=0.000), progesterone receptor (PR) ( χ 2=55.658, P=0.000), human epidermal growth factor receptor-2 (HER2) ( χ2=89.040, P=0.000), Ki67 expression ( χ2=12.927, P=0.005), molecular typing ( χ 2=80.793, P=0.000) and preoperative lymph node status ( χ 2=25.764, P=0.000) were all associated with postoperative RCB grading. Further correlation analysis showed that histological grade ( r=-0.229, P=0.000), HER2 expression ( r=-0.465, P=0.000) and Ki67 expression ( r=-0.179, P=0.000) were negatively correlated with RCB grading, while ER ( r=0.352, P=0.000), PR ( r=0.379, P=0.000) and lymph node metastasis ( r=0.214, P=0.000) were positively correlated with RCB grading. Logistic regression analysis showed that high histological grade, negative expression of ER, PR and AR, positive expression of HER2, high proliferation index of Ki67 and no lymph node metastasis were favorable factors for postoperative pCR, and PR, AR and HER2 were independent predictors of postoperative pCR. Kaplan-Meier survival analysis showed significant differences in postoperative cumulative survival among patients with different RCB grades ( P=0.004) . Conclusions:Postoperative RCB grading of breast cancer is closely related to many clinicopathological features before neoadjuvant therapy and survival prognosis. Clinicopathological factors closely related to RCB grading are also important influencing factors affecting the pCR of patients with neoadjuvant therapy. Therefors, RCB grading has a high prognostic value.