XYXin-Hua Ye

Xin-Hua Ye

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xin-Hua Ye has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Preoperative Contrast‐Enhanced Ultrasound Predicts Microvascular Invasion in Hepatocellular Carcinoma as Accurately as Contrast‐Enhanced MR

    by Cuiwei Wang, Teng Zhang, Shuwen Sun, Xinhua Ye, Yali Wang, Minhong Pan, Haibin Shi

    Objectives: Both contrast‐enhanced ultrasound (CEUS) and contrast‐enhanced magnetic resonance (CEMR) are important imaging methods for hepatocellular carcinoma (HCC). This study aimed to establish a model using preoperative CEUS parameters to predict microvascular invasion (MVI) in HCC, and compare its predictive efficiency with that of CEMR model.Methods: A total of 93 patients with HCC (39 cases in MVI positive group and 54 cases in MVI negative group) who underwent surgery in our hospital from January 2020 to June 2021 were retrospectively analyzed. Their clinical and imaging data were collected to establish CEUS and CEMR models for predicting MVI. The predictive efficiencies of both models were compared.Results: By the univariate and multivariate regression analyses of patients' clinical information, preoperative CEUS static and dynamic images, we found that serrated edge and time to peak were independent predictors of MVI. The CEUS prediction model achieved a sensitivity of 92.3%, a specificity of 83.3%, and an accuracy of 84.6% (Az: 0.934). By analyzing the clinical and CEMR information, we found that tumor morphology, fast‐in and fast‐out, peritumoral enhancement, and capsule were independent predictors of MVI. The CEMR prediction model achieved a sensitivity of 97.4%, a specificity of 77.8%, and an accuracy of 83.2% (Az: 0.900). The combination of the two models achieved a sensitivity of 84.6%, a specificity of 87.0%, and an accuracy of 86.2% (Az: 0.884). There was no significant statistical difference in the areas under the ROC curve of the three models.Conclusion: The CEUS model and the CEMR model have similar predictive efficiencies for MVI of HCC. CEUS is also an effective method to predict MVI before operation.


  • Pretreatment ultrasound-based deep learning radiomics model for the early prediction of pathologic response to neoadjuvant chemotherapy in breast cancer

    by Fei-Hong Yu, Shu-Mei Miao, Cui-Ying Li, Jing Hang, Jing Deng, Xin-Hua Ye, Yun Liu

    Objectives To investigate the predictive performance of the deep learning radiomics (DLR) model integrating pretreatment ultrasound imaging features and clinical characteristics for evaluating therapeutic response after neoadjuvant chemotherapy (NAC) in patients with breast cancer. Methods A total of 603 patients who underwent NAC were retrospectively included between January 2018 and June 2021 from three different institutions. Four different deep convolutional neural networks (DCNNs) were trained by pretreatment ultrasound images using annotated training dataset (n = 420) and validated in a testing cohort (n = 183). Comparing the predictive performance of these models, the best one was selected for image-only model structure. Furthermore, the integrated DLR model was constructed based on the image-only model combined with independent clinical-pathologic variables. Areas under the curve (AUCs) of these models and two radiologists were compared by using the DeLong method. Results As the optimal basic model, Resnet50 achieved an AUC and accuracy of 0.879 and 82.5% in the validation set. The integrated DLR model, yielding the highest classification performance in predicting response to NAC (AUC 0.962 and 0.939 in the training and validation cohort), outperformed the image-only model and the clinical model and also performed better than two radiologists’ prediction (all p < 0.05). In addition, predictive efficacy of the radiologists was improved under the assistance of the DLR model significantly. Conclusion The pretreatment US-based DLR model could hold promise as a clinical guidance for predicting NAC response of patients with breast cancer, thereby providing benefit of timely treatment strategy adjustment to potential poor NAC responders. Key Points • Multicenter retrospective study showed that deep learning radiomics (DLR) model based on pretreatment ultrasound image and clinical parameter achieved satisfactory prediction of tumor response to neoadjuvant chemotherapy (NAC) in breast cancer. • The integrated DLR model could become an effective tool to guide clinicians in identifying potential poor pathological responders before chemotherapy. • The predictive efficacy of the radiologists was improved under the assistance of the DLR model.


  • Open Access

    BRAFV600E vs. TIRADS in predicting papillary thyroid cancers in Bethesda system I, III, and V nodules

    by Wu Ya, Xu Ting, Cao Xingyue, Zhao Xin, Deng Hongyan, Wang Jianxiang, Li Xiao, Yao Qing, Ye Xinhua, Shen Meiping, et al.

    BRAFV600E vs. TIRADS in predicting papillary thyroid cancers in Bethesda system I, III, and V nodules