APPLICATION OF DEEP LEARNING TO REDUCE THE RATE OF MALIGNANCY AMONG BI-RADS 4A BREAST LESIONS BASED ON ULTRASONOGRAPHY

摘要

aim of the work described here was to develop an ultrasound (US) image -based deep learning model to reduce the rate of malignancy among breast lesions diagnosed as category 4A of the Breast Imaging-Reporting and Data System (BI-RADS) during the pre-operative US examination. A total of 479 breast lesions diagnosed as BI-RADS 4A in pre-operative US examination were enrolled. There were 362 benign lesions and 117 malignant lesions confirmed by postoperative pathology with a malignancy rate of 24.4%. US images were collected from the database server. They were then randomly divided into training and testing cohorts at a ratio of 4:1. To correctly classify malig-nant and benign tumors diagnosed as BI-RADS 4A in US, four deep learning models, including MobileNet, Dense-Net121, Xception and Inception V3, were developed. The performance of deep learning models was compared using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predic-tive value (PPV) and negative predictive value (NPV). Meanwhile, the robustness of the models was evaluated by five-fold cross-validation. Among the four models, the MobileNet model turned to be the optimal model with the best per-formance in classifying benign and malignant lesions among BI-RADS 4A breast lesions. The AUROC, accuracy, sensi-tivity, specificity, PPV and NPV of the optimal model in the testing cohort were 0.897, 0.913, 0.926, 0.899, 0.958 and 0.784, respectively. About 14.4% of patients were expected to be upgraded to BI-RADS 4B in US with the assistance of the MobileNet model. The deep learning model MobileNet can help to reduce the rate of malignancy among BI-RADS 4A breast lesions in pre-operative US examinations, which is valuable to clinicians in tailoring treatment for suspicious breast lesions identified on US. (E-mail addresses: jgchen@cee.ecnu.edu.cn jiaweili2006@163.

关键词