Go beyond image-based benign-malignant classification: AI can identify responsible frames better than physicians in breast ultrasound screening video

Abstract

Breast Cancer is the most common cancer in the world and the single leading cause of cancer mortality in women. Heavy workload and shortage of ultrasound specialists impede the penetration of breast cancer screening. To reduce the burden of sonographers and empower junior physicians, we propose a novel framework FEBrNet by integrating deep learning architecture with the idea of entropy from Information theory. FEBrNet is capable of auto-selecting responsible frames from ultrasound screening videos based on entropy reduce method and classifying breast nodules using Artificial Intelligence (AI). A combination of 13702 images and 1066 videos from breast ultrasound exams are used to train and test the robustness of the proposed framework. Reader studies show that FEBrNet has equivalent or even superior diagnostic performance to that of ultrasound specialists and that overall physician’s performance improves when using FEBrNet's recommended frames and corresponding prediction. Therefore, merging FEBrNet into clinical ultrasound screening workflow might bring actual benefit by helping address the scarcity of sonographers, so as to increase the use of ultrasound screening in cancer prevention.