Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams

TLDR

Breast ultrasound reliably detects mammographically occult cancers but suffers from high false‑positive rates. This study presents an AI system designed to match radiologist accuracy in detecting breast cancer on ultrasound. The AI system is trained to achieve radiologist‑level accuracy in breast‑cancer detection on ultrasound images. On a test set of 44,755 exams, the AI achieved an AUROC of 0.976, outperforming ten radiologists (0.962 vs 0.924) and reducing radiologist false positives by 37.3 % and biopsy requests by 27.8 % while preserving sensitivity.

Abstract

Abstract Though consistently shown to detect mammographically occult cancers, breast ultrasound has been noted to have high false-positive rates. In this work, we present an AI system that achieves radiologist-level accuracy in identifying breast cancer in ultrasound images. Developed on 288,767 exams, consisting of 5,442,907 B-mode and Color Doppler images, the AI achieves an area under the receiver operating characteristic curve (AUROC) of 0.976 on a test set consisting of 44,755 exams. In a retrospective reader study, the AI achieves a higher AUROC than the average of ten board-certified breast radiologists (AUROC: 0.962 AI, 0.924 ± 0.02 radiologists). With the help of the AI, radiologists decrease their false positive rates by 37.3% and reduce requested biopsies by 27.8%, while maintaining the same level of sensitivity. This highlights the potential of AI in improving the accuracy, consistency, and efficiency of breast ultrasound diagnosis.