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

Shen, Yiqiu; Shamout, Farah E.; Oliver, Jamie R.; Witowski, Jan; Kannan, Kawshik; Park, Jungkyu; Wu, Nan; Huddleston, Connor; Wolfson, Stacey; Millet, Alexandra; Ehrenpreis, Robin; Awal, Divya; Tyma, Cathy; Samreen, Naziya; Gao, Yiming; Chhor, Chloe; Gandhi, Stacey; Lee, Cindy; Kumari-Subaiya, Sheila; Leonard, Cindy; Mohammed, Reyhan; Moczulski, Christopher; Altabet, Jaime; Babb, James; Lewin, Alana; Reig, Beatriu; Moy, Linda; Heacock, Laura; Geras, Krzysztof J.

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.