A study that trained an AI algorithm with over 5 million B-mode and Color Doppler ultrasound images helped radiologists decrease the need for follow-up biopsies by over 25% and reduced false-positive diagnoses by over 35%. The study, performed by researchers at New York University, was published online on September 24, 2021.

“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,” wrote the team.

“‘Our study demonstrates how artificial intelligence can help radiologists reading breast ultrasound exams to reveal only those that show real signs of breast cancer and to avoid verification by biopsy in cases that turn out to be benign,’ said senior investigator Krzysztof Geras, Ph.D., of NYU Grossman School of Medicine, in a statement,'” according to Ridley.

“‘If our efforts to use machine learning as a triaging tool for ultrasound studies prove successful, ultrasound could become a more effective tool in breast cancer screening, especially as an alternative to mammography, and for those with dense breast tissue,” added study co-investigator, Dr. Linda Moy, in the statement,” according to Ridley.

Sources:

Shen, Y., Shamout, F.E., Oliver, J.R. et al. Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams. Nat Commun 12, 5645 (2021). Published online September 24, 2021, at https://www.nature.com/articles/s41467-021-26023-2. Accessed October 11, 2021.

Ridley, Erik. AI of breast ultrasound helps radiologists focus on cancer. AuntMinnie.com September 24, 2021. Accessed October 11, 2021, at https://www.auntminnie.com/index.aspx?sec=sup&sub=ult&pag=dis&ItemID=133582.