Artificial Intelligence Tool Improves Accuracy of Breast Cancer Imaging
Retrieved on:
Friday, September 24, 2021
Linda, NYU Langone Health, Ultrasound, Breast, NYU, Alvin J. Siteman Cancer Center, Radiation, Artificial intelligence, Student, Radiology, Polish National Agency for Academic Exchange, University of Texas Health Science Center Department of Radiology, National, PPN, Cancer, Mammography, Patient, Physician, New York University Grossman School of Medicine, MD, National Institutes of Health, AI, Biopsy, Nature Communications, Woman, National Science Foundation, Reading, Disease, Risk, Technology, Intelligence, Tissue, Machine learning, Doctor of Philosophy, Anxiety, American Cancer Society, Breast cancer, Department, Medical imaging, Pharmaceutical industry
"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," says study senior investigator Krzysztof Geras, PhD.
Key Points:
- "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," says study senior investigator Krzysztof Geras, PhD.
- Some studies have shown that a majority of breast ultrasound exams indicating signs of cancer turn out to be noncancerous after biopsy.
- Ten radiologists then each reviewed a separate set of 663 breast exams, with an average accuracy of 92 percent.
- When aided by the AI model, their average accuracy in diagnosing breast cancer improved to 96 percent.