Research Finds That Automated Systems May Be as Good as Clinicians in Assessing Breast Cancer Risk

Women who have had screening mammography are informed of their breast density on the basis of Breast Imaging Reporting and Data System density categories estimated subjectively by radiologists. Variation in these clinical categories across and within radiologists has led to discussion about whether automated analysis would provide more accurate results. Research conducted by scholars at the University of California, San Francisco and the Mayo Clinic found that automated systems were just as accurate in predicting women’s risk of breast cancer as subjective evaluations by professional radiologists.

Karla Kerlikowske, professor of medicine at the University of California, San Francisco and lead author of the study, stated that “there have been concerns raised about the reliability of breast density measures, since an assessment might vary for an individual woman depending on the radiologist and the mammogram. Automated assessments, which are done by computer algorithm, are more reproducible and less subjective. Therefore, they could reduce variation and alleviate the sense of subjectivity and inconsistency.”

Dr. Kerlikowske is a graduate of Michigan State University, where she majored in medical technology. She holds a master’s degree in nutrition from the University of California, Berkeley, and a medical doctorate from the University of California, San Francisco.

The study, “Automated and Clinical Breast Imaging Reporting and Data System Density Measures Predict Risk of Screen-Detected and Interval Cancers,” was published on the website of the Annals of Internal Medicine. It may be accessed here.