Trained Radiologists Can Detect Breast Cancer in An Instant

They further tested this ability through a series of four experiments to explore what signal may alert radiologists to the presence of a possible abnormality, in the hopes of using these insights to improve breast cancer screening and early detection.

They found that radiologist performance did not depend on detection of breaks in the normal symmetry of left and right breasts. Moreover, above-chance classification is possible using images from the normal breast of a patient, even when overt signs of cancer are present only in the other breast. They speculate that parts of the parenchyma that do not contain a lesion, or that are in the contralateral breast, confer an abnormal ‘gist’ that may be based on a widely distributed image statistic that is learned by experts. The study was published on August 29, 2016, in Proceedings of the National Academy of Sciences (PNAS).

“Radiologists can have ‘hunches’ after a first look at a mammogram. We found that these hunches are based on something real in the images. It's really striking that in the blink of an eye, an expert can pick up on something about that mammogram that indicates abnormality,” said senior author Jeremy Wolfe, PhD, director of the Visual Attention Laboratory at BWH. “Not only that, but they can detect something abnormal in the other breast, the breast that does not contain a lesion. Radiologists may be picking up on some sort of early, global signal of abnormality that is unknown to us at this point.”

According to the researchers, defining the signal that experienced radiologists are detecting could help researchers refine and improve computer-aided detection (CAD) systems that can aid in medical screening and could be incorporated into clinician training to improve detection rates. The researchers are also interested in exploring whether other medical image experts, such as dermatologists and pathologists, can use analogous signals.

Related Links:
Brigham and Women's Hospital
University of York