We are searching data for your request:
Upon completion, a link will appear to access the found materials.
Although pathologists generally do a good job of spotting breast cancer there is no doubt that assistance is always useful. As such, UCLA scientists have developed a novel artificial intelligence system that aids in the reading of biopsies.
RELATED: AI DETECTS BREAST CANCER BETTER THAN AVERAGE RADIOLOGIST
"It is critical to get a correct diagnosis from the beginning so that we can guide patients to the most effective treatments," said Dr. Joann Elmore, the study's senior author and a professor of medicine at the David Geffen School of Medicine at UCLA.
Why would there be a need for such a study? Well, because, according to a 2015 study led by Elmore, pathologists often disagree on the result of breast biopsies. Furthermore, research has also found that errors occurred in about one out of every six women who were diagnosed with ductal carcinoma in situ (DCIS) and incorrect diagnoses were given in about half of the biopsy cases of breast atypia.
These are quite some significant errors. The reason for these misinterpretations is because breast biopsies are notoriously difficult to read accurately.
"Medical images of breast biopsies contain a great deal of complex data and interpreting them can be very subjective," said Elmore, who is also a researcher at the UCLA Jonsson Comprehensive Cancer Center. "Distinguishing breast atypia from ductal carcinoma in situ is important clinically but very challenging for pathologists. Sometimes, doctors do not even agree with their previous diagnosis when they are shown the same case a year later."
In order to find a more consistent method of diagnosing readings, the researchers stipulated that an AI could help by drawing from a large data set. As such, they fed 240 breast biopsy images into a computer system and trained it to recognize patterns associated with a variety of breast lesions.
They then compared its results to independent diagnoses made by 87 practicing U.S. pathologists. Impressively, the program performed almost as well as the doctors in differentiating cancer from non-cancer cases.
Differentiating DCIS from atypia
However, it outshined human doctors in one particular tricky area; differentiating DCIS from atypia. This area is considered the greatest challenge in breast cancer diagnosis. The system displayed a sensitivity between 0.88 and 0.89, while the pathologists' average sensitivity was a mere 0.70.
"These results are very encouraging," Elmore said. "There is low accuracy among practicing pathologists in the U.S. when it comes to the diagnosis of atypia and ductal carcinoma in situ, and the computer-based automated approach shows great promise."
The study is published in JAMA Network Open.