UCLA researchers have developed an artificial intelligence system that could help pathologists read biopsies more accurately and better detect and diagnose breast cancer. The new system, described in a study published in JAMA Network Open, helps interpret medical images used to diagnose breast cancer that can be difficult for the human eye to classify. It does so nearly as accurately or better as experienced pathologists. 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.
Medical images of breast biopsies contain a great deal of complex data. A 2015 study led by Elmore found that pathologists often disagree on the interpretation of breast biopsies, which are performed on millions of women each year. That earlier research revealed that diagnostic errors occurred in about one out of every six women who had ductal carcinoma in situ (a noninvasive type of breast cancer) and that incorrect diagnoses were given in about half of the biopsy cases of breast atypia (abnormal cells that are associated with a higher risk for breast cancer).
“Distinguishing breast atypia from ductal carcinoma in situ is important clinically but very challenging for pathologists. Interpreting them can be very subjective,” said Elmore, who is also a researcher at the UCLA Jonsson Comprehensive Cancer Center. Sometimes, doctors do not even agree with their previous diagnosis when shown the same case a year later. The scientists reasoned that artificial intelligence could provide more accurate readings consistently because by drawing from a large data set, the system can recognize patterns in the samples associated with cancer but are difficult for humans to see.
The team fed 240 breast biopsy images into a computer, training it to recognize patterns associated with several types of breast lesions, ranging from benign (noncancerous) and atypia to ductal carcinoma in situ, or DCIS, and invasive breast cancer. Separately, the correct diagnoses for each image were determined by a consensus among three expert pathologists. The researchers compared its readings to independent diagnoses made by 87 practicing U.S. pathologists to test the system. While the artificial intelligence program came close to performing and human doctors in differentiating cancer from non-cancer cases, the AI program outperformed doctors when differentiating DCIS from atypia — considered the greatest challenge in breast cancer diagnosis.
The system correctly determined whether scans showed DCIS or atypia more often than the doctors; it had sensitivity between 0.88 and 0.89, while the pathologists’ average sensitivity was 0.70. (A higher sensitivity score indicates a greater likelihood that a diagnosis and classification is correct.) 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 researchers are now working on training the system to diagnose melanoma.
Ezgi Mercan of Seattle’s Children Hospital is the study’s first author. Other authors are Sachin Mehta and Linda Shapiro of the University of Washington, Jamen Bartlett of Southern Ohio Pathology Consultants, and Donald Weaver of Vermont. The study was supported by the National Cancer Institute of the National Institutes of Health. Early detection and early treatment are the best ways to fight any cancer — and that can be especially true of breast cancer. There are many tools for breast cancer diagnosis, and the American Cancer Society recommends examinations should be tailored to the individual: An annual mammogram for normal-risk women over 40 or an annual mammogram and MRI for high-risk women starting at age 30.
But what’s been a subject of debate is whether it harms or good for women to do their own breast self-examinations. Both the ACS and the American College of Obstetricians and Gynecologists have backed away from breast self-exams as a recommendation to diagnose breast cancer — because the average person may not know the difference between true breast cancer symptoms and other physical changes, which may not be cancer-related.
“It hasn’t been shown to save lives, so it has fallen out of favor in recommending it as a screening tool.
Dr. Deborah Axelrod, a surgeon, specializing in breast disease and cancer at NYU Langone Health’s Perlmutter Cancer Center, told TODAY. According to a statement provided to TODAY by Kate Connors, the American College of Obstetricians and Gynecologists does not recommend breast self-exams, the organization’s Interim Director of Media Relations and Communications.
Breast self-examination is not recommended in average-risk women because there is a risk of harm from false-positive test results and a lack of evidence of benefit,” said the statement. “In its 2009 breast cancer screening guidelines, the U.S. Preventive Services Task Force recommended against teaching breast self-examination (grade D recommendation) based on the lack of evidence regarding benefits and because of potential harms from false-positive findings. But, there is a powerful reason that breast self-exams are still worth the time, according to Axelrod: Women need to stay aware of their own breast areas so that any concerning changes can be brought to a medical professional. First of all, it doesn’t cost anything, and it’s convenient to do,” Axelrod said.
But, I think it’s helpful that every woman should really familiarize herself with what her breasts look like and what they feel like.” Young women should be particularly aware of their breasts, she added, since they are not typically recommended to have breast cancer screenings as often as older women — and that awareness can save lives. We’re not really screening them in any effective way unless they have a specific risk,” Axelrod said. According to the statement from ACOG, approximately 71 percent of the cases of breast cancer in women younger than 50 years of age are detected by women themselves.