The Promise of Using A.I. Technology to Detect Breast Cancer
Photo credit: CNN
The American Cancer Society (2018) states that while breast cancer is more common in White women, the mortality rate for Black women is higher. The differences may be attributed to poor access to healthcare, screenings, and education. Satarian and Metz (March 6, 2023) report that advancements in artificial intelligence (A.I.) are beginning to deliver breakthroughs in breast cancer screening by detecting the signs that cancer specialists could miss. So far, the technology is showing an impressive ability to spot cancer at least as well as human radiologists, according to early results and radiologists, in what is one of the most promising signs of how A.I. can improve public health.
The country of Hungary, which has one of the most robust breast cancer screening programs, has become one of the most significant testing grounds for the technology on actual patients. In Hungary, at least five hospitals and clinics, according to Satarian and Metz, perform more than 35,000 screenings a year. Their A.I. systems became part of their screening program a few years ago to help to check for signs of cancer that a radiologist may have overlooked. Clinics and hospitals in the United States are also beginning to test or provide data to help develop the systems.
Although the added A.I. screen is potential, additional clinical trials are needed before the systems can be automated as a second reader of breast cancer screens. Ultimately, an A.I. tools must consistently produce accurate results on women of all ages, ethnicities, and body types. And the technology must prove it can cut down on false positives that are not cancerous. Harlow (March 8, 2023) featured a segment where she met with Dr. Larry Norton, the medical director at the Memorial Sloan Kettering Cancer Center, regarding the benefits of using artificial intelligence in breast cancer detection.
Dr. Norton discussed the application of A.I. technology to look at mammograms and identify areas a human radiologist may want to look at more carefully. But, first, Dr. Norton discussed that computer-assisted detection is familiar and has been around for about three decades. Fortunately, technology is continually improving. For example, MIT used artificial intelligence to predict breast cancer; on the left side of your screen, you see an area in a woman’s breast identified as high risk; four years later, cancer developed right, and the point is a doctor’s human eyes might miss lots of abnormalities you can’t call everything cancer cause.
MIT and the Massachusetts General Hospital are collaborating with Memorial Sloan Kettering. Machines can look at previous mammograms and see if there are any changes, and so and so other than a human eye can compare to images. Individual judgments about individual people tests such as contrast-enhanced mammograms, MRI’s, and other tests people sometimes should go for testing to see if they’re carrying an abnormal gene to know if they’re at high risk. The more individualized approach using A.I. may be a plus for screening for women and especially Black women in the future.
References:
American Cancer Society. (2018).https://www.cancer.org/content...
Harlow, P. (March 7, 2023). Images show AI detecting breast cancer 4 years before it developed.https://www.cnn.com/videos/hea...
Satarian, A. and Metz, C. (March 6, 2023). Using A.I. to Detect Breast Cancer That Doctors Miss. https://www.nytimes.com/2023/0...