Will AI be able to transform the mammogram and "allow patients to avoid aggressive treatments and even save the lives of countless people who get breast cancer"?
Professor Regina Barzilay |
The Post article reports that Barzilay and Adam Yala, a student protege, "have built an AI that seems able to predict with unprecedented accuracy whether a healthy person will get breast cancer, in an innovation that could seriously disrupt how we think about the disease."
How it works was laid out in an piece in the Journal of Clinical Oncology: "By analyzing a mammogram's set of byzantine pixels and then cross-referencing them with thousands of older mammograms, the AI — known as Mirai — can product nearly half of all incidences of breast cancer up to five years before they happen."
"If the data is validated, I think this is very exciting," Zeitchik's story quotes Janine T. Katzen, radiologist at Weill Cornell Medicine who specializes in breast imaging. It also quotes Dorraya El-Ashry, chief scientific officer for the Breast Cancer Research Foundation, as saying, "This is the next, very positive step forward. There is a lot of work to do. But this is very encouraging."
Meanwhile, breast cancer statistics are discouraging. "While many cancers, such as lung cancer, have been declining in the United States," the Post story says, "breast cancer rates have been going up — an annual average of half a percentage point between 2008 and 2017, according to the American Cancer Society."
More information on out-of-the-ordinary treatments can be found in "Rollercoaster: How a man can survive his partner's breast cancer," a VitalityPress book that I, Woody Weingarten, aimed at caregivers.