Despite major advances in genetics and modern imaging, most patients are caught off guard by a breast cancer diagnosis. For some, it comes too late. Late diagnosis means aggressive treatments, uncertain outcomes and higher medical costs, so patient screening has been a central pillar of research into the disease, which is expected to have 300,590 new cases in 2023 and claim the lives of 43,700 people.
With that in mind, a team from the Computer Science and Artificial Intelligence Laboratory "CSAIL" at the Massachusetts Institute of Technology MIT and Massachusetts General Hospital MGH have created a new deep learning model where Artificial Intelligence helps predict, from a mammogram, whether a patient is likely to develop breast cancer up to five years in the future.
Trained on mammograms and known results from more than 60,000 MGH patients, the model learned the subtle patterns in breast tissue that are precursors to malignant tumors.
MIT professor Regina Barzilay, a breast cancer survivor herself, says the hope is that systems like these will allow doctors to customize screening and prevention programs at the individual level, making late diagnosis a relic of the past.
Although mammography has been shown to reduce breast cancer mortality, there is ongoing debate about how often screening should be performed and when to begin.
While the American Cancer Society recommends annual screening beginning at age 45, the U.S. Cancer Prevention Task Force recommends screening every other year beginning at age 50.