Breast cancer is the most commonly diagnosed cancer among women and the second leading cause of cancer death among women. Proper screening and early detection allow physicians to diagnose breast cancer sooner, leading to faster treatment, better outcomes, and reduced breast cancer mortality.
Now, MIT has introduced a new artificial intelligence (AI) tool that can predict from a mammogram if a patient is likely to develop breast cancer as far as five years into the future. Working in partnership with Massachusetts General Hospital, their team of researchers utilized “deep learning,” a machine learning technique that teaches computers to learn by example, to train their tool to recognize patterns from 90,000 mammograms with known patient outcomes.
The model learned the subtle patterns in a cancer mammogram that were precursors to malignant tumors, including patterns too subtle for the human eye to detect. The model was able to predict cancer significantly better than existing approaches. After assessing the mammograms, it placed 31 percent of all cancer patients in its highest risk category, whereas other models placed just 18 percent.
Until now, screening strategies relied on human knowledge of major risk factors – such as age, family history of breast and ovarian cancer, and breast density – in estimating individual risk. With this tool, the team hopes physicians will be able to customize screening and prevention programs.
“Since the 1960s radiologists have noticed that women have unique and widely variable patterns of breast tissue visible on the mammogram,” says Lehman. “These patterns can represent the influence of genetics, hormones, pregnancy, lactation, diet, weight loss, and weight gain. We can now leverage this detailed information to be more precise in our risk assessment at the individual level.”