Artificial Intelligence to predict breast cancer, how it works

Delayed diagnosis makes breast cancer a deadly desease. To help doctors identify at-risk patients early, researchers are taking the help of artificial intelligence.

MIT researchers have built a new deep learning model that can predict from a mammogram if a patient is likely to develop breast cancer in the future. As their official release explains, the system has been trained on mammograms and known outcomes from over 60,000 patients to learn the subtle patterns in breast tissue.

The AI was able to accurately access 31 per cent of all cancer patients in its highest-risk compared to 18 per cent by traditional models. Systems like these could help doctors in early diagnosis, much before the disease actually develops. 

(With inputs from agencies.)