Problem

High breast density is, in itself, a risk factor for cancer. It can also make the recognition of lesions more difficult and reduce the sensitivity of the mammography. In current clinical practice, breast density is mostly assessed visually with reference to the A, B, C, D classification of the American College of Radiology: from class A for almost entirely fatty breasts to class D for extremely dense breasts. However, visual evaluation is subject to observer variability and differences in evaluations between multiple subjects.

Solution

Artificial intelligence (AI) software capable of consistently and accurately classifying breast density during mammography: the software is based on deep learning algorithms, capable of learning to automatically carry out tasks typically entrusted to visual perception of expert humans.