Breast Density Analysis on Mammograms: Application of Machine Learning with Textural Features

Abstract

Breast cancer (BC) is the world’s most prevalent cancer in female population, with 2.3 million new cases diagnosed worldwide in 2020. The great efforts made to set screening campaigns, early detection programs, and increasingly targeted treatments led to a significant improvement in patients’ survival. Full-Field Digital Mammograph (FFDM) is considered the gold standard method for the early diagnosis of BC. From several previous studies it has emerged that breast density (BD) is a risk factor in the development of BC, affecting the periodicity of screening plans present today at an international level. In this study, the focus is the development of mammographic image processing techniques that allows the extraction of indicators derived from textural patterns of the mammary parenchyma indicative of BD risk factor. Different Machine Learning (ML) techniques have been employed to classify breasts based on the values of the tissue density. Textural features were extracted only from breast parenchyma with which to train classifiers thanks to aid of ML algorithms. The preliminary results are in line with those obtained in the literature, reaching an accuracy of 93.55% for a binary classification between dense and no-dense tissues.