A Software Pipeline for Multimodal and Network-Based Analysis of Breast Cancer Data

Early diagnosis of Breast cancer is essential to improve treatment success rates and optimize clinical outcomes. Contrast-Enhanced Mammography (CEM) has recently emerged as an advanced and promising technology for the early detection of breast cancer that has many benefits with respect to Magnetic Resonance Imaging (MRI) diagnosis and the gold standard diagnosis based on traditional histological examination. This paper presents the design of an innovative software pipeline for analyzing images obtained through Contrast-Enhanced Mammography (CEM) using advanced deep learning techniques. The goal is to predict the histological characteristics of breast cancer, such as subtype, grade, and phenotype, directly from CEM images. This innovation is designed to reduce the diagnostic time compared to traditional histological examination, thereby improving the timeliness of treatment and patient out-comes.