The discerning influence of dynamic contrast-enhanced MRI in anticipating molecular subtypes of breast cancer through the artistry of artificial intelligence – a narrative review

Abstract

Radio genomics is an exciting new area that uses diagnostic imaging to discover genetic features of diseases. In this review, we carefully examined existing literature to evaluate the role of artificial intelligence (AI) and machine learning (ML) on dynamic contrastenhanced MRI (DCE-MRI) data to distinguish molecular subtypes of breast cancer (BC). Implications to noninvasive assessment of molecular subtype include reduction in procedure risks, tailored treatment approaches, ability to examine entire lesion, follow-up of tumour biology in response to treatment and evaluation of treatment resistance and failure secondary to tumour heterogeneity. Recent studies leverage radiomics and AI on DCE-MRI data for reliable, non-invasive breast cancer subtype classification. This review recognizes the potential of AI to predict the molecular subtypes of breast cancer non-invasively. Keywords: Artificial Intelligence, Radiomics, Magnetic Resonance Imaging, Machine Learning, Genomics, Neoplasms, Molecular Subtypes, Breast Cancer