A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features

TLDR

MRI‑based imaging phenotypes of breast tumours have been preliminarily linked to molecular and genomic characteristics of breast cancer. This study provides a comprehensive analysis of the relationship between breast tumour MRI phenotypes and molecular/genomic characteristics. Using 922 invasive breast cancer patients, 529 MRI‑derived features were extracted and fed into machine‑learning models trained on half the cohort to predict molecular subtype, hormone receptor status, HER2, and Ki‑67, then evaluated on the remaining patients. The models achieved AUCs of 0.697 for Luminal A, 0.654 for triple‑negative, 0.649 for ER, and 0.622 for PR, demonstrating moderate predictive ability of MRI features for breast cancer molecular characteristics.

Abstract

Recent studies showed preliminary data on associations of MRI-based imaging phenotypes of breast tumours with breast cancer molecular, genomic, and related characteristics. In this study, we present a comprehensive analysis of this relationship. We analysed a set of 922 patients with invasive breast cancer and pre-operative MRI. The MRIs were analysed by a computer algorithm to extract 529 features of the tumour and the surrounding tissue. Machine-learning-based models based on the imaging features were trained using a portion of the data (461 patients) to predict the following molecular, genomic, and proliferation characteristics: tumour surrogate molecular subtype, oestrogen receptor, progesterone receptor and human epidermal growth factor status, as well as a tumour proliferation marker (Ki-67). Trained models were evaluated on the set of the remaining 461 patients. Multivariate models were predictive of Luminal A subtype with AUC = 0.697 (95% CI: 0.647–0.746, p < .0001), triple negative breast cancer with AUC = 0.654 (95% CI: 0.589–0.727, p < .0001), ER status with AUC = 0.649 (95% CI: 0.591–0.705, p < .001), and PR status with AUC = 0.622 (95% CI: 0.569–0.674, p < .0001). Associations between individual features and subtypes we also found. There is a moderate association between tumour molecular biomarkers and algorithmically assessed imaging features.