To identify novel breast cancer subtypes by extracting quantitative imaging phenotypes of the tumor and surrounding parenchyma, and to elucidate the underlying biological underpinnings and evaluate the prognostic capacity for predicting recurrence-free survival (RFS).We retrospectively analyzed dynamic contrast-enhanced magnetic resonance imaging data of patients from a single-center discovery cohort (n=60) and an independent multi-center validation cohort (n=96). Quantitative image features were extracted to characterize tumor morphology, intra-tumor heterogeneity of contrast agent wash-in/wash-out patterns, and tumor-surrounding parenchyma enhancement. Based on these image features, we used unsupervised consensus clustering to identify robust imaging subtypes, and evaluated their clinical and biological relevance. We built a gene expression-based classifier of imaging subtypes and tested their prognostic significance in five additional cohorts with publically available gene expression data but without imaging data (n=1160).Three distinct imaging subtypes, i.e., homogeneous intratumoral enhancing, minimal parenchymal enhancing, and prominent parenchymal enhancing, were identified and validated. In the discovery cohort, imaging subtypes stratified patients with significantly different 5-year RFS rates of 79.6%, 65.2%, 52.5% (logrank P=0.025), and remained as an independent predictor after adjusting for clinicopathological factors (hazard ratio=2.79, P=0.016). The prognostic value of imaging subtypes was further validated in five independent gene expression cohorts, with average 5-year RFS rates of 88.1%, 74.0%, 59.5% (logrank P from <0.0001 to 0.008). Each imaging subtype was associated with specific dysregulated molecular pathways that can be therapeutically targeted.Imaging subtypes provide complimentary value to established histopathological or molecular subtypes, and may help stratify breast cancer patients.
View details for DOI 10.1158/1078-0432.CCR-16-2415
View details for PubMedID 28073839