Unsupervised Analysis Based on DCE-MRI Radiomics Features Revealed Three Novel Breast Cancer Subtypes with Distinct Clinical Outcomes and Biological Characteristics

SIMPLE SUMMARY: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is an important approach for the diagnosis and evaluation of breast cancer (BC) in clinical practice. Recently, DCE-MRI-based radiomics studies have received widespread attention and application in BC research, such as in non-invasively predicting subtypes and recurrence risks. Therefore, we collected two radiogenomics cohorts of BC and identified and validated three novel imaging subtypes by unsupervised analysis in this work. In several external datasets, we found that breast tumors with larger sizes and showing rapid enhancement patterns generally had the worst prognostic outcomes. The bioinformatics analysis revealed significant differences in gene expression profiling and tumor microenvironment characteristics among the three imaging subtypes. These findings highlight the heterogeneity in BC imaging and its potential value as a clinical biomarker for BC and for achieving precision medicine in BC. ABSTRACT: Background: This study aimed to reveal the heterogeneity of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of breast cancer (BC) and identify its prognosis values and molecular characteristics. Methods: Two radiogenomics cohorts (n = 246) were collected and tumor regions were segmented semi-automatically. A total of 174 radiomics features were extracted, and the imaging subtypes were identified and validated by unsupervised analysis. A gene-profile-based classifier was developed to predict the imaging subtypes. The prognostic differences and the biological and microenvironment characteristics of subtypes were uncovered by bioinformatics analysis. Results: Three imaging subtypes were identified and showed high reproducibility. The subtypes differed remarkably in tumor sizes and enhancement patterns, exhibiting significantly different disease-free survival (DFS) or overall survival (OS) in the discovery cohort (p = 0.024) and prognosis datasets (p ranged from <0.0001 to 0.0071). Large sizes and rapidly enhanced tumors usually had the worst outcomes. Associations were found between imaging subtypes and the established subtypes or clinical stages (p ranged from <0.001 to 0.011). Imaging subtypes were distinct in cell cycle and extracellular matrix (ECM)-receptor interaction pathways (false discovery rate, FDR < 0.25) and different in cellular fractions, such as cancer-associated fibroblasts (p < 0.05). Conclusions: The imaging subtypes had different clinical outcomes and biological characteristics, which may serve as potential biomarkers.