Quantitative analysis of fiber-level collagen features in H&E whole-slide images predicts neoadjuvant therapy response in patients with HER2+ BC

Neoadjuvant treatment (NAT) combining chemotherapy and HER2-targeted agents is frequently administered to HER2-positive (HER2+) breast cancer (BC) patients, with some experiencing a pathological complete response (pCR) and others having residual disease measured by the residual cancer burden (RCB) score. Here, we investigate associations between treatment response in this patient population and properties of collagen fibers and the tumor microenvironment. Detailed visualizations of collagen were generated by inferred quantitative multimodal anisotropy imaging (iQMAI), a machine learning (ML)-based model that infers fiber-level collagen features from hematoxylin and eosin (H&E)-stained whole slide images (WSIs). iQMAI models were trained on fiber-level collagen images using QMAI, a polarization-based imaging technique that highlights structured substances like collagen in breast tissue1 or liver tissue.