Deep-Learning Based Prediction of Homologous Recombination Deficiency (HRD) Status from Histological Features in Breast Cancer, a research study

HRD, originally described in tumors from patients with germline mutations in BRCA1/2 genes, renders cells sensitive to poly-ADP ribose polymerase inhibitors (PARPi), but can be caused by mutations in other genes and is prevalent across multiple cancer types. Eligibility for PARPi therapy is based on determination of tumor HRD or homologous recombination proficient (HRP) status . Genomic sequencing to identify BRCA mutations or genomic instability is used to determine HRD status but has a high rate of failure. Here, we apply a deep-learning based computational approach to directly infer HRD status from digitized whole side images (WSI) of hematoxylin and eosin (H&E) stained histology samples in breast cancer tumors.