Translating Histopathology-Based AI Models into Clinical Tools for Homologous Recombination Deficiency Detection

Research Article

Abstract

With extensive research and development in the past decade, affordability of Poly (ADP-ribose) polymerase (PARP) inhibitor therapy has drastically improved. Homologous recombination deficiency (HRD), a key biomarker has been identified as an important guiding factor for PARP inhibitor therapeutic decisions in breast and ovarian cancer. However, identification of patients who will respond to Poly (ADP-ribose) polymerase (PARP) inhibitor therapy is challenging due to the lack of a unifying morphological phenotype. Current HRD testing via next-generation sequencing (NGS) is tissue-dependent, has high failure rates, misses relevant HRD genes, and involves longer turn-around times. To overcome these limitations, we developed OncoPredikt, a deep learning model trained on Hematoxylin and Eosin (H&E)-stained whole slide images (WSIs) to non-invasively predict HRD status. Based on a ResNet-50 architecture, the model was trained and validated on 514 WSIs, including 315 breast and 80 ovarian cancer samples from The Cancer Genome Atlas (TCGA), with HRD labels derived from genomic data. An independent dataset of 119 ovarian cancer cases with known BRCA1/2 or HRR mutations was used for validation. OncoPredikt achieved an AUC of 0.85 in breast cancer and 0.97 in ovarian cancer, with robust sensitivity, specificity, and F1-scores in identifying HRD-positive cases. These findings demonstrate OncoPredikt’s potential as a rapid, cost-effective, and tissue-sparing alternative to conventional NGS testing. While promising, further validation is needed to establish its generalizability across broader cancer types.