Deep Learning Artificial Intelligence Predicts Homologous Recombination Deficiency and Platinum Response From Histologic Slides.

Erik N Bergstrom Ammal Abbasi Marcos Diaz-GayLoïck GallandSylvain Ladoire Scott M Lippman Ludmil B Alexandrov

Published in: Journal of clinical oncology : official journal of the American Society of Clinical Oncology (2024)

DeepHRD can predict HRD in breast and ovarian cancers directly from routine H&E slides across multiple external cohorts, slide scanners, and tissue fixation variables. When compared with molecular testing, DeepHRD classified 1.8- to 3.1-fold more patients with HRD, which exhibited better OS in high-grade serous ovarian cancer and platinum-specific PFS in metastatic breast cancer.

Keyphrases

artificial intelligence
high grade
metastatic breast cancer
deep learning
dna repair
low grade
dna damage
big data
machine learning
convolutional neural network
minimally invasive
clinical practice
single molecule