Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children’s Oncology Group

Milewski D, Jung H, Brown GT, Liu Y, Somerville B, Lisle C, Ladanyi M, Rudzinski ER, Choo-Wosoba H, Barkauskas DA, Lo T, Hall D, Linardic CM, Wei JS, Chou HC, Skapek SX, Venkatramani R, Bode PK, Steinberg SM, Zaki G, Kuznetsov IB, Hawkins DS, Shern JF, Collins J, Khan J. Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children’s Oncology Group. Clin Cancer Res. 2023 Jan 17;29(2):364-378. doi: 10.1158/1078-0432.CCR-22-1663. PubMed PMID: 36346688; PubMed Central PMCID: PMC9843436.

Rhabdomyosarcoma (RMS) is an aggressive soft-tissue sarcoma, which primarily occurs in children and young adults. We previously reported specific genomic alterations in RMS, which strongly correlated with survival; however, predicting these mutations or high-risk disease at diagnosis remains a significant challenge. In this study, we utilized convolutional neural networks (CNN) to learn histologic features associated with driver mutations and outcome using hematoxylin and eosin (H&E) images of RMS. Digital whole slide H&E images were collected from clinically annotated diagnostic tumor samples from 321 patients with RMS enrolled in Children’s Oncology Group (COG) trials (1998–2017). Patches were extracted and fed into deep learning CNNs to learn features associated with mutations and relative event-free survival risk. The performance of the trained models was evaluated against independent test sample data (n = 136) or holdout test data.