Machine learning for rhabdomyosarcoma histopathology

• Published in: Modern Pathology Vol. 35; no. 9; pp. 1193 - 1203
• Main Authors: Frankel, Arthur O., Lathara, Melvin, Shaw, Celine Y., Wogmon, Owen, Jackson, Jacob M., Clark, Mattie M., Eshraghi, Navah, Keenen, Stephanie E., Woods, Andrew D., Purohit, Reshma, Ishi, Yukitomo, Moran, Nirupama, Eguchi, Mariko, Ahmed, Farhat Ul Ain, Khan, Sara, Ioannou, Maria, Perivoliotis, Konstantinos, Li, Pin, Zhou, Huixia, Alkhaledi, Ahmad, Davis, Elizabeth J., Galipeau, Danielle, Randall, R.L., Wozniak, Agnieszka, Schoffski, Patrick, Lee, Che-Jui, Huang, Paul H., Jones, Robin L., Rubin, Brian P., Darrow, Morgan, Srinivasa, Ganapati, Rudzinski, Erin R., Chen, Sonja, Berlow, Noah E., Keller, Charles
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 01.09.2022; Elsevier BV; Nature Publishing Group US; Elsevier Limited
• Subjects: 13/105; 14/105; 631/67/1798; 631/67/2321; 631/67/2332; Adolescent; Alveoli; Animal models; Animals; Child; Children; Deep learning; Differential diagnosis; Genetic engineering; Histopathology; Humans; Laboratory Medicine; Learning algorithms; Machine Learning; Medicine; Medicine & Public Health; Mice; Neural networks; Neural Networks, Computer; Pathologists; Pathology; Pediatrics; Rhabdomyosarcoma; Rhabdomyosarcoma - diagnosis; Rhabdomyosarcoma, Embryonal; Rhabdomyosarcoma, Embryonal - pathology; Sarcoma; Tumors; Young Adult; Young adults
• ISSN: 0893-3952; 1530-0285; 1530-0285
• DOI: 10.1038/s41379-022-01075-x

Correctly diagnosing a rare childhood cancer such as sarcoma can be critical to assigning the correct treatment regimen. With a finite number of pathologists worldwide specializing in pediatric/young adult sarcoma histopathology, access to expert differential diagnosis early in case assessment is limited for many global regions. The lack of highly-trained sarcoma pathologists is especially pronounced in low to middle-income countries, where pathology expertise may be limited despite a similar rate of sarcoma incidence. To address this issue in part, we developed a deep learning convolutional neural network (CNN)-based differential diagnosis system to act as a pre-pathologist screening tool that quantifies diagnosis likelihood amongst trained soft-tissue sarcoma subtypes based on whole histopathology tissue slides. The CNN model is trained on a cohort of 424 centrally-reviewed histopathology tissue slides of alveolar rhabdomyosarcoma, embryonal rhabdomyosarcoma and clear-cell sarcoma tumors, all initially diagnosed at the originating institution and subsequently validated by central review. This CNN model was able to accurately classify the withheld testing cohort with resulting receiver operating characteristic (ROC) area under curve (AUC) values above 0.889 for all tested sarcoma subtypes. We subsequently used the CNN model to classify an externally-sourced cohort of human alveolar and embryonal rhabdomyosarcoma samples and a cohort of 318 histopathology tissue sections from genetically engineered mouse models of rhabdomyosarcoma. Finally, we investigated the overall robustness of the trained CNN model with respect to histopathological variations such as anaplasia, and classification outcomes on histopathology slides from untrained disease models. Overall positive results from our validation studies coupled with the limited worldwide availability of sarcoma pathology expertise suggests the potential of machine learning to assist local pathologists in quickly narrowing the differential diagnosis of sarcoma subtype in children, adolescents, and young adults.