Document Type
Article
Publication Date
2-15-2025
Abstract
Primary cutaneous squamous cell carcinoma (cSCC) is responsible for ~10,000 deaths annually in the United States. Stratification of risk of poor outcome at initial biopsy would significantly impact clinical decision-making during the initial post operative period where intervention has been shown to be most effective. Using whole-slide images (WSI) from 163 patients from 3 institutions, we developed a self supervised deep-learning model to predict poor outcomes in cSCC patients from histopathological features at initial diagnosis, and validated it using WSI from 563 patients, collected from two other academic institutions. For disease-free survival prediction, the model attained a concordance index of 0.73 in the development cohort and 0.84 in the Mayo cohort. The model's interpretability revealed that features like poor differentiation and deep invasion were strongly associated with poor prognosis. Furthermore, the model is effective in stratifying risk among BWH T2a and AJCC T2, known for outcome heterogeneity.
Recommended Citation
Coudray, Nicolas; Juarez, Michelle C.; Criscito, Maressa C.; Quiros, Adalberto Claudio; Wilken, Reason; Jackson Cullison, Stephanie R.; Stevenson, Mary L.; Doudican, Nicole A.; Yuan, Ke; Aquino, Jamie D.; Klufas, Daniel M.; North, Jeffrey P.; Yu, Siegrid S.; Murad, Fadi; Ruiz, Emily; Schmults, Chrysalyne D.; Cardona Machado, Cristian D.; Cañueto, Javier; Choudhary, Anirudh; Hughes, Alysia N.; Stockard, Alyssa; Leibovit-Reiben, Zachary; Mangold, Aaron R.; Tsirigos, Aristotelis; and Carucci, John A., "Self Supervised Artificial Intelligence Predicts Poor Outcome From Primary Cutaneous Squamous Cell Carcinoma at Diagnosis" (2025). Department of Dermatology and Cutaneous Biology Faculty Papers. Paper 202.
https://jdc.jefferson.edu/dcbfp/202
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
PubMed ID
39955424
Language
English
Comments
This article is the author's final published version in npj Digital Medicine, Volume 8, Issue 1, 2025, Article number 105.
The published version is available at https://doi.org/10.1038/s41746-025-01496-3.
Copyright © The Author(s) 2025