Self supervised artificial intelligence predicts poor outcome from primary cutaneous squamous cell carcinoma at diagnosis
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.
Authors
- Siegrid S. Yu
- Maressa C. Criscito (ORCID: https://orcid.org/0000-0003-0951-3817)
- Mary L. Stevenson (ORCID: https://orcid.org/0000-0002-7113-2065)
- Ke Yuan (ORCID: https://orcid.org/0000-0002-2318-1460)
- Zachary Leibovit‐Reiben (ORCID: https://orcid.org/0000-0002-9229-1145)
- Chrysalyne D. Schmults (ORCID: https://orcid.org/0000-0002-0446-5847)
- Nicole Doudican (ORCID: https://orcid.org/0000-0003-3827-9644)
- Jeffrey P. North (ORCID: https://orcid.org/0000-0003-3973-5314)
- Emily S. Ruiz (ORCID: https://orcid.org/0000-0001-5824-2721)
- Fadi Murad (ORCID: https://orcid.org/0000-0001-9135-571X)
- Aristotelis Tsirigos (ORCID: https://orcid.org/0000-0002-7512-8477)
- Nicolas Coudray (ORCID: https://orcid.org/0000-0002-6050-2219)
- Aaron R. Mangold (ORCID: https://orcid.org/0000-0001-6873-1705)
- Reason Wilken (ORCID: https://orcid.org/0000-0001-7512-7565)
- Daniel M. Klufas (ORCID: https://orcid.org/0000-0002-4745-104X)
- Stephanie R. Jackson (ORCID: https://orcid.org/0000-0002-5833-122X)
- John A. Carucci (ORCID: https://orcid.org/0000-0001-6817-9439)
- Michelle C. Juarez (ORCID: https://orcid.org/0000-0002-5791-4984)
- Javier Cañueto (ORCID: https://orcid.org/0000-0003-0037-7353)
- Adalberto Claudio Quiros (ORCID: https://orcid.org/0000-0003-4804-0741)
- Jamie D. Aquino
- Alysia N. Hughes
- Anirudh Choudhary
- C Machado (ORCID: https://orcid.org/0009-0005-5399-121X)
- Alyssa Stockard
Institutions
- Brigham and Women's Hospital (US)
- Northwell Health (US)
- Harvard University (US)
- Thomas Jefferson University (US)
- University of Illinois Urbana-Champaign (US)
- University of California, San Francisco (US)
- Telio (Norway) (NO)
- Complejo Hospitalario de Salamanca (ES)
- Precision for Medicine (United States) (US)
- Mayo Clinic in Arizona (US)
- Instituto de Investigación Biomédica de Salamanca (ES)
- Centro de Investigación del Cáncer (ES)
- Cancer Research UK Scotland Institute (GB)
- New York University (US)
- University of Glasgow (GB)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2025-02-15
- DOI
- https://doi.org/10.1038/s41746-025-01496-3
- Citations
- 8
- Primary Topic
- Nonmelanoma Skin Cancer Studies
- Type
- article
- Field-Weighted Citation Impact
- 10.83
Funders
- York University
- University of Glasgow
- National Institutes of Health
- School of Medicine, New York University
- National Cancer Institute