Assessment of a Deep Learning Model Trained on Permanent Pathology for the Classification of Squamous Cell Carcinoma in Mohs Frozen Sections: Lessons Learned.

Journal: Dermatologic surgery : official publication for American Society for Dermatologic Surgery [et al.]
Published Date: Jul 9, 2025

Abstract

BACKGROUND: There is a scarcity of artificial intelligence models trained on frozen pathology. One way to expand the clinical utility of models trained on permanent pathology is by applying them to frozen sections and fine-tune based on weaknesses.

Authors

  • Jorge A Rios-Duarte
    School of Medicine, Universidad de los Andes, Bogotá, Colombia.
  • Anirudh Choudhary
    Department of Computational Science and Engineering, Georgia Institute of Technology, GA, USA.
  • Shams Nassir
    Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • Miranda Yousif
    Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • Alysia Hughes
    Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • Jacob A Kechter
    Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • Ravishankar K Iyer
    Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States of America.
  • Zachary Leibovit-Reiben
    Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • Alyssa Stockard
    Alix School of Medicine, Mayo Clinic, Scottsdale, Arizona.
  • Aaron R Mangold
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • Nahid Y Vidal
    Department of Dermatology, Mayo Clinic, Rochester, Minnesota, USA Division of Dermatologic Surgery, Mayo Clinic, Rochester, Minnesota, USA. Vidal.Nahid@mayo.edu.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals