Deep learning for dermatologists: Part I. Fundamental concepts.

Journal: Journal of the American Academy of Dermatology
Published Date:

Abstract

Artificial intelligence is generating substantial interest in the field of medicine. One form of artificial intelligence, deep learning, has led to rapid advances in automated image analysis. In 2017, an algorithm demonstrated the ability to diagnose certain skin cancers from clinical photographs with the accuracy of an expert dermatologist. Subsequently, deep learning has been applied to a range of dermatology applications. Although experts will never be replaced by artificial intelligence, it will certainly affect the specialty of dermatology. In this first article of a 2-part series, the basic concepts of deep learning will be reviewed with the goal of laying the groundwork for effective communication between clinicians and technical colleagues. In part 2 of the series, the clinical applications of deep learning in dermatology will be reviewed and limitations and opportunities will be considered.

Authors

  • Dennis H Murphree
    Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, Minnesota, USA.
  • Pranav Puri
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Mayo Clinic Alix School of Medicine, Scottsdale, Arizona.
  • Huma Shamim
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota.
  • Spencer A Bezalel
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota.
  • Lisa A Drage
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota.
  • Michael Wang
    Department of Dermatology, University of California San Francisco, San Francisco, California.
  • Mark R Pittelkow
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • Rickey E Carter
    Department of Health Sciences Research, Mayo Clinic, Jacksonville, Florida.
  • Mark D P Davis
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota.
  • Alina G Bridges
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota.
  • Aaron R Mangold
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • James A Yiannias
    Department of Dermatology, Mayo Clinic, Scottsdale, Arizona.
  • Megha M Tollefson
    Department of Dermatology, Mayo Clinic, Rochester, MN.
  • Julia S Lehman
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota.
  • Alexander Meves
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota.
  • Clark C Otley
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota.
  • Olayemi Sokumbi
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Jacksonville, Florida; Department of Laboratory Medicine and Pathology, Mayo Clinic, Jacksonville, Florida.
  • Matthew R Hall
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Jacksonville, Florida.
  • Nneka Comfere
    Mayo Clinic Office of Artificial Intelligence in Dermatology; Department of Dermatology, Mayo Clinic, Rochester, Minnesota; Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota.