Diagnostic performance of a deep learning convolutional neural network in the differentiation of combined naevi and melanomas.

Journal: Journal of the European Academy of Dermatology and Venereology : JEADV
Published Date: Jun 1, 2020

Abstract

BACKGROUND: Deep learning convolutional neural networks (CNN) may assist physicians in the diagnosis of melanoma. The capacity of a CNN to differentiate melanomas from combined naevi, the latter representing well-known melanoma simulators, has not been investigated.

Authors

  • C Fink
    Department of Dermatology, University of Heidelberg, Heidelberg, Germany.
  • A Blum
    Office Based Clinic of Dermatology, Konstanz, Germany.
  • T Buhl
    Department of Dermatology, University of Göttingen, Göttingen, Germany.
  • C Mitteldorf
    Department of Dermatology and Allergology, University Medical Center Göttingen, Göttingen, Germany.
  • R Hofmann-Wellenhof
    Department of Dermatology and Venerology, Medical University of Graz, Graz, Austria.
  • T Deinlein
    Department of Dermatology and Venerology, Medical University of Graz, Graz, Austria.
  • W Stolz
    Department of Dermatology, Allergology and Environmental Medicine II, Hospital Thalkirchner Street, Munich, Germany.
  • L Trennheuser
    Department of Dermatology, University of Heidelberg, Heidelberg, Germany.
  • C Cussigh
    Department of Dermatology, University of Heidelberg, Heidelberg, Germany.
  • D Deltgen
    Department of Dermatology, University of Heidelberg, Heidelberg, Germany.
  • J K Winkler
    Department of Dermatology, University of Heidelberg, Heidelberg, Germany.
  • F Toberer
    Department of Dermatology, University of Heidelberg, Heidelberg, Germany.
  • A Enk
    Department of Dermatology, University of Heidelberg, Heidelberg, Germany.
  • A Rosenberger
    Department of Genetic Epidemiology, University Medical Center of Goettingen, Goettingen, Germany.
  • H A Haenssle
    Department of Dermatology, University of Heidelberg, Heidelberg, Germany. Electronic address: Holger.Haenssle@med.uni-heidelberg.de.

Keywords

External Resources

Popular Topics
Recent Journals