Deep learning based histological classification of adnex tumors.

Journal: European journal of cancer (Oxford, England : 1990)
Published Date:

Abstract

BACKGROUND: Cutaneous adnexal tumors are a diverse group of tumors arising from structures of the hair appendages. Although often benign, malignant entities occur which can metastasize and lead to patients´ death. Correct diagnosis is critical to ensure optimal treatment and best possible patient outcome. Artificial intelligence (AI) in the form of deep neural networks has recently shown enormous potential in the field of medicine including pathology, where we and others have found common cutaneous tumors can be detected with high sensitivity and specificity. To become a widely applied tool, AI approaches will also need to reliably detect and distinguish less common tumor entities including the diverse group of cutaneous adnexal tumors.

Authors

  • Philipp Jansen
    Department of Dermatology, University Hospital Essen, Essen, Germany.
  • Jean Le'Clerc Arrastia
    University of Bremen, Bremen 28359, Germany.
  • Daniel Otero Baguer
    University of Bremen, Bremen 28359, Germany.
  • Maximilian Schmidt
    University of Bremen, Bremen 28359, Germany.
  • Jennifer Landsberg
    Department of Dermatology and Allergy, University of Bonn, Bonn, Germany.
  • Jörg Wenzel
    Department of Dermatology, University Hospital Bonn, Bonn 53127, Germany.
  • Michael Emberger
    Patholab - Labor für Pathologie Salzburg, Salzburg 5020, Austria.
  • Dirk Schadendorf
    Department of Dermatology, University Hospital Essen, 45147 Essen, Germany.
  • Eva Hadaschik
    Department of Dermatology, University Hospital Essen, Essen 45147, Germany.
  • Peter Maaß
    Center for Industrial Mathematics, University of Bremen, 28359 Bremen, Germany.
  • Klaus Georg Griewank
    Department of Dermatology, University Hospital Essen, Essen 45147, Germany; Dermatopathologie bei Mainz, Nieder-Olm 55268, Germany. Electronic address: klaus.griewank@uk-essen.de.