Evaluating deep learning-based melanoma classification using immunohistochemistry and routine histology: A three center study

Research output: Contribution to journalResearch articleContributedpeer-review

Contributors

  • Christoph Wies - , German Cancer Research Center (DKFZ) (Author)
  • Lucas Schneider - , German Cancer Research Center (DKFZ) (Author)
  • Sarah Haggenmüller - , German Cancer Research Center (DKFZ) (Author)
  • Tabea-Clara Bucher - , German Cancer Research Center (DKFZ) (Author)
  • Sarah Hobelsberger - , Department of Dermatology, Skin Tumor Center, University Hospital Carl Gustav Carus Dresden (Author)
  • Markus V Heppt - , Friedrich-Alexander University Erlangen-Nürnberg (Author)
  • Gerardo Ferrara - , Anatomic Pathology and Cytopathology Unit-Istituto Nazionale Tumori di Napoli (Author)
  • Eva I Krieghoff-Henning - , German Cancer Research Center (DKFZ) (Author)
  • Titus J Brinker - , German Cancer Research Center (DKFZ) (Author)

Abstract

Pathologists routinely use immunohistochemical (IHC)-stained tissue slides against MelanA in addition to hematoxylin and eosin (H&E)-stained slides to improve their accuracy in diagnosing melanomas. The use of diagnostic Deep Learning (DL)-based support systems for automated examination of tissue morphology and cellular composition has been well studied in standard H&E-stained tissue slides. In contrast, there are few studies that analyze IHC slides using DL. Therefore, we investigated the separate and joint performance of ResNets trained on MelanA and corresponding H&E-stained slides. The MelanA classifier achieved an area under receiver operating characteristics curve (AUROC) of 0.82 and 0.74 on out of distribution (OOD)-datasets, similar to the H&E-based benchmark classification of 0.81 and 0.75, respectively. A combined classifier using MelanA and H&E achieved AUROCs of 0.85 and 0.81 on the OOD datasets. DL MelanA-based assistance systems show the same performance as the benchmark H&E classification and may be improved by multi stain classification to assist pathologists in their clinical routine.

Details

Original languageEnglish
Pages (from-to)e0297146
JournalPloS one
Volume19
Issue number1
Publication statusPublished - 2024
Peer-reviewedYes

External IDs

PubMedCentral PMC10798511
Scopus 85182868794
ORCID /0000-0001-5703-324X/work/152543186

Keywords

Keywords

  • Humans, Melanoma/diagnosis, Immunohistochemistry, Deep Learning, MART-1 Antigen, ROC Curve