Discordance, accuracy and reproducibility study of pathologists’ diagnosis of melanoma and melanocytic tumors

Sarah Haggenmüller, Christoph Wies, Julia Abels, Jana T. Winterstein, Lukas Heinlein, Carina Nogueira Garcia, Jochen S. Utikal, Sebastian A. Wohlfeil, Friedegund Meier, Sarah Hobelsberger, Frank F. Gellrich, Mildred Sergon, Axel Hauschild, Lars E. French, Lucie Heinzerling, Justin G. Schlager, Kamran Ghoreschi, Max Schlaak, Franz J. Hilke, Gabriela Poch, Sören Korsing, Cosimo Sarfert, Carola Berking, Markus V. Heppt, Michael Erdmann, Sebastian Haferkamp, Konstantin Drexler, Dirk Schadendorf, Wiebke Sondermann, Matthias Goebeler, Bastian Schilling, Jakob Nikolas Kather, Stefan Fröhling, Mar Llamas-Velasco, Luis C. Requena, Gerardo Ferrara, Maite Fernandez-Figueras, Sylvie Fraitag, Cornelia S. L. Müller, Hans Starz, Heinz Kutzner, Raymond Barnhill, Richard Carr, Kenneth S. Resnik, Stephan Alexander Braun, Tim Holland-Letz and Titus J. Brinker ()
Additional contact information
Sarah Haggenmüller: German Cancer Research Center (DKFZ)
Christoph Wies: German Cancer Research Center (DKFZ)
Julia Abels: German Cancer Research Center (DKFZ)
Jana T. Winterstein: German Cancer Research Center (DKFZ)
Lukas Heinlein: German Cancer Research Center (DKFZ)
Carina Nogueira Garcia: German Cancer Research Center (DKFZ)
Jochen S. Utikal: Ruprecht-Karl University of Heidelberg
Sebastian A. Wohlfeil: Ruprecht-Karl University of Heidelberg
Friedegund Meier: Technische Universität Dresden
Sarah Hobelsberger: Technische Universität Dresden
Frank F. Gellrich: Technische Universität Dresden
Mildred Sergon: Technische Universität Dresden
Axel Hauschild: University Hospital (UKSH)
Lars E. French: LMU Munich
Lucie Heinzerling: LMU Munich
Justin G. Schlager: LMU Munich
Kamran Ghoreschi: Corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin
Max Schlaak: Corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin
Franz J. Hilke: Corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin
Gabriela Poch: Corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin
Sören Korsing: Corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin
Cosimo Sarfert: Corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin
Carola Berking: CCC Alliance WERA
Markus V. Heppt: CCC Alliance WERA
Michael Erdmann: CCC Alliance WERA
Sebastian Haferkamp: University Hospital Regensburg
Konstantin Drexler: University Hospital Regensburg
Dirk Schadendorf: University Hospital Essen
Wiebke Sondermann: University Hospital Essen
Matthias Goebeler: University Hospital Würzburg and National Center for Tumor Diseases (NCT) WERA Würzburg
Bastian Schilling: Department of Dermatology
Jakob Nikolas Kather: Technical University Dresden
Stefan Fröhling: National Center for Tumor Diseases (NCT) Heidelberg and German Cancer Research Center (DKFZ)
Mar Llamas-Velasco: University Hospital La Princesa
Luis C. Requena: Fundación Jiménez Díaz
Gerardo Ferrara: Istituto Nazionale Tumori I.R.C.C.S. Fondazione ‘G. Pascale’
Maite Fernandez-Figueras: Sant Cugat del Vallés
Sylvie Fraitag: Assistance Publique des Hopitaux de Paris
Cornelia S. L. Müller: Cytology and Molecular Diagnostics
Hans Starz: Dermpath München
Heinz Kutzner: Dermatopathology Friedrichshafen
Raymond Barnhill: Institut Curie
Richard Carr: Warwick Hospital
Kenneth S. Resnik: Institute for Dermatopathology
Stephan Alexander Braun: Heinrich-Heine-University
Tim Holland-Letz: German Cancer Research Center (DKFZ)
Titus J. Brinker: German Cancer Research Center (DKFZ)

Nature Communications, 2025, vol. 16, issue 1, 1-8

Abstract: Abstract Accurate melanoma diagnosis is crucial for patient outcomes and reliability of AI diagnostic tools. We assess interrater variability among eight expert pathologists reviewing histopathological images and clinical metadata of 792 melanoma-suspicious lesions prospectively collected at eight German hospitals. Moreover, we provide access to the largest panel-validated dataset featuring dermoscopic and histopathological images with metadata. Complete agreement is achieved in 53.5% of cases (424/792), and a majority vote ( ≥ five pathologists) in 90.9% (720/792). Considerable discordance is observed for non-invasive melanomas (complete agreement in only 10/73 cases). The expert panel disagrees with the local pathologists’ and dermatologists’ diagnoses in 14.9% and 33.5% of cases, respectively. This variability highlights the diagnostic challenges of early-stage melanomas and the need to reconsider how ground truth is established in routine care and AI research. Including at least two pathologists or virtual panels may contribute to more consistent diagnostic results.

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-56160-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-56160-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-56160-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().