Haggenmueller, Sarah and Wies, Christoph and Abels, Julia and Winterstein, Jana T. and Heinlein, Lukas and Nogueira Garcia, Carina and Utikal, Jochen S. and Wohlfeil, Sebastian A. and Meier, Friedegund and Hobelsberger, Sarah and Gellrich, Frank F. and Sergon, Mildred and Hauschild, Axel and French, Lars E. and Heinzerling, Lucie and Schlager, Justin G. and Ghoreschi, Kamran and Schlaak, Max and Hilke, Franz J. and Poch, Gabriela and Korsing, Soren and Sarfert, Cosimo and Berking, Carola and Heppt, Markus V. and Erdmann, Michael and Haferkamp, Sebastian and Drexler, Konstantin and Schadendorf, Dirk and Sondermann, Wiebke and Goebeler, Matthias and Schilling, Bastian and Kather, Jakob Nikolas and Froehling, Stefan and Llamas-Velasco, Mar and Requena, Luis C. and Ferrara, Gerardo and Fernandez-Figueras, Maite and Fraitag, Sylvie and Mueller, Cornelia S. L. and Starz, Hans and Kutzner, Heinz and Barnhill, Raymond and Carr, Richard and Resnik, Kenneth S. and Braun, Stephan Alexander and Holland-Letz, Tim and Brinker, Titus J. (2025) Discordance, accuracy and reproducibility study of pathologists' diagnosis of melanoma and melanocytic tumors. NATURE COMMUNICATIONS, 16 (1): 789. ISSN , 2041-1723
Full text not available from this repository. (Request a copy)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.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | HISTOPATHOLOGIC DIAGNOSIS; CLASSIFICATION; CANCER; |
| Subjects: | 600 Technology > 610 Medical sciences Medicine |
| Divisions: | Medicine > Lehrstuhl für Dermatologie und Venerologie |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 24 Mar 2026 12:51 |
| Last Modified: | 24 Mar 2026 12:51 |
| URI: | https://pred.uni-regensburg.de/id/eprint/68066 |
Actions (login required)
 |
View Item |
