Artificial intelligence predicts c-KIT exon 11 genotype by phenotype in canine cutaneous mast cell tumors: Can human observers learn it?

Journal: Veterinary pathology
Published Date: Oct 8, 2025

Abstract

Canine cutaneous mast cell tumors (ccMCTs) are frequent neoplasms with variable biological behaviors. Internal tandem duplication mutations in c-KIT exon 11 (c-KIT-11-ITD) are associated with poor prognosis but predict therapeutic response to tyrosine kinase inhibitors. In a previous work, deep learning algorithms managed to predict the presence of c-KIT-11-ITD on digitalized hematoxylin and eosin-stained histological slides (whole-slide images, WSIs) in up to 87% of cases, suggesting the existence of morphological features characterizing ccMCTs carrying c-KIT-11-ITD. This 3-stage blinded study aimed to identify morphological features indicative of c-KIT-11-ITD and to evaluate the ability of human observers to learn this task. 17 untrained pathologists first classified 8 WSIs and 200 image patches (highly relevant for algorithmic classification) of ccMCTs as either positive or negative for c-KIT-11-ITD. Second, they self-trained to recognize c-KIT-11-ITD by looking at the same WSIs and patches correctly sorted. Third, pathologists classified 15 new WSIs and 200 new patches according to c-KIT-11-ITD status. In addition, participants reported microscopic features they considered relevant for their decision. Without training, participants correctly classified the c-KIT-11-ITD status of 63%-88% of WSIs and 43%-55% of patches. With self-training, 25%-38% of WSIs and 55%-56% of patches were correctly classified. High cellular pleomorphism, anisokaryosis, and sparse cytoplasmic granulation were commonly suggested as features associated with c-KIT-11-ITD-positive ccMCTs, none of which showed reliable predictivity in a follow-up study. The results indicate that transfer of algorithmic skills to the human observer is difficult. A c-KIT-11-ITD-specific morphological feature remains to be extracted from the artificial intelligence model.

Authors

  • Chloé Puget
    Institute of Veterinary Pathology, Freie Universität Berlin, Berlin, Germany.
  • Jonathan Ganz
    Technische Hochschule Ingolstadt, Ingolstadt, Germany.
  • Christof A Bertram
    Institute of Veterinary Pathology, Freie Universität Berlin, Berlin, Germany.
  • Thomas Conrad
    Freie Universität Berlin, Berlin, Germany.
  • Malte Baeblich
    Freie Universität Berlin, Berlin, Germany.
  • Anne Voss
    Freie Universität Berlin, Berlin, Germany.
  • Katharina Landmann
    Freie Universität Berlin, Berlin, Germany.
  • Alexander F H Haake
    Freie Universität Berlin, Berlin, Germany.
  • Andreas Spree
    Freie Universität Berlin, Berlin, Germany.
  • Svenja Hartung
    Sieklandstraße, Tecklenburg, Germany.
  • Leonore Aeschlimann
    University of Bern, Bern, Switzerland.
  • Sara Soto
    University of Bern, Bern, Switzerland.
  • Simone de Brot
    University of Bern, Bern, Switzerland.
  • Martina Dettwiler
    University of Bern, Bern, Switzerland.
  • Heike Aupperle-Lellbach
    LABOKLIN GmbH & Co.KG, Bad Kissingen, Germany.
  • Pompei Bolfa
    Ross University School of Veterinary Medicine, Basseterre, Saint Kitts and Nevis.
  • Alexander Bartel
    Freie Universität Berlin, Berlin, Germany.
  • Matti Kiupel
    Michigan State University, Lansing, MI, USA.
  • Katharina Breininger
  • Marc Aubreville
    Pattern Recognition Lab, Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. [email protected].
  • Robert Klopfleisch
    Institute of Veterinary Pathology, Freie Universität Berlin, Berlin, Germany.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals