https://phaidra.vetmeduni.ac.at/o:4633 Artificial intelligence predicts c-KIT exon 11 genotype by phenotype in canine cutaneous mast cell tumors: Can human observers learn it? Puget, Chloe Chloe Puget Ganz, Jonathan Jonathan Ganz Bertram, Christof A. Christof A. Bertram 0000-0002-2402-9997 University of Veterinary Medicine Vienna Conrad, Thomas Thomas Conrad Baeblich, Malte Malte Baeblich Voss, Anne Anne Voss Landmann, Katharina Katharina Landmann Haake, Alexander F. H. Alexander F. H. Haake Spree, Andreas Andreas Spree Hartung, Svenja Svenja Hartung Aeschlimann, Leonore Leonore Aeschlimann Soto, Sara Sara Soto de Brot, Simone Simone de Brot Dettwiler, Martina Martina Dettwiler Aupperle-Lellbach, Heike Heike Aupperle-Lellbach Bolfa, Pompei Pompei Bolfa Bartel, Alexander Alexander Bartel Kiupel, Matti Matti Kiupel Breininger, Katharina Katharina Breininger Aubreville, Marc Marc Aubreville Klopfleisch, Robert Robert Klopfleisch Sage Publications Inc journal article open access eng 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. Online Version of Record before inclusion in an issue c-KIT Digital Pathology Deep Learning Dog Genotype Prediction Mast Cell Tumor Morphological Feature Performance Study http://creativecommons.org/licenses/by-nc/4.0/ https://phaidra.vetmeduni.ac.at/api/object/o:4633/download 10.1177/03009858251380284 https://phaidra.vetmeduni.ac.at/o:605 application/pdf Veterinary Pathology issn:1544-2217 VoR Veterinary Pathology 1.86 MB 2025