https://phaidra.vetmeduni.ac.at/o:3278 Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility Glahn, Imaine Imaine Glahn 0009-0003-9247-9302 University of Veterinary Medicine Vienna Bertram, Christof A. Christof A. Bertram 0000-0002-2402-9997 University of Veterinary Medicine Vienna Winkler, Stephan M. Stephan M. Winkler University of Applied Sciences Upper Austria / Johannes Kepler University of Linz Aubreville, Marc Marc Aubreville 0000-0002-5294-5247 Technische Hochschule Ingolstadt Scharinger, Josef Josef Scharinger 0000-0001-6502-7501 Johannes Kepler University of Linz Ganz, Jonathan Jonathan Ganz Technische Hochschule Ingolstadt Schulman, F. Yvonne F. Yvonne Schulman 0000-0002-7454-8517 Mars Petcare Science and Diagnostics Richter, Barbara Barbara Richter University of Veterinary Medicine Vienna Merz, Sophie Sophie Merz IDEXX Vet Med Labor GmbH Klopfleisch, Robert Robert Klopfleisch 0000-0002-6308-0568 Freie Universität Berlin Klang, Andrea Andrea Klang University of Veterinary Medicine Vienna Dark, Michael J. Michael J. Dark 0000-0002-6547-1298 University of Florida Bolfa, Pompei Pompei Bolfa 0000-0002-2903-1535 Ross University School of Veterinary Medicine Bartenschlager, Florian Florian Bartenschlager Freie Universität Berlin Assenmacher, Charles-Antoine Charles-Antoine Assenmacher 0000-0003-0073-2730 University of Pennsylvania Janout, Hannah Hannah Janout 0000-0002-0294-3585 University of Applied Sciences Upper Austria / Johannes Kepler University of Linz Hyndman, Philip S. Philip S. Hyndman 0000-0003-4367-4032 The Schwarzman Animal Medical Center Kreilmeier-Berger, Theresa Theresa Kreilmeier-Berger 0000-0001-5346-2821 University of Veterinary Medicine Vienna Bartel, Alexander Alexander Bartel 0000-0002-1280-6138 Freie Universität Berlin Degasperi, Brigitte Brigitte Degasperi 0009-0001-0559-3728 University of Veterinary Medicine Vienna Haghofer, Andreas Andreas Haghofer 0000-0001-6649-5374 University of Applied Sciences Upper Austria / Johannes Kepler University of Linz Donovan, Taryn A. Taryn A. Donovan 0000-0001-5740-9550 The Schwarzman Animal Medical Center MDPI text eng The integration of deep learning-based tools into diagnostic workflows is increasingly prevalent due to their efficiency and reproducibility in various settings. We investigated the utility of automated nuclear morphometry for assessing nuclear pleomorphism (NP), a criterion of malignancy in the current grading system in canine pulmonary carcinoma (cPC), and its prognostic implications. We developed a deep learning-based algorithm for evaluating NP (variation in size, i.e., anisokaryosis and/or shape) using a segmentation model. Its performance was evaluated on 46 cPC cases with comprehensive follow-up data regarding its accuracy in nuclear segmentation and its prognostic ability. Its assessment of NP was compared to manual morphometry and established prognostic tests (pathologists' NP estimates (n = 11), mitotic count, histological grading, and TNM-stage). The standard deviation (SD) of the nuclear area, indicative of anisokaryosis, exhibited good discriminatory ability for tumor-specific survival, with an area under the curve (AUC) of 0.80 and a hazard ratio (HR) of 3.38. The algorithm achieved values comparable to manual morphometry. In contrast, the pathologists' estimates of anisokaryosis resulted in HR values ranging from 0.86 to 34.8, with slight inter-observer reproducibility (k = 0.204). Other conventional tests had no significant prognostic value in our study cohort. Fully automated morphometry promises a time-efficient and reproducible assessment of NP with a high prognostic value. Further refinement of the algorithm, particularly to address undersegmentation, and application to a larger study population are required. Primary Lung-Tumors; Prostate-Cancer; Dogs; Classification; Survival; Stereology; Prognosis; Neoplasia; Biopsies http://creativecommons.org/licenses/by/4.0/ https://phaidra.vetmeduni.ac.at/api/object/o:3278/download 10.3390/vetsci11060278 https://phaidra.vetmeduni.ac.at/o:605 application/pdf Veterinary Sciences 11(6) (2024) Veterinary Sciences 11 6 5.63 MB 2024