application/pdf eng doi:10.3390/vetsci11060278 https://phaidra.vetmeduni.ac.at/o:3278 2024 article Primary Lung-Tumors; Prostate-Cancer; Dogs; Classification; Survival; Stereology; Prognosis; Neoplasia; Biopsies Glahn, Imaine (University of Veterinary Medicine Vienna) Bertram, Christof A. (University of Veterinary Medicine Vienna) Klang, Andrea (University of Veterinary Medicine Vienna) Dark, Michael J. (University of Florida) Bolfa, Pompei (Ross University School of Veterinary Medicine) Bartenschlager, Florian (Freie Universität Berlin) Assenmacher, Charles-Antoine (University of Pennsylvania) Janout, Hannah (University of Applied Sciences Upper Austria / Johannes Kepler University of Linz) Hyndman, Philip S. (The Schwarzman Animal Medical Center) Kreilmeier-Berger, Theresa (University of Veterinary Medicine Vienna) Bartel, Alexander (Freie Universität Berlin) Degasperi, Brigitte (University of Veterinary Medicine Vienna) Winkler, Stephan M. (University of Applied Sciences Upper Austria / Johannes Kepler University of Linz) Haghofer, Andreas (University of Applied Sciences Upper Austria / Johannes Kepler University of Linz) Donovan, Taryn A. (The Schwarzman Animal Medical Center) Aubreville, Marc (Technische Hochschule Ingolstadt) Scharinger, Josef (Johannes Kepler University of Linz) Ganz, Jonathan (Technische Hochschule Ingolstadt) Schulman, F. Yvonne (Mars Petcare Science and Diagnostics) Richter, Barbara (University of Veterinary Medicine Vienna) Merz, Sophie (IDEXX Vet Med Labor GmbH) Klopfleisch, Robert (Freie Universität Berlin) Veterinary Sciences 11(6) (2024) 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. MDPI Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility CC BY 4.0 International http://creativecommons.org/licenses/by/4.0/