Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility
University of Veterinary Medicine Vienna
University of Veterinary Medicine Vienna
Stephan M. Winkler University of Applied Sciences Upper Austria / Johannes Kepler University of Linz
Technische Hochschule Ingolstadt
Johannes Kepler University of Linz
Jonathan Ganz Technische Hochschule Ingolstadt
Mars Petcare Science and Diagnostics
Barbara Richter University of Veterinary Medicine Vienna
Sophie Merz IDEXX Vet Med Labor GmbH
Freie Universität Berlin
Andrea Klang University of Veterinary Medicine Vienna
University of Florida
Ross University School of Veterinary Medicine
Florian Bartenschlager Freie Universität Berlin
University of Pennsylvania
University of Applied Sciences Upper Austria / Johannes Kepler University of Linz
The Schwarzman Animal Medical Center
University of Veterinary Medicine Vienna
Freie Universität Berlin
University of Veterinary Medicine Vienna
University of Applied Sciences Upper Austria / Johannes Kepler University of Linz
The Schwarzman Animal Medical Center
MDPI
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.
Englisch
2024
Dieses Werk bzw. dieser Inhalt steht unter einer
CC BY 4.0 - Creative Commons Namensnennung 4.0 International Lizenz.
CC BY 4.0 International
http://creativecommons.org/licenses/by/4.0/
Primary Lung-Tumors; Prostate-Cancer; Dogs; Classification; Survival; Stereology; Prognosis; Neoplasia; Biopsies