Titel (eng)

Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility

Autor*in

Imaine Glahn   University of Veterinary Medicine Vienna

Christof A. Bertram   University of Veterinary Medicine Vienna

Stephan M. Winkler   University of Applied Sciences Upper Austria / Johannes Kepler University of Linz

Marc Aubreville   Technische Hochschule Ingolstadt

Josef Scharinger   Johannes Kepler University of Linz

Jonathan Ganz   Technische Hochschule Ingolstadt

F. Yvonne Schulman   Mars Petcare Science and Diagnostics

Barbara Richter   University of Veterinary Medicine Vienna

Sophie Merz   IDEXX Vet Med Labor GmbH

Robert Klopfleisch   Freie Universität Berlin

Andrea Klang   University of Veterinary Medicine Vienna

Michael J. Dark   University of Florida

Pompei Bolfa   Ross University School of Veterinary Medicine

Florian Bartenschlager   Freie Universität Berlin

Charles-Antoine Assenmacher   University of Pennsylvania

Hannah Janout   University of Applied Sciences Upper Austria / Johannes Kepler University of Linz

Philip S. Hyndman   The Schwarzman Animal Medical Center

Theresa Kreilmeier-Berger   University of Veterinary Medicine Vienna

Alexander Bartel   Freie Universität Berlin

Brigitte Degasperi   University of Veterinary Medicine Vienna

Andreas Haghofer   University of Applied Sciences Upper Austria / Johannes Kepler University of Linz

Taryn A. Donovan   The Schwarzman Animal Medical Center

Verlag

MDPI

Beschreibung (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.

Sprache des Objekts

Englisch

Datum

2024

Rechte

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/

Klassifikation

Primary Lung-Tumors; Prostate-Cancer; Dogs; Classification; Survival; Stereology; Prognosis; Neoplasia; Biopsies

Mitglied in der/den Collection(s) (1)