phaidra.vetmeduni.ac.at o:3278 DOI 10.3390/vetsci11060278 Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility 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. eng Primary Lung-Tumors; Prostate-Cancer; Dogs; Classification; Survival; Stereology; Prognosis; Neoplasia; Biopsies 2024-07-24T07:29:37.198Z LOMv1.0 Author BEGIN:VCARD VERSION:3.0 N:Glahn;Imaine; FN:Imaine Glahn X-ORCID:https://orcid.org/0009-0003-9247-9302 END:VCARD BEGIN:VCARD VERSION:3.0 N:Bertram;Christof A.; FN:Christof A. Bertram X-ORCID:https://orcid.org/0000-0002-2402-9997 END:VCARD BEGIN:VCARD VERSION:3.0 N:Winkler;Stephan M.; FN:Stephan M. Winkler END:VCARD BEGIN:VCARD VERSION:3.0 N:Aubreville;Marc; FN:Marc Aubreville X-ORCID:https://orcid.org/0000-0002-5294-5247 END:VCARD BEGIN:VCARD VERSION:3.0 N:Scharinger;Josef; FN:Josef Scharinger X-ORCID:https://orcid.org/0000-0001-6502-7501 END:VCARD BEGIN:VCARD VERSION:3.0 N:Ganz;Jonathan; FN:Jonathan Ganz END:VCARD BEGIN:VCARD VERSION:3.0 N:Schulman;F. Yvonne; FN:F. Yvonne Schulman X-ORCID:https://orcid.org/0000-0002-7454-8517 END:VCARD BEGIN:VCARD VERSION:3.0 N:Richter;Barbara; FN:Barbara Richter END:VCARD BEGIN:VCARD VERSION:3.0 N:Merz;Sophie; FN:Sophie Merz END:VCARD BEGIN:VCARD VERSION:3.0 N:Klopfleisch;Robert; FN:Robert Klopfleisch X-ORCID:https://orcid.org/0000-0002-6308-0568 END:VCARD BEGIN:VCARD VERSION:3.0 N:Klang;Andrea; FN:Andrea Klang END:VCARD BEGIN:VCARD VERSION:3.0 N:Dark;Michael J.; FN:Michael J. Dark X-ORCID:https://orcid.org/0000-0002-6547-1298 END:VCARD BEGIN:VCARD VERSION:3.0 N:Bolfa;Pompei; FN:Pompei Bolfa X-ORCID:https://orcid.org/0000-0002-2903-1535 END:VCARD BEGIN:VCARD VERSION:3.0 N:Bartenschlager;Florian; FN:Florian Bartenschlager END:VCARD BEGIN:VCARD VERSION:3.0 N:Assenmacher;Charles-Antoine; FN:Charles-Antoine Assenmacher X-ORCID:https://orcid.org/0000-0003-0073-2730 END:VCARD BEGIN:VCARD VERSION:3.0 N:Janout;Hannah; FN:Hannah Janout X-ORCID:https://orcid.org/0000-0002-0294-3585 END:VCARD BEGIN:VCARD VERSION:3.0 N:Hyndman;Philip S.; FN:Philip S. Hyndman X-ORCID:https://orcid.org/0000-0003-4367-4032 END:VCARD BEGIN:VCARD VERSION:3.0 N:Kreilmeier-Berger;Theresa; FN:Theresa Kreilmeier-Berger X-ORCID:https://orcid.org/0000-0001-5346-2821 END:VCARD BEGIN:VCARD VERSION:3.0 N:Bartel;Alexander; FN:Alexander Bartel X-ORCID:https://orcid.org/0000-0002-1280-6138 END:VCARD BEGIN:VCARD VERSION:3.0 N:Degasperi;Brigitte; FN:Brigitte Degasperi X-ORCID:https://orcid.org/0009-0001-0559-3728 END:VCARD BEGIN:VCARD VERSION:3.0 N:Haghofer;Andreas; FN:Andreas Haghofer X-ORCID:https://orcid.org/0000-0001-6649-5374 END:VCARD BEGIN:VCARD VERSION:3.0 N:Donovan;Taryn A.; FN:Taryn A. Donovan X-ORCID:https://orcid.org/0000-0001-5740-9550 END:VCARD https://w3id.org/kim/hcrt/scheme https://w3id.org/kim/hcrt/text Textdokument Text LOMv1.0 yes https://creativecommons.org/licenses/by/4.0 application/pdf 5907061 https://phaidra.vetmeduni.ac.at/o:3278 https://phaidra.vetmeduni.ac.at/api/object/o:3278/thumbnail LOMv1.0 discipline