phaidra.vetmeduni.ac.at o:2554 DOI 10.1038/s41598-023-46607-w Histological classification of canine and feline lymphoma using a modular approach based on deep learning and advanced image processing Histopathological examination of tissue samples is essential for identifying tumor malignancy and the diagnosis of different types of tumor. In the case of lymphoma classification, nuclear size of the neoplastic lymphocytes is one of the key features to differentiate the different subtypes. Based on the combination of artificial intelligence and advanced image processing, we provide a workflow for the classification of lymphoma with regards to their nuclear size (small, intermediate, and large). As the baseline for our workflow testing, we use a Unet++ model trained on histological images of canine lymphoma with individually labeled nuclei. As an alternative to the Unet++, we also used a publicly available pre-trained and unmodified instance segmentation model called Stardist to demonstrate that our modular classification workflow can be combined with different types of segmentation models if they can provide proper nuclei segmentation. Subsequent to nuclear segmentation, we optimize algorithmic parameters for accurate classification of nuclear size using a newly derived reference size and final image classification based on a pathologists-derived ground truth. Our image classification module achieves a classification accuracy of up to 92% on canine lymphoma data. Compared to the accuracy ranging from 66.67 to 84% achieved using measurements provided by three individual pathologists, our algorithm provides a higher accuracy level and reproducible results. Our workflow also demonstrates a high transferability to feline lymphoma, as shown by its accuracy of up to 84.21%, even though our workflow was not optimized for feline lymphoma images. By determining the nuclear size distribution in tumor areas, our workflow can assist pathologists in subtyping lymphoma based on the nuclei size and potentially improve reproducibility. Our proposed approach is modular and comprehensible, thus allowing adaptation for specific tasks and increasing the users' trust in computer-assisted image classification. eng 2024-02-16T10:31:10.796Z LOMv1.0 Author BEGIN:VCARD VERSION:3.0 N:Haghofer;Andreas; FN:Andreas Haghofer 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:Weissenböck;Herbert; FN:Herbert Weissenböck X-ORCID:https://orcid.org/0000-0001-8197-6379 END:VCARD BEGIN:VCARD VERSION:3.0 N:Scharinger;Josef; FN:Josef Scharinger END:VCARD BEGIN:VCARD VERSION:3.0 N:Aubreville;Marc; FN:Marc Aubreville END:VCARD BEGIN:VCARD VERSION:3.0 N:Klopfleisch;Robert; FN:Robert Klopfleisch END:VCARD BEGIN:VCARD VERSION:3.0 N:Fuchs-Baumgartinger;Andrea; FN:Andrea Fuchs-Baumgartinger END:VCARD BEGIN:VCARD VERSION:3.0 N:Lipnik;Karoline; FN:Karoline Lipnik X-ORCID:https://orcid.org/0000-0002-7832-9012 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 3513423 https://phaidra.vetmeduni.ac.at/o:2554 https://phaidra.vetmeduni.ac.at/api/object/o:2554/thumbnail LOMv1.0 discipline