Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images

Fragoso-Garcia M, Wilm F, Bertram CA, Merz S, Schmidt A, Donovan T, Fuchs-Baumgartinger A, Bartel A, Marzahl C, Diehl L, Puget C, Maier A, Aubreville M, Breininger K, Klopfleisch R (2023)

Publication Type: Journal article

Publication year: 2023

Journal

DOI: 10.1177/03009858231189205

Abstract

Microscopic evaluation of hematoxylin and eosin-stained slides is still the diagnostic gold standard for a variety of diseases, including neoplasms. Nevertheless, intra- and interrater variability are well documented among pathologists. So far, computer assistance via automated image analysis has shown potential to support pathologists in improving accuracy and reproducibility of quantitative tasks. In this proof of principle study, we describe a machine-learning-based algorithm for the automated diagnosis of 7 of the most common canine skin tumors: trichoblastoma, squamous cell carcinoma, peripheral nerve sheath tumor, melanoma, histiocytoma, mast cell tumor, and plasmacytoma. We selected, digitized, and annotated 350 hematoxylin and eosin-stained slides (50 per tumor type) to create a database divided into training, n = 245 whole-slide images (WSIs), validation (n = 35 WSIs), and test sets (n = 70 WSIs). Full annotations included the 7 tumor classes and 6 normal skin structures. The data set was used to train a convolutional neural network (CNN) for the automatic segmentation of tumor and nontumor classes. Subsequently, the detected tumor regions were classified patch-wise into 1 of the 7 tumor classes. A majority of patches-approach led to a tumor classification accuracy of the network on the slide-level of 95% (133/140 WSIs), with a patch-level precision of 85%. The same 140 WSIs were provided to 6 experienced pathologists for diagnosis, who achieved a similar slide-level accuracy of 98% (137/140 correct majority votes). Our results highlight the feasibility of artificial intelligence-based methods as a support tool in diagnostic oncologic pathology with future applications in other species and tumor types.

Authors with CRIS profile

Involved external institutions

IDEXX Laboratories Germany (DE) Freie Universität Berlin Germany (DE) Veterinärmedizinische Universität Wien (Vetmeduni Vienna) / University of Veterinary Medicine, Vienna Austria (AT) Technische Hochschule Ingolstadt Germany (DE) Animal Medical Center (AMC) United States (USA) (US)

How to cite

APA:

Fragoso-Garcia, M., Wilm, F., Bertram, C.A., Merz, S., Schmidt, A., Donovan, T.,... Klopfleisch, R. (2023). Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images. Veterinary Pathology. https://doi.org/10.1177/03009858231189205

MLA:

Fragoso-Garcia, Marco, et al. "Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images." Veterinary Pathology (2023).

BibTeX: Download