Publikationsdatenbank

Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images (2023)

Art

Zeitschriftenartikel / wissenschaftlicher Beitrag

Autoren

Fragoso-Garcia, Marco

Wilm, Frauke

Bertram, Christof A.

Merz, Sophie

Schmidt, Anja

Donovan, Taryn

Fuchs-Baumgartinger, Andrea

Bartel, Alexander (WE 16)

Marzahl, Christian

Diehl, L. (WE 12)

Puget, Chloe

Maier, Andreas

Aubreville, Marc

Breininger, Katharina

Klopfleisch, R (WE 12)

Quelle

Veterinary pathology : an internat. journal of natural and experimental disease in animals

Bandzählung: 60

Heftzählung: 6

Seiten: 865 – 875

ISSN: 0300-9858

Sprache

Englisch

Verweise

URL (Volltext): http://journals.sagepub.com/doi/10.1177/03009858231189205

DOI: 10.1177/03009858231189205

Pubmed: 37515411

Kontakt

Institut für Tierpathologie

Robert-von-Ostertag-Str. 15
14163 Berlin
+49 30 838 62450
pathologie@vetmed.fu-berlin.de

Abstract / Zusammenfassung

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.