Artificial Intelligence to Predict the BRAF V595E Mutation in Canine Urinary Bladder Urothelial Carcinomas

Abstract

In dogs, the BRAF mutation (V595E) is common in bladder and prostate cancer and represents a specific diagnostic marker. Recent advantages in artificial intelligence (AI) offer new opportunities in the field of tumour marker detection. While AI histology studies have been conducted in humans to detect BRAF mutation in cancer, comparable studies in animals are lacking. In this study, we used commercially available AI histology software to predict BRAF mutation in whole slide images (WSI) of bladder urothelial carcinomas (UC) stained with haematoxylin and eosin (HE), based on a training (n = 81) and a validation set (n = 96). Among 96 WSI, 57 showed identical PCR and AI-based BRAF predictions, resulting in a sensitivity of 58% and a specificity of 63%. The sensitivity increased substantially to 89% when excluding small or poor-quality tissue sections. Test reliability depended on tumour differentiation (p < 0.01), presence of inflammation (p < 0.01), slide quality (p < 0.02) and sample size (p < 0.02). Based on a small subset of cases with available adjacent non-neoplastic urothelium, AI was able to distinguish malignant from benign epithelium. This is the first study to demonstrate the use of AI histology to predict BRAF mutation status in canine UC. Despite certain limitations, the results highlight the potential of AI in predicting molecular alterations in routine tissue sections.

Effective detection of BRAFV595E mutation in canine urothelial and prostate carcinomas using immunohistochemistry

“…In the present study, 72/122 (59%) UC and 13/21 (65%) PC were BRAF V595E mutated. This is in accordance with the prevalence of the mutation reported in the literature using PCR, 5–7,9,20 despite our limitation of a small sample size of PC cases. In the dog, BRAF V595E is considered a diagnostic marker for UC and PC 5,20 .…”

“…For instance, in thyroid cancer, it is strongly linked with either the papillary or anaplastic morphology, 34 and in melanomas, it is associated with pigmentation, scatter of intraepidermal melanocytes and solar elastosis 35 . Our recent study using artificial intelligence to analyse canine urinary bladder tumours revealed that BRAF mutations in these cases frequently corresponded with papillary growth, smooth and pushing rather than invasive tumour fronts 7 . The present investigations support a parallel between the morphological implications of BRAF mutations in both human and canine cancers.…”

“…There is a significant predisposition for Scottish Terriers, West Highland White Terriers, Shelties and others breeds for tumour development, and other risk factors include female sex and being spayed or neutered 3–6 . The high breed predisposition indicates an underlying genetic basis for the disease 3,6–9 . In multiple studies, the activating BRAF V595E mutation, the canine homologue of human BRAF V600E , was identified as somatic driver mutation to be frequently present in 65%–87% of UC of dogs 1,5,6,8,10,11 .…”

Review of Molecular Technologies for Investigating Canine Cancer

“…In veterinary oncology, investigations of deep learning-based tumour histology are starting to be performed on canine tumours, wherein artificial intelligence (AI)-based methods are using digitized whole-slide images (WSIs) to make pathological diagnoses, such as diagnosing canine skin tumours (of seven different types) [ 144 , 145 ] and canine osteosarcoma (where the AI program was able to identify specific histologic subtypes that may have prognostic value) [ 146 ]. However, to date, there has only been one genotype–phenotype correlation study in canines; it was recently shown that deep learning using a commercial AI histology software could detect the BRAF p.V595E mutation on HE-stained canine bladder cancer tissue sections ( Figure 9 ), with a sensitivity of 89% [ 147 ].…”

“…may have prognostic value) [146]. However, to date, there has only been one genotypephenotype correlation study in canines; it was recently shown that deep learning using a commercial AI histology software could detect the BRAF p.V595E mutation on HE-stained canine bladder cancer tissue sections (Figure 9), with a sensitivity of 89% [147].…”