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

Simple Summary In canine urothelial carcinoma, the BRAF gene is frequently mutated (V595E). To detect this mutation, urine or tissue samples are currently tested by PCR. Recent advances in digital pathology and the power of artificial intelligence (AI) have opened up new possibilities for the detection of genetic alterations through AI histology. This new approach offers a wide range of new opportunities in the field of diagnostic and predictive tumour marker detection. The aim of this study was to test the efficacy of AI histology to predict the presence of the BRAF mutation in canine bladder carcinomas and to assess its intratumoral heterogeneity. This is the first study to utilise AI histology to predict BRAF mutational status in canine urothelial cell 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.

[1]  B. Inman,et al.  Whole exome sequencing analysis of canine urothelial carcinomas without BRAF V595E mutation: Short in-frame deletions in BRAF and MAP2K1 suggest alternative mechanisms for MAPK pathway disruption , 2023, PLoS genetics.

[2]  Ognjen Arandjelovíc,et al.  Detection of malignancy in whole slide images of endometrial cancer biopsies using artificial intelligence , 2023, PloS one.

[3]  Cheng Yang,et al.  Artificial intelligence-based model for lymph node metastases detection on whole slide images in bladder cancer: a retrospective, multicentre, diagnostic study. , 2023, The Lancet. Oncology.

[4]  Youshan Zhang,et al.  Artificial intelligence 101 for veterinary diagnostic imaging. , 2022, Veterinary radiology & ultrasound : the official journal of the American College of Veterinary Radiology and the International Veterinary Radiology Association.

[5]  William P. Katt,et al.  Highly recurrent BRAF p.V595E mutation in canine papillary oral squamous cell carcinoma. , 2022, Veterinary and comparative oncology.

[6]  J. Suárez-Peñaranda,et al.  Machine Learning Techniques in Predicting BRAF Mutation Status in Cutaneous Melanoma From Clinical and Histopathologic Features , 2022, Applied immunohistochemistry & molecular morphology : AIMM.

[7]  G. Scambia,et al.  Deep-Learning to Predict BRCA Mutation and Survival from Digital H&E Slides of Epithelial Ovarian Cancer , 2022, International journal of molecular sciences.

[8]  Jakob Nikolas Kather,et al.  Artificial intelligence in histopathology: enhancing cancer research and clinical oncology , 2022, Nature Cancer.

[9]  T. Nakajima,et al.  Artificial Intelligence-Powered Prediction of ALK Gene Rearrangement in Patients With Non-Small-Cell Lung Cancer. , 2022, JCO clinical cancer informatics.

[10]  S. Pradervand,et al.  Structure-based prediction of BRAF mutation classes using machine-learning approaches , 2022, Scientific Reports.

[11]  K. Sirinukunwattana,et al.  Automated quality assessment of large digitised histology cohorts by artificial intelligence , 2022, Scientific Reports.

[12]  P. Oliveira,et al.  Molecular Markers in Urinary Bladder Cancer: Applications for Diagnosis, Prognosis and Therapy , 2022, Veterinary sciences.

[13]  Reza Borhani,et al.  Artificial intelligence: A promising frontier in bladder cancer diagnosis and outcome prediction. , 2022, Critical reviews in oncology/hematology.

[14]  Beatriz Garcia Gonzalez,et al.  Computer-assisted mitotic count using a deep learning–based algorithm improves interobserver reproducibility and accuracy , 2021, bioRxiv.

[15]  A. Kehl,et al.  BRAF mutation status and its prognostic significance in 79 canine urothelial carcinomas: a retrospective study (2006-2019). , 2021, Veterinary and comparative oncology.

[16]  Jakob Nikolas Kather,et al.  Swarm learning for decentralized artificial intelligence in cancer histopathology , 2021, Nature Medicine.

[17]  N. Razavian,et al.  Deep learning and pathomics analyses reveal cell nuclei as important features for mutation prediction of BRAF-mutated melanomas. , 2021, The Journal of investigative dermatology.

[18]  Dimitris N. Metaxas,et al.  Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning , 2021, npj Precision Oncology.

[19]  F. Aeffner,et al.  Whole-slide imaging, tissue image analysis, and artificial intelligence in veterinary pathology: An updated introduction and review , 2021, Veterinary pathology.

[20]  K. Yoon,et al.  Establishment of Canine Transitional Cell Carcinoma Cell Lines Harboring BRAF V595E Mutation as a Therapeutic Target , 2021, International journal of molecular sciences.

[21]  Sagar M. Utturkar,et al.  Phase I/II Trial of Vemurafenib in Dogs with Naturally Occurring, BRAF-mutated Urothelial Carcinoma , 2021, Molecular Cancer Therapeutics.

[22]  Neeraj Kumar,et al.  Weakly supervised learning on unannotated H&E‐stained slides predicts BRAF mutation in thyroid cancer with high accuracy , 2021, The Journal of pathology.

[23]  Neel S. Madhukar,et al.  Artificial Intelligence in Cancer Research and Precision Medicine. , 2021, Cancer discovery.

[24]  M. Colombel,et al.  Artificial intelligence to improve cytology performances in bladder carcinoma detection: results of the VisioCyt test , 2021, BJU international.

[25]  M. Furue,et al.  BRAF Heterogeneity in Melanoma , 2021, Current Treatment Options in Oncology.

[26]  B. Martin,et al.  Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study. , 2021, The Lancet. Oncology.

[27]  Y. Jo,et al.  Artificial intelligence to predict the BRAFV600E mutation in patients with thyroid cancer , 2020, PloS one.

[28]  Filippo Molinari,et al.  The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis , 2020, Comput. Biol. Medicine.

[29]  S. Hewitt,et al.  The Use of Quantitative Digital Pathology to Measure Proteoglycan and Glycosaminoglycan Expression and Accumulation in Healthy and Diseased Tissues , 2020, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[30]  Qijiang Mao,et al.  Classification and mutation prediction based on histopathology H&E images in liver cancer using deep learning , 2020, npj Precision Oncology.

[31]  H. Inokuma,et al.  Quantitative analysis of the BRAF V595E mutation in plasma cell-free DNA from dogs with urothelial carcinoma , 2020, PloS one.

[32]  Jonathan L Lustgarten,et al.  Veterinary informatics: forging the future between veterinary medicine, human medicine, and One Health initiatives—a joint paper by the Association for Veterinary Informatics (AVI) and the CTSA One Health Alliance (COHA) , 2020, JAMIA open.

[33]  M. Rantalainen,et al.  Artificial intelligence as the next step towards precision pathology , 2020, Journal of internal medicine.

[34]  J. Gardner,et al.  Artificial intelligence in educational assessment: 'Breakthrough? Or buncombe and ballyhoo?' , 2020, J. Comput. Assist. Learn..

[35]  Sagar M. Utturkar,et al.  Naturally-Occurring Invasive Urothelial Carcinoma in Dogs, a Unique Model to Drive Advances in Managing Muscle Invasive Bladder Cancer in Humans , 2020, Frontiers in Oncology.

[36]  A. Peaston,et al.  Comparative aspects of mast cell neoplasia in animals and the role of KIT in prognosis and treatment , 2019, Veterinary medicine and science.

[37]  Thomas J. Fuchs,et al.  Clinical-grade computational pathology using weakly supervised deep learning on whole slide images , 2019, Nature Medicine.

[38]  M. Kiupel,et al.  Diagnosis and Prognosis of Canine Cutaneous Mast Cell Tumors. , 2019, The Veterinary clinics of North America. Small animal practice.

[39]  N. Mongan,et al.  A Fibromyxoid Stromal Response is Associated with Muscle Invasion in Canine Urothelial Carcinoma. , 2019, Journal of comparative pathology.

[40]  R. Klopfleisch,et al.  Correlation of BRAF Variant V595E, Breed, Histological Grade and Cyclooxygenase-2 Expression in Canine Transitional Cell Carcinomas , 2019, Veterinary sciences.

[41]  A. Lane.  Tumors in domestic animals, 5th edn. Edited by DJ Meuten. Wiley-Blackwell, 2016. 1000 pages. Price A$321.95. ISBN 9780813821795. , 2018, Australian Veterinary Journal.

[42]  A. Kehl,et al.  Diagnostische Aussagekraft der BRAF-Mutation V595E in Urinproben, Ausstrichen und Bioptaten beim kaninen Übergangszellkarzinom , 2018, Tierärztliche Praxis Ausgabe K: Kleintiere / Heimtiere.

[43]  S. Boorjian,et al.  The dog as an animal model for bladder and urethral urothelial carcinoma: Comparative epidemiology and histology , 2018, Oncology letters.

[44]  Steven J. M. Jones,et al.  Comprehensive Molecular Characterization of Muscle-Invasive Bladder Cancer , 2017, Cell.

[45]  T. Ratliff,et al.  Naturally Occurring Canine Invasive Urinary Bladder Cancer: A Complementary Animal Model to Improve the Success Rate in Human Clinical Trials of New Cancer Drugs , 2017, International journal of genomics.

[46]  K. Owzar,et al.  Targeted Exome Sequencing of the Cancer Genome in Patients with Very High-risk Bladder Cancer. , 2016, European urology.

[47]  C. Cole,et al.  COSMIC: High‐Resolution Cancer Genetics Using the Catalogue of Somatic Mutations in Cancer , 2016, Current protocols in human genetics.

[48]  M. Breen,et al.  Detection of BRAF Mutation in Urine DNA as a Molecular Diagnostic for Canine Urothelial and Prostatic Carcinoma , 2015, PloS one.

[49]  M. Breen,et al.  Comparative Aspects of BRAF Mutations in Canine Cancers , 2015, Veterinary sciences.

[50]  D. Knapp,et al.  Management of transitional cell carcinoma of the urinary bladder in dogs: a review. , 2015, Veterinary journal.

[51]  M. Breen,et al.  BRAF Mutations in Canine Cancers , 2015, PloS one.

[52]  Kristin M. Post,et al.  Discordancy in BRAF mutations among primary and metastatic melanoma lesions: clinical implications for targeted therapy , 2015, Modern Pathology.

[53]  E. Ostrander,et al.  Homologous Mutation to Human BRAF V600E Is Common in Naturally Occurring Canine Bladder Cancer—Evidence for a Relevant Model System and Urine-Based Diagnostic Test , 2015, Molecular Cancer Research.

[54]  J. Utikal,et al.  Combined BRAF and MEK inhibition versus BRAF inhibition alone in melanoma. , 2014, The New England journal of medicine.

[55]  C. Sander,et al.  Prevalence and co-occurrence of actionable genomic alterations in high-grade bladder cancer. , 2013, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[56]  Matti Pietikäinen,et al.  Identification of tumor epithelium and stroma in tissue microarrays using texture analysis , 2012, Diagnostic Pathology.

[57]  D. Spandidos,et al.  Mutational Analysis of the BRAF Gene in Transitional Cell Carcinoma of the Bladder , 2009 .

[58]  O. Rath,et al.  MAP kinase signalling pathways in cancer , 2007, Oncogene.

[59]  G. Ogilvie,et al.  Canine bladder and urethral tumors: a retrospective study of 115 cases (1980-1985). , 1992, Journal of veterinary internal medicine.

[60]  A. Kehl,et al.  [Diagnostic value of the BRAF variant V595E in urine samples, smears and biopsies from canine transitional cell carcinoma]. , 2018, Tierarztliche Praxis. Ausgabe K, Kleintiere/Heimtiere.

[61]  J. Fagin,et al.  Association between BRAF V600E mutation and recurrence of papillary thyroid cancer. , 2015, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.