Deep Learning for Classification of Colorectal Polyps on Whole-slide Images

• Published in: Journal of pathology informatics Vol. 8; no. 1; p. 30
• Main Authors: Korbar, Bruno, Olofson, Andrea M., Miraflor, Allen P, Nicka, Catherine M., Suriawinata, Matthew A., Torresani, Lorenzo, Suriawinata, Arief A., Hassanpour, Saeed
• Format: Journal Article
• Language: English
• Published: India Elsevier Inc 01.01.2017; Wolters Kluwer India Pvt. Ltd; Medknow Publications & Media Pvt. Ltd; Medknow Publications & Media Pvt Ltd; Elsevier
• Subjects: Cancer; Classification; Colonoscopy; Colorectal cancer; Colorectal polyps; Computer science; Confidence intervals; Deep learning; digital pathology; Digitization; Garlic; Histology; histopathological characterization; Human performance; Image analysis; Image classification; Information processing; Laboratories; Machine learning; Medical screening; Medicine; Neural networks; Original; Pathology; Pattern recognition; Risk assessment; Statistical analysis; Surveillance; Test procedures; histopathological characterization; Colorectal polyps; deep learning; digital pathology
• ISSN: 2153-3539; 2229-5089; 2153-3539
• DOI: 10.4103/jpi.jpi_34_17

Context: Histopathological characterization of colorectal polyps is critical for determining the risk of colorectal cancer and future rates of surveillance for patients. However, this characterization is a challenging task and suffers from significant inter- and intra-observer variability. Aims: We built an automatic image analysis method that can accurately classify different types of colorectal polyps on whole-slide images to help pathologists with this characterization and diagnosis. Setting and Design: Our method is based on deep-learning techniques, which rely on numerous levels of abstraction for data representation and have shown state-of-the-art results for various image analysis tasks. Subjects and Methods: Our method covers five common types of polyps (i.e., hyperplastic, sessile serrated, traditional serrated, tubular, and tubulovillous/villous) that are included in the US Multisociety Task Force guidelines for colorectal cancer risk assessment and surveillance. We developed multiple deep-learning approaches by leveraging a dataset of 2074 crop images, which were annotated by multiple domain expert pathologists as reference standards. Statistical Analysis: We evaluated our method on an independent test set of 239 whole-slide images and measured standard machine-learning evaluation metrics of accuracy, precision, recall, and F1 score and their 95% confidence intervals. Results: Our evaluation shows that our method with residual network architecture achieves the best performance for classification of colorectal polyps on whole-slide images (overall accuracy: 93.0%, 95% confidence interval: 89.0%-95.9%). Conclusions: Our method can reduce the cognitive burden on pathologists and improve their efficacy in histopathological characterization ofcolorectal polyps and in subsequent risk assessment and follow-up recommendations.