J Pathol Inform. 2017 Jul 25;8:30. doi: 10.4103/jpi.jpi_34_17. eCollection 2017.
Deep Learning for Classification of Colorectal Polyps on Whole-slide Images.
Journal of pathology informatics
Bruno Korbar, Andrea M Olofson, Allen P Miraflor, Catherine M Nicka, Matthew A Suriawinata, Lorenzo Torresani, Arief A Suriawinata, Saeed Hassanpour
Affiliations
Affiliations
- Department of Biomedical Data Science, Geisel School of Medicine at Dartmouth, One Medical Center Drive, Lebanon, NH 03756, USA.
- Department of Computer Science, Dartmouth College, Hanover, NH 03755, USA.
- Department of Pathology and Laboratory Medicine, Geisel School of Medicine at Dartmouth, One Medical Center Drive, Lebanon, NH 03756, USA.
- Department of Epidemiology, Geisel School of Medicine at Dartmouth, One Medical Center Drive, Lebanon, NH 03756, USA.
PMID: 28828201
PMCID: PMC5545773 DOI: 10.4103/jpi.jpi_34_17
Abstract
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 of colorectal polyps and in subsequent risk assessment and follow-up recommendations.
Keywords: Colorectal polyps; deep learning; digital pathology; histopathological characterization
Conflict of interest statement
There are no conflicts of interest.
References
- Am J Clin Pathol. 2005 Feb;123(2):281-7 - PubMed
- J Pathol Inform. 2013 May 30;4:9 - PubMed
- Med Image Anal. 2015 Feb;20(1):237-48 - PubMed
- Gastrointest Endosc. 2015 Mar;81(3):517-24 - PubMed
- Med Image Comput Comput Assist Interv. 2013;16(Pt 2):403-10 - PubMed
- Ann Diagn Pathol. 1998 Feb;2(1):79-91 - PubMed
- Gastroenterology. 2012 Sep;143(3):844-857 - PubMed
- Hum Pathol. 2011 Jan;42(1):1-10 - PubMed
- AMIA Annu Symp Proc. 2015 Nov 05;2015 :1899-908 - PubMed
- Gastroenterology. 2010 Jun;138(6):2088-100 - PubMed
- Phys Med Biol. 2003 Jul 7;48(13):N183-91 - PubMed
- IEEE Trans Med Imaging. 2015 Nov;34(11):2366-78 - PubMed
- J Pathol Inform. 2016 Jul 26;7:29 - PubMed
- Arch Pathol Lab Med. 2006 May;130(5):630-2 - PubMed
- IEEE Trans Med Imaging. 2016 May;35(5):1196-1206 - PubMed
- Dig Dis Sci. 2015 Mar;60(3):773-80 - PubMed
- IEEE Rev Biomed Eng. 2009;2:147-71 - PubMed
- Dis Colon Rectum. 2011 Oct;54(10):1216-23 - PubMed
- Cancer. 2005 Nov 15;104(10):2205-13 - PubMed
- Histopathology. 2009 Jul;55(1):63-6 - PubMed
- Nature. 2015 May 28;521(7553):436-44 - PubMed
- IEEE Rev Biomed Eng. 2014;7:97-114 - PubMed
- Microsc Res Tech. 2002 Oct 15;59(2):109-18 - PubMed
- Med Image Anal. 2016 Oct;33:170-175 - PubMed
- J Biophotonics. 2013 Jan;6(1):88-100 - PubMed
Publication Types