Original article Clinical endoscopy| Volume 92, ISSUE 4, P891-899, October 2020

Download started.


Computer-aided diagnosis for characterization of colorectal lesions: comprehensive software that includes differentiation of serrated lesions

Published:March 04, 2020DOI:

      Background and Aims

      Endoscopy guidelines recommend adhering to policies such as resect and discard only if the optical biopsy is accurate. However, accuracy in predicting histology can vary greatly. Computer-aided diagnosis (CAD) for characterization of colorectal lesions may help with this issue. In this study, CAD software developed at the University of Adelaide (Australia) that includes serrated polyp differentiation was validated with Japanese images on narrow-band imaging (NBI) and blue-laser imaging (BLI).


      CAD software developed using machine learning and densely connected convolutional neural networks was modeled with NBI colorectal lesion images (Olympus 190 series - Australia) and validated for NBI (Olympus 290 series) and BLI (Fujifilm 700 series) with Japanese datasets. All images were correlated with histology according to the modified Sano classification. The CAD software was trained with Australian NBI images and tested with separate sets of images from Australia (NBI) and Japan (NBI and BLI).


      An Australian dataset of 1235 polyp images was used as training, testing, and internal validation sets. A Japanese dataset of 20 polyp images on NBI and 49 polyp images on BLI was used as external validation sets. The CAD software had a mean area under the curve (AUC) of 94.3% for the internal set and 84.5% and 90.3% for the external sets (NBI and BLI, respectively).


      The CAD achieved AUCs comparable with experts and similar results with NBI and BLI. Accurate CAD prediction was achievable, even when the predicted endoscopy imaging technology was not part of the training set.


      ASGE (American Society for Gastrointestinal Endoscopy), AUC (area under the curve), BLI (blue-laser imaging), CAD (computer-aided diagnosis), CI (confidence interval), CNN (convolutional neural network), CRC (colorectal cancer), HP (hyperplastic polyp), MS (modified Sano), NBI (narrow-band imaging), SSA/P (sessile serrated adenoma/polyp), WASP (Workgroup on Serrated Polyps and Polyposis)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Gastrointestinal Endoscopy
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Arnold M.
        • Sierra M.S.
        • Laversanne M.
        • et al.
        Global patterns and trends in colorectal cancer incidence and mortality.
        Gut. 2017; 66: 683-691
        • Pyenson B.
        • Pickhardt P.J.
        • Sawhney T.G.
        • et al.
        Medicare cost of colorectal cancer screening: CT colonography vs. optical colonoscopy.
        Abdom Imaging. 2015; 40: 2966-2976
        • Bowel Cancer Australia
        A Colonoscopy Wait-time and Performance Guarantee.
        (Available at:)
        • Rex D.K.
        • Kahi C.
        • O'Brien M.
        • et al.
        The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps.
        Gastrointest Endosc. 2011; 73: 419-422
        • Abu Dayyeh B.K.
        • Thosani N.
        • Konda V.
        • et al.
        ASGE Technology Committee systematic review and meta-analysis assessing the ASGE PIVI thresholds for adopting real-time endoscopic assessment of the histology of diminutive colorectal polyps.
        Gastrointest Endosc. 2015; 81: 502.e1-502.e16
        • Sharma P.
        • Frye J.
        • Frizelle F.
        Accuracy of visual prediction of pathology of colorectal polyps: how accurate are we?.
        ANZ J Surg. 2014; 84: 365-370
        • Rees C.J.
        • Rajasekhar P.T.
        • Wilson A.
        • et al.
        Narrow band imaging optical diagnosis of small colorectal polyps in routine clinical practice: the Detect Inspect Characterise Resect and Discard 2 (DISCARD 2) study.
        Gut. 2017; 66: 887-895
        • Ladabaum U.
        • Fioritto A.
        • Mitani A.
        • et al.
        Real-time optical biopsy of colon polyps with narrow band imaging in community practice does not yet meet key thresholds for clinical decisions.
        Gastroenterology. 2013; 144: 81-91
        • Byrne M.F.
        • Chapados N.
        • Soudan F.
        • et al.
        Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model.
        Gut. 2019; 68: 94-100
        • Tamai N.
        • Saito Y.
        • Sakamoto T.
        • et al.
        Effectiveness of computer-aided diagnosis of colorectal lesions using novel software for magnifying narrow-band imaging: a pilot study.
        Endosc Int Open. 2017; 5: E690-E694
        • Singh R.
        • Jayanna M.
        • Navadgi S.
        • et al.
        Narrow-band imaging with dual focus magnification in differentiating colorectal neoplasia.
        Dig Endosc. 2013; 25: 16-20
        • IJspeert J.E.
        • Bastiaansen B.A.
        • van Leerdam M.E.
        • et al.
        Development and validation of the WASP classification system for optical diagnosis of adenomas, hyperplastic polyps and sessile serrated adenomas/polyps.
        Gut. 2016; 65: 963-970
        • Zorron Cheng Tao Pu L.
        • Cheong K.L.
        • Koay D.S.C.
        • et al.
        Randomised controlled trial comparing modified Sano's and narrow band imaging international colorectal endoscopic classifications for colorectal lesions.
        World J Gastrointest Endosc. 2018; 10: 210-218
        • Zorron Cheng Tao Pu L.
        • Yamamura T.
        • Nakamura M.
        • et al.
        Modified Sano's is the most accurate classification for characterising serrated polyps and adenomas with different virtual chromoendoscopy methods: results of a prospective study.
        J Gastroenterol Hepatol. 2019; 34: 226-227
      1. Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Available at: Accessed March 20, 2020.

      2. Kingma DP, Ba J. Adam: a method for stochastic optimization. International Conference on Learning Representations. Available at: Accessed March 20, 2020.

        • Hanley J.A.
        • McNeil B.J.
        The meaning and use of the area under a receiver operating characteristic (ROC) curve.
        Radiology. 1982; 143: 29-36
        • Takemura Y.
        • Yoshida S.
        • Tanaka S.
        • et al.
        Computer-aided system for predicting the histology of colorectal tumors by using narrow-band imaging magnifying colonoscopy (with video).
        Gastrointest Endosc. 2012; 75: 179-185
        • Kominami Y.
        • Yoshida S.
        • Tanaka S.
        • et al.
        Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy.
        Gastrointest Endosc. 2016; 83: 643-649
        • Krizhevsky A.
        • Sutskever I.
        • Hinton G.E.
        ImageNet classification with deep convolutional neural networks.
        Commun ACM. 2017; 60: 84-90
        • Ribeiro E.
        • Uhl A.
        • Wimmer G.
        • et al.
        Exploring deep learning and transfer learning for colonic polyp classification.
        Comput Math Methods Med. 2016; 20166584725
        • Chen P.J.
        • Lin M.C.
        • Lai M.J.
        • et al.
        Accurate classification of diminutive colorectal polyps using computer-aided analysis.
        Gastroenterology. 2018; 154: 568-575
        • Jass J.R.
        Classification of colorectal cancer based on correlation of clinical, morphological and molecular features.
        Histopathology. 2007; 50: 113-130
        • Samowitz W.S.
        • Albertsen H.
        • Herrick J.
        • et al.
        Evaluation of a large, population-based sample supports a CpG island methylator phenotype in colon cancer.
        Gastroenterology. 2005; 129: 837-845
        • Kahi C.J.
        • Hewett D.G.
        • Norton D.L.
        • et al.
        Prevalence and variable detection of proximal colon serrated polyps during screening colonoscopy.
        Clin Gastroenterol Hepatol. 2011; 9: 42-46
        • Stefanescu D.
        • Streba C.
        • Cartana E.T.
        • et al.
        Computer aided diagnosis for confocal laser endomicroscopy in advanced colorectal adenocarcinoma.
        PLoS One. 2016; 11e0154863
        • Mesejo P.
        • Pizarro D.
        • Abergel A.
        • et al.
        Computer-aided classification of gastrointestinal lesions in regular colonoscopy.
        IEEE Trans Med Imaging. 2016; 35: 2051-2063
        • Misawa M.
        • Kudo S.E.
        • Mori Y.
        • et al.
        Accuracy of computer-aided diagnosis based on narrow-band imaging endocytoscopy for diagnosing colorectal lesions: comparison with experts.
        Int J Comput Assist Radiol Surg. 2017; 12: 757-766
        • Sano Y.
        • Tanaka S.
        • Kudo S-e
        • et al.
        Narrow-band imaging (NBI) magnifying endoscopic classification of colorectal tumors proposed by the Japan NBI Expert Team.
        Dig Endosc. 2016; 28: 526-533