Advertisement

Artificial intelligence for automatic diagnosis of biliary stricture malignancy status in single-operator cholangioscopy: a pilot study

  • Author Footnotes
    ∗ Drs Saraiva and Ribeiro contributed equally to this article.
    Miguel Mascarenhas Saraiva
    Correspondence
    Reprint requests: Miguel Mascarenhas Saraiva, CHUSJ: Centro Hospitalar Universitario de Sao Joao, Rua Oliveira Martins 104, Porto, Porto 4200-427, Portugal.
    Footnotes
    ∗ Drs Saraiva and Ribeiro contributed equally to this article.
    Affiliations
    Department of Gastroenterology, São João University Hospital, Porto, Portugal

    WGO Gastroenterology and Hepatology Training Center, Porto, Portugal

    Department of Gastroenterology, Faculty of Medicine, University of Porto, Porto, Portugal
    Search for articles by this author
  • Author Footnotes
    ∗ Drs Saraiva and Ribeiro contributed equally to this article.
    Tiago Ribeiro
    Footnotes
    ∗ Drs Saraiva and Ribeiro contributed equally to this article.
    Affiliations
    Department of Gastroenterology, São João University Hospital, Porto, Portugal

    WGO Gastroenterology and Hepatology Training Center, Porto, Portugal
    Search for articles by this author
  • João P.S. Ferreira
    Affiliations
    Department of Mechanical Engineering, Faculty of Engineering, University of Porto, Porto, Portugal
    Search for articles by this author
  • Filipe Vilas Boas
    Affiliations
    Department of Gastroenterology, São João University Hospital, Porto, Portugal

    WGO Gastroenterology and Hepatology Training Center, Porto, Portugal

    Department of Gastroenterology, Faculty of Medicine, University of Porto, Porto, Portugal
    Search for articles by this author
  • João Afonso
    Affiliations
    Department of Gastroenterology, São João University Hospital, Porto, Portugal

    WGO Gastroenterology and Hepatology Training Center, Porto, Portugal
    Search for articles by this author
  • Ana Luísa Santos
    Affiliations
    Department of Gastroenterology, São João University Hospital, Porto, Portugal

    WGO Gastroenterology and Hepatology Training Center, Porto, Portugal

    Department of Gastroenterology, Faculty of Medicine, University of Porto, Porto, Portugal
    Search for articles by this author
  • Marco P.L. Parente
    Affiliations
    Department of Mechanical Engineering, Faculty of Engineering, University of Porto, Porto, Portugal
    Search for articles by this author
  • Renato N. Jorge
    Affiliations
    Department of Mechanical Engineering, Faculty of Engineering, University of Porto, Porto, Portugal
    Search for articles by this author
  • Pedro Pereira
    Affiliations
    Department of Gastroenterology, São João University Hospital, Porto, Portugal

    WGO Gastroenterology and Hepatology Training Center, Porto, Portugal

    Department of Gastroenterology, Faculty of Medicine, University of Porto, Porto, Portugal
    Search for articles by this author
  • Guilherme Macedo
    Affiliations
    Department of Gastroenterology, São João University Hospital, Porto, Portugal

    WGO Gastroenterology and Hepatology Training Center, Porto, Portugal

    Department of Gastroenterology, Faculty of Medicine, University of Porto, Porto, Portugal
    Search for articles by this author
  • Author Footnotes
    ∗ Drs Saraiva and Ribeiro contributed equally to this article.
Published:September 07, 2021DOI:https://doi.org/10.1016/j.gie.2021.08.027

      Background and Aims

      The diagnosis and characterization of biliary strictures (BSs) is challenging. The introduction of digital single-operator cholangioscopy (DSOC) that allows direct visual inspection of the lesion and targeted biopsy sampling significantly improved the diagnostic yield in patients with indeterminate BSs. However, the diagnostic efficiency of DSOC remains suboptimal. Convolutional neural networks (CNNs) have shown great potential for the interpretation of medical images. We aimed to develop a CNN-based system for automatic detection of malignant BSs in DSOC images.

      Methods

      We developed, trained, and validated a CNN-based on DSOC images. Each frame was labeled as a normal/benign finding or as a malignant lesion if histopathologic evidence of biliary malignancy was available. The entire dataset was split for 5-fold cross-validation. In addition, the image dataset was split for constitution of training and validation datasets. The performance of the CNN was measured by calculating the area under the receiving operating characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive values.

      Results

      A total of 11,855 images from 85 patients were included (9695 malignant strictures and 2160 benign findings). The model had an overall accuracy of 94.9%, sensitivity of 94.7%, specificity of 92.1%, and AUC of .988 in cross-validation analysis. The image processing speed of the CNN was 7 ms per frame.

      Conclusions

      The developed deep learning algorithm accurately detected and differentiated malignant strictures from benign biliary conditions. The introduction of artificial intelligence algorithms to DSOC systems may significantly increase its diagnostic yield for malignant strictures.

      Graphical abstract

      Abbreviations:

      AI (artificial intelligence), AUC (area under the receiver operating characteristic curve), BS (biliary stricture), CI (confidence interval), CNN (convolutional neural network), DSOC (digital single-operator cholangioscopy)
      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:

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

      References

        • Larghi A.
        • Tringali A.
        • Lecca P.G.
        • et al.
        Management of hilar biliary strictures.
        Am J Gastroenterol. 2008; 103: 458-473
        • Tummala P.
        • Munigala S.
        • Eloubeidi M.A.
        • et al.
        Patients with obstructive jaundice and biliary stricture ± mass lesion on imaging: prevalence of malignancy and potential role of EUS-FNA.
        J Clin Gastroenterol. 2013; 47: 532-537
        • Paranandi B.
        • Oppong K.W.
        Biliary strictures: endoscopic assessment and management.
        Frontline Gastroenterol. 2017; 8: 133-137
        • Singhi A.D.
        • Slivka A.
        Evaluation of indeterminate biliary strictures: Is there life on MARS?.
        Gastrointest Endosc. 2020; 92: 320-322
        • Burnett A.S.
        • Calvert T.J.
        • Chokshi R.J.
        Sensitivity of endoscopic retrograde cholangiopancreatography standard cytology: 10-y review of the literature.
        J Surg Res. 2013; 184: 304-311
        • Navaneethan U.
        • Njei B.
        • Lourdusamy V.
        • et al.
        Comparative effectiveness of biliary brush cytology and intraductal biopsy for detection of malignant biliary strictures: a systematic review and meta-analysis.
        Gastrointest Endosc. 2015; 81: 168-176
        • Pereira P.
        • Vilas-Boas F.
        • Peixoto A.
        • et al.
        How SpyGlass™ may impact endoscopic retrograde cholangiopancreatography practice and patient management.
        GE Port J Gastroenterol. 2018; 25: 132-137
        • Gerges C.
        • Beyna T.
        • Tang R.S.Y.
        • et al.
        Digital single-operator peroral cholangioscopy-guided biopsy sampling versus ERCP-guided brushing for indeterminate biliary strictures: a prospective, randomized, multicenter trial (with video).
        Gastrointest Endosc. 2020; 91: 1105-1113
        • Jang S.
        • Stevens T.
        • Kou L.
        • et al.
        Efficacy of digital single-operator cholangioscopy and factors affecting its accuracy in the evaluation of indeterminate biliary stricture.
        Gastrointest Endosc. 2020; 91: 385-393
        • Sethi A.
        • Doukides T.
        • Sejpal D.V.
        • et al.
        Interobserver agreement for single operator choledochoscopy imaging: Can we do better?.
        Diagn Ther Endosc. 2014; 2014: 1-4
        • Gargeya R.
        • Leng T.
        Automated identification of diabetic retinopathy using deep learning.
        Ophthalmology. 2017; 124: 962-969
        • Esteva A.
        • Kuprel B.
        • Novoa R.A.
        • et al.
        Dermatologist-level classification of skin cancer with deep neural networks.
        Nature. 2017; 542: 115-118
        • Ding Z.
        • Shi H.
        • Zhang H.
        • et al.
        Gastroenterologist-level identification of small-bowel diseases and normal variants by capsule endoscopy using a deep-learning model.
        Gastroenterology. 2019; 157: 1044-1054
        • Hassan C.
        • Spadaccini M.
        • Iannone A.
        • et al.
        Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis.
        Gastrointest Endosc. 2021; 93: 77-85
        • Sethi A.
        • Tyberg A.
        • Slivka A.
        • et al.
        Digital single-operator cholangioscopy (DSOC) improves interobserver agreement (IOA) and accuracy for evaluation of indeterminate biliary strictures: the Monaco classification.
        J Clin Gastroenterol. Epub 2020 Feb 7;
        • Pedregosa F.
        • Varoquaux G.
        • Gramfort A.
        • et al.
        Scikit-learn: machine learning in Python.
        J Machine Learn Res. 2011; 12: 2825-2830
        • Le Berre C.
        • Sandborn W.J.
        • Aridhi S.
        • et al.
        Application of artificial intelligence to gastroenterology and hepatology.
        Gastroenterology. 2020; 158: 76-94
        • Marya N.B.
        • Powers P.D.
        • Chari S.T.
        • et al.
        Utilisation of artificial intelligence for the development of an EUS-convolutional neural network model trained to enhance the diagnosis of autoimmune pancreatitis.
        Gut. 2020; 70: 1335-1344
        • Săftoiu A.
        • Vilmann P.
        • Dietrich C.F.
        • et al.
        Quantitative contrast-enhanced harmonic EUS in differential diagnosis of focal pancreatic masses (with videos).
        Gastrointest Endosc. 2015; 82: 59-69
        • de Oliveira P.
        • de Moura D.T.H.
        • Ribeiro I.B.
        • et al.
        Efficacy of digital single-operator cholangioscopy in the visual interpretation of indeterminate biliary strictures: a systematic review and meta-analysis.
        Surg Endosc. 2020; 34: 3321-3329
        • Wen L.J.
        • Chen J.H.
        • Xu H.J.
        • et al.
        Efficacy and safety of digital single-operator cholangioscopy in the diagnosis of indeterminate biliary strictures by targeted biopsies: a systematic review and meta-analysis.
        Diagnostics (Basel). 2020; 10: 1-11
        • Navaneethan U.
        • Hasan M.K.
        • Kommaraju K.
        • et al.
        Digital, single-operator cholangiopancreatoscopy in the diagnosis and management of pancreatobiliary disorders: a multicenter clinical experience (with video).
        Gastrointest Endosc. 2016; 84: 649-655
        • Sun X.
        • Zhou Z.
        • Tian J.
        • et al.
        Is single-operator peroral cholangioscopy a useful tool for the diagnosis of indeterminate biliary lesion? A systematic review and meta-analysis.
        Gastrointest Endosc. 2015; 82: 79-87
        • Robles-Medranda C.
        • Oleas R.
        • Sánchez-Carriel M.
        • et al.
        Vascularity can distinguish neoplastic from non-neoplastic bile duct lesions during digital single-operator cholangioscopy.
        Gastrointest Endosc. 2021; 93: 935-941
        • Robles-Medranda C.
        • Valero M.
        • Soria-Alcivar M.
        • et al.
        Reliability and accuracy of a novel classification system using peroral cholangioscopy for the diagnosis of bile duct lesions.
        Endoscopy. 2018; 50: 1059-1070
        • Fukasawa Y.
        • Takano S.
        • Fukasawa M.
        • et al.
        Form-vessel classification of cholangioscopy findings to diagnose biliary tract carcinoma's superficial spread.
        Int J Mol Sci. 2020; 21: 1-13

      Linked Article

      • Generalizability challenges of a machine learning model for classification of indeterminate biliary strictures
        Gastrointestinal EndoscopyVol. 95Issue 6
        • Preview
          We have read with great interest the article by Saraiva et al,1 which developed a deep learning algorithm for the classification of malignant and benign biliary strictures with the use of cholangioscopy images. We also agree with the important role that artificial intelligence can play in improving the characterization of indeterminate biliary strictures.2 We would, however, appreciate some clarification regarding the methods used to develop the neural network, including the following:
        • Full-Text
        • PDF
      • Artificial intelligence–assisted cholangioscopy for automatic detection of malignant biliary strictures
        Gastrointestinal EndoscopyVol. 96Issue 6
        • Preview
          We read with great interest the article by Mascarenhas Saraiva et al1 regarding optimal diagnosis of malignant biliary strictures by using an artificial intelligence (AI) algorithm. We concur with their findings and agree that the introduction of AI algorithms such as convolutional neural network (CNN) imaging may significantly increase our diagnostic repertoire in dealing with patients who have suspected bile duct cancers. In addition, owing to the high accuracy of AI-assisted cholangioscopy, patients with highly suggestive lesions on cholangioscopy who are suitable for surgery may be able to proceed to early surgery before cancer progresses.
        • Full-Text
        • PDF