Advertisement

Artificial intelligence–assisted cholangioscopy for automatic detection of malignant biliary strictures

      To the Editor:
      We read with great interest the article by Mascarenhas Saraiva et al
      • Mascarenhas Saraiva M.
      • Ribeiro T.
      • Ferreira J.P.S.
      • et al.
      Artificial intelligence for automatic diagnosis of biliary strictures malignancy status in single-operator cholangioscopy: a pilot study.
      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.
      One of the major potential benefits of AI-assisted cholangioscopy is that a diagnosis may be made without further invasive testing such as biopsy and hence is likely to result in fewer procedure-associated adverse events.
      • Njei B.
      • McCarty T.R.
      • Varadarajulu S.
      • et al.
      Cost utility of ERCP-based modalities for the diagnosis of cholangiocarcinoma in primary sclerosing cholangitis.
      Although the potential of AI-assisted cholangioscopy is promising, it is critical to delineate some challenges. CNN algorithms require large datasets for validation, which are not readily available. As with any computer vision machine learning modality, addressing “overfitting” and bias are also important.
      • Goyal H.
      • Mann R.
      • Gandhi Z.
      • et al.
      Application of artificial intelligence in pancreaticobiliary diseases.
      It is key that we focus not only on algorithm performance but also on increasing the trustworthiness of the algorithms; and these AI-imaging applications should be able to help save diagnosis time.
      We predict a trajectory of increased use and adoption of AI-assisted cholangioscopy. AI-assisted cholangioscopy is likely to meet the test of pervasiveness, improvement, and innovation. The adoption of AI-assisted cholangioscopy will likely follow Amara’s law and the 5 stages of the hype cycle. We believe that we are still in the infant stages of this technology, and this phase may last 3 to 5 years before there is a peak of inflated expectation. The trough of disillusionment and slopes of enlightenment may only be observed in the next decades.

      Disclosure

      All authors disclosed no financial relationships.

      References

        • Mascarenhas Saraiva M.
        • Ribeiro T.
        • Ferreira J.P.S.
        • et al.
        Artificial intelligence for automatic diagnosis of biliary strictures malignancy status in single-operator cholangioscopy: a pilot study.
        Gastrointest Endosc. 2022; 95: 339-348
        • Njei B.
        • McCarty T.R.
        • Varadarajulu S.
        • et al.
        Cost utility of ERCP-based modalities for the diagnosis of cholangiocarcinoma in primary sclerosing cholangitis.
        Gastrointest Endosc. 2017; 85: 773-781.e10
        • Goyal H.
        • Mann R.
        • Gandhi Z.
        • et al.
        Application of artificial intelligence in pancreaticobiliary diseases.
        Ther Adv Gastrointest Endosc. 2021; 142631774521993059

      Linked Article

      • Artificial intelligence for automatic diagnosis of biliary stricture malignancy status in single-operator cholangioscopy: a pilot study
        Gastrointestinal EndoscopyVol. 95Issue 2
        • Preview
          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.
        • Full-Text
        • PDF
      • Caution should be exercised in denying the protective effect of clip closure on post-EMR perforation of a proximal large nonpedunculated colorectal polyp
        Gastrointestinal EndoscopyVol. 96Issue 6
        • Preview
          We read with great interest the article by Forbes et al1 entitled “Clip closure to prevent adverse events following endoscopic mucosal resection of proximal large non-pedunculated colorectal polyps: meta-analysis of individual patient data from randomized controlled trials.” By representing 1248 patients with proximal large nonpedunculated colorectal polyps (LNPCPs) from 4 randomized controlled trials, the authors concluded that preventive clipping could effectively prevent the bleeding after EMR of proximal LNPCPs.
        • Full-Text
        • PDF
      • Response
        Gastrointestinal EndoscopyVol. 96Issue 6
        • Preview
          We are honored by the interest of Njei et al1 in our proof-of-concept work.2 We share their view of a potential role of artificial intelligence (AI) for significantly enhancing the diagnostic yield of digital cholangioscopy for malignant biliary strictures. In our view, the application of AI to cholangioscopy will, at this stage, work alongside current criterion standard techniques, as a complement rather than disrupting the current standard of care. Therefore, although we agree with Njei et al1 that AI-assisted cholangioscopy should ultimately achieve diagnosis without more invasive techniques, we believe that in the near future AI will be applied to increase the yield of current techniques, particularly cholangioscopy-guided biopsies, which remain the current criterion standard.
        • Full-Text
        • PDF