Advertisement

Challenge to the “impossible”

      A Dutch research team engaged in the national colorectal cancer screening program published an “amazing” result in 2020.
      • Vleugels J.L.A.
      • Koens L.
      • Dijkgraaf M.G.W.
      • et al.
      Suboptimal endoscopic cancer recognition in colorectal lesions in a national bowel screening programme.
      As many as 60% of T1 (submucosally invasive) colorectal cancers detected during the program were misdiagnosed as adenomas by the on-site endoscopists and thus could be susceptible to inappropriate treatment intervention. Is this surprisingly low sensitivity for cancer recognition (40% in this case) reality? We would say yes, although many retrospective studies assessing advanced endoscopic modalities have suggested >90% sensitivities in predicting T1 cancers. We should seriously handle this matter because the Dutch data come from a very reliable real-world source but not from retrospective analyses of endoscopic diagnoses done exclusively by experts. Now in 2021, when we have narrow-band imaging, magnifying endoscopy, and even in-vivo microscopical imaging, we should still acknowledge that accurate recognition of T1 cancer is much more challenging than we thought. Furthermore, recognition of T1 cancer is getting more clinically relevant, given that many nations have implemented public colorectal cancer screening programs. A decent proportion (30% to 40%) of colorectal cancers found during such screening programs are actually T1 cancers.
      • Vleugels J.L.A.
      • Koens L.
      • Dijkgraaf M.G.W.
      • et al.
      Suboptimal endoscopic cancer recognition in colorectal lesions in a national bowel screening programme.
      ,
      • Amri R.
      • Bordeianou L.G.
      • Sylla P.
      • et al.
      Impact of screening colonoscopy on outcomes in colon cancer surgery.
      T1 colorectal cancers are not only challenging in terms of their optical diagnosis but also very common in terms of prevalence. Therefore, research on T1 colorectal cancers is attracting increasing attention in the endoscopy field.

      Abbreviation:

      AI (artificial intelligence)
      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

        • Vleugels J.L.A.
        • Koens L.
        • Dijkgraaf M.G.W.
        • et al.
        Suboptimal endoscopic cancer recognition in colorectal lesions in a national bowel screening programme.
        Gut. 2020; 69: 977-980
        • Amri R.
        • Bordeianou L.G.
        • Sylla P.
        • et al.
        Impact of screening colonoscopy on outcomes in colon cancer surgery.
        JAMA Surg. 2013; 148: 747-754
        • Luo X.
        • Wang J.
        • Han Z.
        • et al.
        Artificial intelligence−enhanced white-light colonoscopy with attention guidance predicts colorectal cancer invasion depth.
        Gastrointest Endosc. 2021; 94: 627-638.e1
        • Takeda K.
        • Kudo S.
        • Mori Y.
        • et al.
        Accuracy of diagnosing invasie colorectal cancer using computer-aided endocytoscopy.
        Endoscopy. 2017; 49: 798-802
        • Tokunaga M.
        • Matsumura T.
        • Nankinzan R.
        • et al.
        Computer-aided diagnosis system using only white-light endoscopy for the prediction of invasion depth in colorectal cancer.
        Gastrointest Endosc. 2021; 93: 647-653
      1. Beede E, Baylor E, Hersch F, et al. A human-centered evaluation of a deep learning system deployed in clinics for the detection of diabetic retinopathy. Proceedings of the 2020 CHI conference on human factors in computing systems, 2020.

      Linked Article