Su1614 Artificial Intelligence (AI) in Endoscopy--Deep Learning for Optical Biopsy of Colorectal Polyps in Real-Time on Unaltered Endoscopic Videos

      ASGE-PIVI supports a “resect and discard” strategy for diminutive colon polyps, provided that any technology for optical biopsy depicts 90% agreement in assignment of post-polypectomy surveillance intervals and provides 90% negative predictive value for adenomatous histology. Such standards with optical biopsy are very difficult to achieve in general GI practice. Several groups have looked at supporting the process of optical biopsy in this field using traditional machine learning, but there are significant limitations in terms of (1) using still images only, and non-realtime computer support, and (2) involving very high magnification endoscopy.
      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