Deep-Learning for Automatic Polyp Detection During Colonoscopy

Deep-Learning for Automatic Polyp Detection During Colonoscopy

The primary objective of this study is to examine the role of machine learning and computer aided diagnostics in automatic polyp detection and to determine whether a combination of colonoscopy and an automatic polyp detection software is a feasible way to increase adenoma detection rate compared to standard colonoscopy.

Inclusion Criteria:

• Patients presenting for routine colonoscopy for screening and/or surveillance purposes.
• Ability to provide written, informed consent and understand the responsibilities of trial participation

Exclusion Criteria:

• People with diminished cognitive capacity.
• The subject is pregnant or planning a pregnancy during the study period.
• Patients undergoing diagnostic colonoscopy (e.g. as an evaluation for active GI bleed)
• Patients with incomplete colonoscopies (those where endoscopists did not successfully intubate the cecum due to technical difficulties or poor bowel preparation)
• Patients that have standard contraindications to colonoscopy in general (e.g. documented acute diverticulitis, fulminant colitis and known or suspected perforation).
• Patients with inflammatory bowel disease
• Patients with any polypoid/ulcerated lesion > 20mm concerning for invasive cancer on endoscopy.