The purpose of this project is to examine the role of machine learning and computer aided diagnostics in automatic polyp detection and to determine in real-time how a computer-aided detection (CADe) algorithm will perform when compared to standard screening or surveillance colonoscopy alone. Design will be a multi-center, prospective, unblinded randomized tandem colonoscopy study. 196 patients referred for either screening or surveillance colonoscopy will be included.

Inclusion Criteria:

• Patients presenting to the endoscopy unit for a screening colonoscopy or a surveillance colonoscopy
• Willingness to undergo tandem colonscopies with and without the use of computer-aided software while undergoing conventional colonoscopy with sedation
• Ability to provide written, informed consent (approved by IRB) and understand the responsibilities of trial participation

Exclusion Criteria:

• People with diminished cognitive capacity
• 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 referred for endoscopic mucosal resection (EMR)