Deep-Learning for Automatic Polyp Detection During Colonoscopy

Completed · Not applicable

Conditions studied: Screening Colonoscopy

In brief

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.

Key facts

Study ID

NCT03637712

Run by

NYU Langone Health

People needed

5

Starts

2018-09-01

Expected to finish

2019-07-07

Last updated by the study team

2020-05-15

Who can join

Age: 18 and older, up to 99. Sex: any. Healthy volunteers: not accepted.

You may qualify if…

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

You may not qualify if…

• 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.

Where it is running

• NYU Langone Health — New York, New York, United States

Full record on ClinicalTrials.gov

Trial information comes from ClinicalTrials.gov and is refreshed daily. TrialsForMe does not provide medical care and does not run the studies it lists.