A Fast, Automatic System for Detecting Flat Polyps in Colonoscopy Video

AbstractColorectal cancer is the second most common cause of cancer death in the United Stateswith an estimatednew cases leading todeaths this yearThe best treatment is to detect and treat the cancer before it becomes invasive and spreadsThe most common form of detection is the use of optical colonoscopy in which the clinician visually inspects the surface of the colon through an endoscope to detect the presence of polypsStudies have shown that even the best clinicians will sometimes miss polypsespecially the more subtle flat polypsand that many cancers that develop in the years immediately following a colonoscopy likely originate from missed polypsMany approaches have been used to attempt to improve polyp miss rates but have yielded little to no benefitWe propose to develop an approach for automatically detecting the presence of flat polyps during a colonoscopy procedure to reduce the rate of missed polyps in colonoscopyThis project is a close collaboration between KitwareIncand the University of North Carolina at Chapel HillUNCKitware is scientific computing company known for creating high quality open source software and our co investigators from UNC bring a long history of medical image analysis and clinical experienceThe proposal team has done preliminary work on developing features for detecting polyps and has a strong history of collaborationIn this projectwe propose to combine the UNC teamandapos s expertise with Kitwareandapos s algorithm implementation and software development experience to create the foundation for a system that can be used to automatically detect the presence of flat polyps in colonoscopy video to allow the clinician to return to the site of the polyp and remove it if it was originally missedThe specific aims of the proposed project are toadevelop and evaluate a set of features that can be used to detect the presence of flat polyps during colonoscopy andbaccelerate the computation of these features to be useful in a clinical scenarioThe successful completion of this work will yield a proven set of features and an implementation that will form the basis of an automatic polyp detection system Project NarrativeColorectal cancer is the second most common cause of cancer death in the United Stateswith an estimatednew cases leading todeaths this yearThe best treatment is to detect and treat the cancer before it becomes invasive by removing polyps during a colonoscopybut studies have shown that even the best clinicians will miss polypsIn this projectwe propose to develop a system to automatically detect the more commonly missed flat polyps during a colonoscopy procedure to enable the clinician to return to a polyp and remove it if it was overlooked