STTR Phase I:Video Analysis Techniques for Computer-Aided Quality Control for Colonoscopy

This Small Business Technology Transfer Phase I project will develop algorithms for a quality control system for colonoscopy (a procedure where the mucosa of the large bowel is inspected via a flexible tube with a camera on it) that has contributed to a marked decline in the number of colorectal cancer related deaths. However, recent data suggest that there is a significant miss-rate for the detection of even large polyps and cancers. Anticipated results of this research are: (1) algorithms for colonoscopy to determine whether the beginning of the large bowel was reached; (2) algorithms for detecting the appearance of the appendiceal orifice as the appendix is located at the beginning of the colon, its detection confirms that the entire colon has been traversed; and (3) software tools to derive quality measurements. The broader impacts of this research are that it will enable automated, objective quality control for colonoscopy in large-scale, day-to-day medical settings, which is currently not feasible. This has the potential to benefit the health of millions of people each year. If successful it will initiate new research and development in quaity control for other endoscopic procedures such as bronchoscopy, cystoscopy, and laparoscopy. The project will contribute to medical education, research, and practice by providing videos containing all aspects of typical colonoscopy practice and corresponding quality measurements that can be used for teaching and training of new endoscopists and recertification of previously certified endoscopists.