Research Project
7747155
DESCRIPTION (provided by applicant): Diseases of the small intestine affect nearly 19 million Americans. Care for these patients has been hindered due to the inability to non-invasively image the small intestine. In the past several years, capsule endoscopy (a pill-shaped wireless swallow-able imager) has revolutionized the non- invasive visual imaging of the small intestine. However it has limitations, including lengthy image review times and poor localization of pathology, which is important for surgical guidance. This has a significant impact on the clinical care of patients. During our Phase I study, Intelligent Image Feature Matching for Small Intestine Capsule Endoscopy, we demonstrated the underlying capabilities necessary to match and spatially index capsule images. Based on these positive results, we now propose to develop a new system for capsule reading that makes strong use of spatial indexing to allow a more effective and intuitive sequencing of capsule images, and image content control as a way of filtering the class of images presented to the user. These capabilities will enhance clinical efficiency while preserving diagnostic sensitivity. They also offer a mechanism to spatially map the small intestine to facilitate lesion localization. We further propose to evaluate the efficacy of this system in a retrospective human study to demonstrate that sensitivity and specificity of detection with our Spatial Navigation System, as compared to existing capsule image browsers, are not substantially reduced, while the time required to diagnose patients is decreased. This reduction in review time with little or no reduction in diagnostic yield, plus an increased ability to localize lesions for surgical treatment, will produce a substantial reduction of the total costs for capsule endoscopy procedures while improving patient care. PUBLIC HEALTH RELEVANCE: Capsule endoscopy for the first time has enabled non-invasive visual imaging of the distal small intestinal mucosa. However, it is hindered by time-consuming manual reviews and an inability to localize lesions. Our proposed software technology will provide gastroenterologists with a quick and efficient tool to review capsule endoscopy data.
