J W Berger1, B Madjarov. 1. Computer Vision Laboratory, Scheie Eye Institute, University of Pennsylvania, 51 N 39th St, Philadelphia, PA 19104, USA.
Abstract
BACKGROUND: To guide treatment for macular diseases and to facilitate real-time image correlation, measurement, and comparison, we developed a method for direct overlay of previously stored photographic and angiographic images onto the real-time slitlamp fundus view. METHODS: Previously acquired fundus photographs and angiography images were digitized. A slitlamp interfaced to a charge-coupled device camera, framegrabber, and computer allowed for real-time acquisition and digitization of slitlamp fundus images that was synchronous with posterior segment examination. Custom-developed video injectors containing a miniature cathode ray tube display allowed for real-time superposition of angiographic images to the fundus view. Registration and tracking algorithms were developed and deployed in C++. The feasibility of this approach was demonstrated in 5 human subjects. RESULTS: The computer-vision algorithms provided robust registration, tracking, and image overlay of previously stored photographic and angiographic images directly onto the real-time fundus view. Accurate tracking was demonstrated with updates at 3 to 5 Hz. Direct overlay of previously stored images confirmed registration accuracy, but examiners preferred a more simple rendering that included only relevant information and eliminated extraneous, potentially confusing image data. CONCLUSIONS: Slitlamp-based video injection of previously stored images allows for accurate, robust, real-time correlation and comparison to the biomicroscopic fundus view in human subjects.
BACKGROUND: To guide treatment for macular diseases and to facilitate real-time image correlation, measurement, and comparison, we developed a method for direct overlay of previously stored photographic and angiographic images onto the real-time slitlamp fundus view. METHODS: Previously acquired fundus photographs and angiography images were digitized. A slitlamp interfaced to a charge-coupled device camera, framegrabber, and computer allowed for real-time acquisition and digitization of slitlamp fundus images that was synchronous with posterior segment examination. Custom-developed video injectors containing a miniature cathode ray tube display allowed for real-time superposition of angiographic images to the fundus view. Registration and tracking algorithms were developed and deployed in C++. The feasibility of this approach was demonstrated in 5 human subjects. RESULTS: The computer-vision algorithms provided robust registration, tracking, and image overlay of previously stored photographic and angiographic images directly onto the real-time fundus view. Accurate tracking was demonstrated with updates at 3 to 5 Hz. Direct overlay of previously stored images confirmed registration accuracy, but examiners preferred a more simple rendering that included only relevant information and eliminated extraneous, potentially confusing image data. CONCLUSIONS: Slitlamp-based video injection of previously stored images allows for accurate, robust, real-time correlation and comparison to the biomicroscopic fundus view in human subjects.