Abstract
Purpose: :
To automatically earmark changes on a time sequence of color fundus photographs and to allow the follow-up of individual retinal changes selected manually.
Methods: :
Color fundus photographs (30º fov and 1594 x 1326 pixels) were taken every 6 months during a period of 2 years from 52 eyes from 52 patients and converted to gray-scale through Principal Component Analysis (PCA). This gray-scale image was then processed automatically so as to correct for non-uniform illumination, thus improving contrast and brightness. The retinal vascular tree was then determined in order to register the set of images, thus making it possible to compute the differences of each image to the baseline image. A color scheme was implemented to allow identification on a given instance of the sequence where the changes are coming from by giving a specific coloration to each visit. The computed changes can be mapped to any visit, showing their evolution over time. Any area can be individually followed regarding its size and/or shape.
Results: :
A fully automated procedure was developed to allow mapping of the changes detected over a time-sequence of color fundus images. Drusen size, drusen confluence indicating drusen turnover and other retinal changes were identified in the image-differences.
Conclusions: :
Changes automatically detected in color fundus images were successfully earmarked, despite different image conditions. The developed color scheme allows identification of the location, on the time-sequence, of the earmarked changes, as well as the areas where previous changes return to baseline status.
Keywords: age-related macular degeneration • imaging/image analysis: clinical • image processing