Automated, real time extraction of fundus images from slit lamp fundus biomicroscope video image sequences

Aims-Slit lamp fundus biomicroscopy allows for high magnification, stereosc opic diagnosis, and treatment of macular diseases. Variable contrast, narro w field of view, and specular reflections arising from the cornea, sclera, and examining lens reduce image quality; these images are of limited clinic al utility for diagnosis, treatment planning, and photodocumentation when c ompared with fundus camera images. Algorithms are being developed to se,ame nt fundus imagery from slit lamp biomicroscopic video image sequences in or der to improve clinical utility. Methods-Video fundus image sequences of human volunteers were acquired with a video equipped, Nikon NS-1V slit lamp biomicroscope. Custom developed so ftware identified specular reflections based on brightness and colour conte nt, and extracted the illuminated fundus image based on colour image analys is and size constraints. Results-In five subjects with variable image quality, the approach allowed for automatic, robust, accurate extraction of that portion of the video ima ge corresponding to the illuminated portion of the fundus. Non-real time an alysis allowed for fundus image segmentation for each frame of the image se quence. In real time, segmentation occurs at 2 Hz, and improvements are bei ng implemented for video rate performance. Conclusions-Computer vision algorithms allow for real time extraction of fu ndus imagery from marginal quality, slit lamp fundus biomicroscope image se quences.