AUTOMATIC DETECTION AND SEGMENTATION OF OPTIC DISC IN RETINAL IMAGES

Reliable and efficient Optic Disc (OD) localization and segmentation are important tasks in automatic eye disease screening. The Optic Disc (OD) center and margin are typically essential landmarks in establishing a frame of reference for classifying retinal and optic nerve pathology. This project presents a fast and automatic Optic Disc localization and segmentation algorithm developed for retinal disease screening. Morphological filtering is used to remove blood vessels and bright regions other than the Optic Disc from a retinal image. Experimentation was performed on 100 images from the publicly available MESSIDOR database. The OD location methodology succeeded in 78 out of 100 images (78% success). Its efficiency, robustness and accuracy make the OD localization and segmentation scheme described herein suitable for automatic retinal disease screening in a variety of clinical settings. By detecting eye disease early through automated screening algorithms, treatment would become more effective and significant savings in health care costs could be realized.