Automated Feature Extraction in Color Retinal Images by a Model Based Approach

TLDR

Color retinal photography is a key tool for detecting various eye diseases. This paper develops novel methods to extract main features from color retinal images. The authors use principal component analysis to locate the optic disk, a modified active shape model for its boundary, a fundus coordinate system for feature description, and a combined region‑growing and edge‑detection approach to detect exudates. The proposed algorithms achieve 99 % optic disk localization, 94 % boundary detection, 100 % fovea localization, 100 % exudate sensitivity and 71 % specificity, demonstrating that model‑based methods enable accurate detection suitable for automatic retinal disease screening.

Abstract

Color retinal photography is an important tool to detect the evidence of various eye diseases. Novel methods to extract the main features in color retinal images have been developed in this paper. Principal component analysis is employed to locate optic disk; A modified active shape model is proposed in the shape detection of optic disk; A fundus coordinate system is established to provide a better description of the features in the retinal images; An approach to detect exudates by the combined region growing and edge detection is proposed. The success rates of disk localization, disk boundary detection, and fovea localization are 99%, 94%, and 100%, respectively. The sensitivity and specificity of exudate detection are 100% and 71%, correspondingly. The success of the proposed algorithms can be attributed to the utilization of the model-based methods. The detection and analysis could be applied to automatic mass screening and diagnosis of the retinal diseases.