Motion pattern-based image features for glaucoma detection from retinal images

Glaucoma is an eye disorder that causes irreversible loss of vision and is prevalent in the aging population. Glaucoma is indicated both by structural changes and presence of atrophy in retina. In retinal images, these appear in the form of subtle variation of local intensities. These variations are typically described using local shape based statistics which are prone to error. We propose an automated, global feature based approach to detect glaucoma from images. An image representation is devised to accentuate subtle indicators of the disease such that global image features can discriminate between normal and glaucoma cases effectively. The proposed method is demonstrated on a large image dataset annotated by 3 medical experts. The results show the method to be effective in detecting subtle glaucoma indicators. The classification performance on a dataset of 1186 color retinal images containing a mixture of normal, suspect and confirmed cases of glaucoma is 97 percent sensitivity at 87 percent specificity. This improves further when the suspect cases are removed from the abnormal cases. Thus, the proposed method offers a good solution for glaucoma screening from retinal images.