Automated detection of suspected glaucoma in digital fundus images

A method is proposed using image processing techniques, which is an automated method for detection of suspected glaucoma. In this paper an algorithm is proposed to detect suspected glaucoma by using the presence or absence of hemorrhages in a particular region, near the optic disc, in fundus image. Unlike existing methods, which only uses cup to disc ratio as a deciding parameter to detect glaucoma, method proposed in this paper helps to diagnose the case of suspected glaucoma efficiently. The optic disc and hemorrhages are segmented in a particular region automatically by using adaptive thresholding and some geometrical features. In existing methods, the majority of work is based on diagnosis of glaucoma, but rarely on suspected glaucoma. So, the proposed method can helpful to diagnose the cases of suspected glaucoma. The proposed algorithm achieves accuracy of 93.57% on digital fundus images for detection of suspected glaucoma.