Title :
Automated localisation of optic disk and fovea in retinal fundus images
Author :
Sekhar, S. ; Al-Nuaimy, W. ; Nandi, A.K.
Author_Institution :
Dept. of Electr. Eng. & Electron., Univ. of Liverpool, Liverpool, UK
Abstract :
The retinal fundus photograph is widely used in the diagnosis and treatment of various eye diseases such as diabetic retinopathy and glaucoma. Medical image analysis and processing has great significance in the field of medicine, especially in non-invasive treatment and clinical study. Normally fundus images are manually graded by specially trained clinicians in a time-consuming and resource intensive process. A computer-aided fundus image analysis could provide an immediate detection and characterisation of retinal features prior to specialist inspection. This paper describes a novel method to automatically localise both the optic disk and the fovea. The optic disk is localised by means of using the morphological operations and by using the Hough transform. The fovea is localised by means of its spatial relationship with the optic disk, and from the spatial distribution of the macula lutea. Results from two clinical data sets have been promising.
Keywords :
Hough transforms; biomedical optical imaging; diseases; eye; medical image processing; photography; Hough transform; automated localisation; clinical data sets; clinical treatment; computer-aided fundus image analysis; diabetic retinopathy; eye diseases diagnosis; eye diseases treatment; glaucoma; localised fovea; macula lutea; medical image analysis; medical image processing; morphological operations; noninvasive treatment; optic disk; resource intensive process; retinal features; retinal fundus images; retinal fundus photograph; spatial distribution; specially trained clinicians; Adaptive optics; Biomedical optical imaging; Optical filters; Optical imaging; Optical sensors; Optical signal processing; Retina;
Conference_Titel :
Signal Processing Conference, 2008 16th European
Conference_Location :
Lausanne