DocumentCode :
1564543
Title :
Optic Nerve Head Segmentation in HRT Images
Author :
Yang, Xu ; Morrow, Philip ; Scotney, B.
Author_Institution :
Sch. of Comput. & Inf. Eng., Ulster Univ., UK
fYear :
2006
Firstpage :
65
Lastpage :
68
Abstract :
Accurate segmentation of the optic nerve head (or optic disk) is very useful during the analysis and assessment of glaucoma in the eye. The Heidelberg retinal tomograph (HRT) can acquire high quality images of the optic disk and also allows three dimensional topographic measurements to be made. However, there are significant problems in optic disk segmentation due to having to deal with issues such as distractors along blood vessel edges; the extent of pallor in the optic disk or the very variable appearance of the optic nerve head itself. We propose a multi-scale region and boundary hybrid snake method to extract the optic disk. This model takes account of the vessel edge gradient direction and tries to avoid its force influence when evolving the snake. Experimental results are assessed using an overlap ratio.
Keywords :
biomedical optical imaging; blood vessels; boundary-elements methods; diseases; edge detection; endoscopes; eye; feature extraction; image segmentation; laser applications in medicine; medical image processing; splines (mathematics); B-spline model; Heidelberg retinal tomograph; blood vessel edge gradient direction; boundary hybrid snake method; confocal scanning laser ophthalmoscopy; glaucoma assessment; image quality; multiscale region; optic disk extraction; optic nerve head segmentation; three-dimensional topographic measurements; Biomedical imaging; Biomedical optical imaging; Blood vessels; Head; Image segmentation; Optical filters; Pixel; Reflectivity; Retina; Surfaces; Biomedical imaging; Image segmentation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing, 2006 IEEE International Conference on
Conference_Location :
Atlanta, GA
ISSN :
1522-4880
Print_ISBN :
1-4244-0480-0
Type :
conf
DOI :
10.1109/ICIP.2006.312358
Filename :
4106467
Link To Document :
بازگشت