DocumentCode :
3238052
Title :
A field of experts model for optic cup and disc segmentation from retinal fundus images
Author :
Mahapatra, Dwarikanath ; Buhmann, Joachim M.
Author_Institution :
Dept. of Comput. Sci., ETH Zurich, Zurich, Switzerland
fYear :
2015
fDate :
16-19 April 2015
Firstpage :
218
Lastpage :
221
Abstract :
We present a Field of Experts (FoE) model to segment the optic cup and disc from retinal fundus images. FoE learns a prior model of the cup and neuro-retinal rim region in the form of filters, without relying on hand crafted features. FoE filter responses are integrated into a Random forest (RF) classifier that outputs probability maps for the test image and finally segments the cup and rim. Experimental results show our method achieves significantly better performance than current state-of-the-art.
Keywords :
eye; image segmentation; medical image processing; probability; FoE; disc segmentation; experts model; optic cup; probability maps; random forest classifier; retinal fundus images; Adaptive optics; Biomedical optical imaging; Image segmentation; Optical imaging; Radio frequency; Retina; Training; CDR; Field of Experts; glaucoma; optic cup; optic disc; segmentation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging (ISBI), 2015 IEEE 12th International Symposium on
Conference_Location :
New York, NY
Type :
conf
DOI :
10.1109/ISBI.2015.7163853
Filename :
7163853
Link To Document :
بازگشت