Using deep learning for robustness to parapapillary atrophy in optic disc segmentation

Using deep learning for robustness to parapapillary atrophy in optic disc segmentation
Title:
Using deep learning for robustness to parapapillary atrophy in optic disc segmentation
Other Titles:
2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)
DOI:
10.1109/ISBI.2015.7163985
Publication Date:
19 April 2015
Citation:
Srivastava, R.; Jun Cheng; Wong, D.W.K.; Jiang Liu, "Using deep learning for robustness to parapapillary atrophy in optic disc segmentation," in Biomedical Imaging (ISBI), 2015 IEEE 12th International Symposium on , vol., no., pp.768-771, 16-19 April 2015.
Abstract:
Optic Disc (OD) segmentation from retinal fundus images is important for many applications such as detecting other optic structures and early detection of glaucoma. One of the major problems in segmenting OD is the presence of Para-papillary Atrophy (PPA) which in many cases looks similar to the OD. Researchers have used many different features to distinguish between PPA and OD, however each of these features has some limitation or the other. In this paper, we propose to use a deep neural network for OD segmentation which can learn features to distinguish PPA from OD. Using simple image intensity based features, the proposed method has the least mean overlapping error (9.7%) among the state-of-the-art works for OD segmentation in fundus images with PPA.
License type:
PublisherCopyrights
Funding Info:
Description:
ISSN:
1945-7928
1945-8452
Files uploaded: