Please use this identifier to cite or link to this item: https://idr.l1.nitk.ac.in/jspui/handle/123456789/7422
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGirish, G.N.
dc.contributor.authorKothari, A.R.
dc.contributor.authorRajan, J.
dc.date.accessioned2020-03-30T09:59:04Z-
dc.date.available2020-03-30T09:59:04Z-
dc.date.issued2016
dc.identifier.citationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016, Vol.2016-October, , pp.1292-1295en_US
dc.identifier.urihttp://idr.nitk.ac.in/jspui/handle/123456789/7422-
dc.description.abstractOptical Coherence Tomography (OCT) has emerged as a major diagnostic modality for retinal imaging. Although OCT generates gross volumetric data, manual analysis of the images for locating or quantifying retinal cysts is a time consuming process. Recently semi- and fully-automatic methods for locating and segmenting retinal cysts have been proposed in the literature. Our paper proposes a fully automatic method for intra-retinal cyst segmentation using marker controlled watershed transform on B-scan images obtained on OCT scanning. Markers are obtained using k-means clustering and used as sources for topographical based watershed transform for final segmentation. Proposed method was evaluated both quantitatively and qualitatively on Optima Cyst Challenge dataset against ground truth obtained from two graders. Experimental results show that the proposed method outperformed other recently proposed methods. Our algorithm achieved a recall rate of 82% while preserving precision rate of 77%, and gave a higher correlation rate of 96% with ground truth obtained from two graders. � 2016 IEEE.en_US
dc.titleAutomated segmentation of intra-retinal cysts from optical coherence tomography scans using marker controlled watershed transformen_US
dc.typeBook chapteren_US
Appears in Collections:2. Conference Papers

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.