Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.compbiomed.2007.09.003
DC FieldValue
dc.titleMasseter segmentation using an improved watershed algorithm with unsupervised classification
dc.contributor.authorNg, H.P.
dc.contributor.authorOng, S.H.
dc.contributor.authorFoong, K.W.C.
dc.contributor.authorGoh, P.S.
dc.contributor.authorNowinski, W.L.
dc.date.accessioned2014-06-17T02:56:16Z
dc.date.available2014-06-17T02:56:16Z
dc.date.issued2008-02
dc.identifier.citationNg, H.P., Ong, S.H., Foong, K.W.C., Goh, P.S., Nowinski, W.L. (2008-02). Masseter segmentation using an improved watershed algorithm with unsupervised classification. Computers in Biology and Medicine 38 (2) : 171-184. ScholarBank@NUS Repository. https://doi.org/10.1016/j.compbiomed.2007.09.003
dc.identifier.issn00104825
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/56585
dc.description.abstractThe watershed algorithm always produces a complete division of the image. However, it is susceptible to over-segmentation and sensitivity to false edges. In medical images this leads to unfavorable representations of the anatomy. We address these drawbacks by introducing automated thresholding and post-segmentation merging. The automated thresholding step is based on the histogram of the gradient magnitude map while post-segmentation merging is based on a criterion which measures the similarity in intensity values between two neighboring partitions. Our improved watershed algorithm is able to merge more than 90% of the initial partitions, which indicates that a large amount of over-segmentation has been reduced. To further improve the segmentation results, we make use of K-means clustering to provide an initial coarse segmentation of the highly textured image before the improved watershed algorithm is applied to it. When applied to the segmentation of the masseter from 60 magnetic resonance images of 10 subjects, the proposed algorithm achieved an overlap index (κ) of 90.6%, and was able to merge 98% of the initial partitions on average. The segmentation results are comparable to those obtained using the gradient vector flow snake. © 2007 Elsevier Ltd. All rights reserved.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1016/j.compbiomed.2007.09.003
dc.sourceScopus
dc.subjectBiomedical imaging
dc.subjectK-means clustering
dc.subjectWatershed segmentation
dc.typeArticle
dc.contributor.departmentPREVENTIVE DENTISTRY
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1016/j.compbiomed.2007.09.003
dc.description.sourcetitleComputers in Biology and Medicine
dc.description.volume38
dc.description.issue2
dc.description.page171-184
dc.description.codenCBMDA
dc.identifier.isiut000253408800003
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

26
checked on Sep 19, 2020

WEB OF SCIENCETM
Citations

18
checked on Sep 11, 2020

Page view(s)

90
checked on Sep 14, 2020

Google ScholarTM

Check

Altmetric


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