Please use this identifier to cite or link to this item:
https://doi.org/10.1016/j.compbiomed.2007.09.003
DC Field | Value | |
---|---|---|
dc.title | Masseter segmentation using an improved watershed algorithm with unsupervised classification | |
dc.contributor.author | Ng, H.P. | |
dc.contributor.author | Ong, S.H. | |
dc.contributor.author | Foong, K.W.C. | |
dc.contributor.author | Goh, P.S. | |
dc.contributor.author | Nowinski, W.L. | |
dc.date.accessioned | 2014-06-17T02:56:16Z | |
dc.date.available | 2014-06-17T02:56:16Z | |
dc.date.issued | 2008-02 | |
dc.identifier.citation | Ng, 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.issn | 00104825 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/56585 | |
dc.description.abstract | The 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.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1016/j.compbiomed.2007.09.003 | |
dc.source | Scopus | |
dc.subject | Biomedical imaging | |
dc.subject | K-means clustering | |
dc.subject | Watershed segmentation | |
dc.type | Article | |
dc.contributor.department | PREVENTIVE DENTISTRY | |
dc.contributor.department | ELECTRICAL & COMPUTER ENGINEERING | |
dc.description.doi | 10.1016/j.compbiomed.2007.09.003 | |
dc.description.sourcetitle | Computers in Biology and Medicine | |
dc.description.volume | 38 | |
dc.description.issue | 2 | |
dc.description.page | 171-184 | |
dc.description.coden | CBMDA | |
dc.identifier.isiut | 000253408800003 | |
Appears in Collections: | Staff Publications |
Show simple item record
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.