Spectral clustering for TRUS images
<p>Abstract</p> <p>Background</p> <p>Identifying the location and the volume of the prostate is important for ultrasound-guided prostate brachytherapy. Prostate volume is also important for prostate cancer diagnosis. Manual outlining of the prostate border is able to de...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2007-03-01
|
| Series: | BioMedical Engineering OnLine |
| Online Access: | http://www.biomedical-engineering-online.com/content/6/1/10 |
| _version_ | 1818346356886994944 |
|---|---|
| author | Salama Magdy MA Mohamed Samar S |
| author_facet | Salama Magdy MA Mohamed Samar S |
| author_sort | Salama Magdy MA |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>Identifying the location and the volume of the prostate is important for ultrasound-guided prostate brachytherapy. Prostate volume is also important for prostate cancer diagnosis. Manual outlining of the prostate border is able to determine the prostate volume accurately, however, it is time consuming and tedious. Therefore, a number of investigations have been devoted to designing algorithms that are suitable for segmenting the prostate boundary in ultrasound images. The most popular method is the deformable model (snakes), a method that involves designing an energy function and then optimizing this function. The snakes algorithm usually requires either an initial contour or some points on the prostate boundary to be estimated close enough to the original boundary which is considered a drawback to this powerful method.</p> <p>Methods</p> <p>The proposed spectral clustering segmentation algorithm is built on a totally different foundation that doesn't involve any function design or optimization. It also doesn't need any contour or any points on the boundary to be estimated. The proposed algorithm depends mainly on graph theory techniques.</p> <p>Results</p> <p>Spectral clustering is used in this paper for both prostate gland segmentation from the background and internal gland segmentation. The obtained segmented images were compared to the expert radiologist segmented images. The proposed algorithm obtained excellent gland segmentation results with 93% average overlap areas. It is also able to internally segment the gland where the segmentation showed consistency with the cancerous regions identified by the expert radiologist.</p> <p>Conclusion</p> <p>The proposed spectral clustering segmentation algorithm obtained fast excellent estimates that can give rough prostate volume and location as well as internal gland segmentation without any user interaction.</p> |
| first_indexed | 2024-12-13T17:16:58Z |
| format | Article |
| id | doaj.art-6adea2b82db1494296d01de954b2aeca |
| institution | Directory Open Access Journal |
| issn | 1475-925X |
| language | English |
| last_indexed | 2024-12-13T17:16:58Z |
| publishDate | 2007-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BioMedical Engineering OnLine |
| spelling | doaj.art-6adea2b82db1494296d01de954b2aeca2022-12-21T23:37:25ZengBMCBioMedical Engineering OnLine1475-925X2007-03-01611010.1186/1475-925X-6-10Spectral clustering for TRUS imagesSalama Magdy MAMohamed Samar S<p>Abstract</p> <p>Background</p> <p>Identifying the location and the volume of the prostate is important for ultrasound-guided prostate brachytherapy. Prostate volume is also important for prostate cancer diagnosis. Manual outlining of the prostate border is able to determine the prostate volume accurately, however, it is time consuming and tedious. Therefore, a number of investigations have been devoted to designing algorithms that are suitable for segmenting the prostate boundary in ultrasound images. The most popular method is the deformable model (snakes), a method that involves designing an energy function and then optimizing this function. The snakes algorithm usually requires either an initial contour or some points on the prostate boundary to be estimated close enough to the original boundary which is considered a drawback to this powerful method.</p> <p>Methods</p> <p>The proposed spectral clustering segmentation algorithm is built on a totally different foundation that doesn't involve any function design or optimization. It also doesn't need any contour or any points on the boundary to be estimated. The proposed algorithm depends mainly on graph theory techniques.</p> <p>Results</p> <p>Spectral clustering is used in this paper for both prostate gland segmentation from the background and internal gland segmentation. The obtained segmented images were compared to the expert radiologist segmented images. The proposed algorithm obtained excellent gland segmentation results with 93% average overlap areas. It is also able to internally segment the gland where the segmentation showed consistency with the cancerous regions identified by the expert radiologist.</p> <p>Conclusion</p> <p>The proposed spectral clustering segmentation algorithm obtained fast excellent estimates that can give rough prostate volume and location as well as internal gland segmentation without any user interaction.</p>http://www.biomedical-engineering-online.com/content/6/1/10 |
| spellingShingle | Salama Magdy MA Mohamed Samar S Spectral clustering for TRUS images BioMedical Engineering OnLine |
| title | Spectral clustering for TRUS images |
| title_full | Spectral clustering for TRUS images |
| title_fullStr | Spectral clustering for TRUS images |
| title_full_unstemmed | Spectral clustering for TRUS images |
| title_short | Spectral clustering for TRUS images |
| title_sort | spectral clustering for trus images |
| url | http://www.biomedical-engineering-online.com/content/6/1/10 |
| work_keys_str_mv | AT salamamagdyma spectralclusteringfortrusimages AT mohamedsamars spectralclusteringfortrusimages |