File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Evaluation and optimization of the parameters used in multiple-atlas-based segmentation of prostate cancers in radiation therapy

TitleEvaluation and optimization of the parameters used in multiple-atlas-based segmentation of prostate cancers in radiation therapy
Authors
Issue Date2016
PublisherBritish Institute of Radiology. The Journal's web site is located at http://bjr.birjournals.org
Citation
British Journal of Radiology, 2016, v. 89 n. 1057, article no. 20140732 How to Cite?
AbstractOBJECTIVE: To evaluate and optimize the parameters used in multiple-atlas-based segmentation of prostate cancers in radiation therapy. METHODS: A retrospective study was conducted, and the accuracy of the multiple-atlas-based segmentation was tested on 30 patients. The effect of library size (LS), number of atlases used for contour averaging and the contour averaging strategy were also studied. The autogenerated contours were compared with the manually drawn contours. Dice similarity coefficient (DSC) and Hausdorff distance were used to evaluate the segmentation agreement. RESULTS: Mixed results were found between simultaneous truth and performance level estimation (STAPLE) and majority vote (MV) strategies. Multiple-atlas approaches were relatively insensitive to LS. A LS of ten was adequate, and further increase in the LS only showed insignificant gain. Multiple atlas performed better than single atlas for most of the time. Using more atlases did not guarantee better performance, with five atlases performing better than ten atlases. With our recommended setting, the median DSC for the bladder, rectum, prostate, seminal vesicle and femurs was 0.90, 0.77, 0.84, 0.56 and 0.95, respectively. CONCLUSION: Our study shows that multiple-atlas-based strategies have better accuracy than single-atlas approach. STAPLE is preferred, and a LS of ten is adequate for prostate cases. Using five atlases for contour averaging is recommended. The contouring accuracy of seminal vesicle still needs improvement, and manual editing is still required for the other structures. ADVANCES IN KNOWLEDGE: This article provides a better understanding of the influence of the parameters used in multiple-atlas-based segmentation of prostate cancers.
Persistent Identifierhttp://hdl.handle.net/10722/231803
ISSN
2020 Impact Factor: 3.039
2020 SCImago Journal Rankings: 0.782
PubMed Central ID
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWong, WKH-
dc.contributor.authorLeung, LHT-
dc.contributor.authorKwong, DLW-
dc.date.accessioned2016-09-20T05:25:34Z-
dc.date.available2016-09-20T05:25:34Z-
dc.date.issued2016-
dc.identifier.citationBritish Journal of Radiology, 2016, v. 89 n. 1057, article no. 20140732-
dc.identifier.issn0007-1285-
dc.identifier.urihttp://hdl.handle.net/10722/231803-
dc.description.abstractOBJECTIVE: To evaluate and optimize the parameters used in multiple-atlas-based segmentation of prostate cancers in radiation therapy. METHODS: A retrospective study was conducted, and the accuracy of the multiple-atlas-based segmentation was tested on 30 patients. The effect of library size (LS), number of atlases used for contour averaging and the contour averaging strategy were also studied. The autogenerated contours were compared with the manually drawn contours. Dice similarity coefficient (DSC) and Hausdorff distance were used to evaluate the segmentation agreement. RESULTS: Mixed results were found between simultaneous truth and performance level estimation (STAPLE) and majority vote (MV) strategies. Multiple-atlas approaches were relatively insensitive to LS. A LS of ten was adequate, and further increase in the LS only showed insignificant gain. Multiple atlas performed better than single atlas for most of the time. Using more atlases did not guarantee better performance, with five atlases performing better than ten atlases. With our recommended setting, the median DSC for the bladder, rectum, prostate, seminal vesicle and femurs was 0.90, 0.77, 0.84, 0.56 and 0.95, respectively. CONCLUSION: Our study shows that multiple-atlas-based strategies have better accuracy than single-atlas approach. STAPLE is preferred, and a LS of ten is adequate for prostate cases. Using five atlases for contour averaging is recommended. The contouring accuracy of seminal vesicle still needs improvement, and manual editing is still required for the other structures. ADVANCES IN KNOWLEDGE: This article provides a better understanding of the influence of the parameters used in multiple-atlas-based segmentation of prostate cancers.-
dc.languageeng-
dc.publisherBritish Institute of Radiology. The Journal's web site is located at http://bjr.birjournals.org-
dc.relation.ispartofBritish Journal of Radiology-
dc.rightsRepublished with permission of British Institute of Radiology, © 2015, from British Journal of Radiology, 2016, v. 89 n. 1057, article no. 20140732.-
dc.titleEvaluation and optimization of the parameters used in multiple-atlas-based segmentation of prostate cancers in radiation therapy-
dc.typeArticle-
dc.identifier.emailKwong, DLW: dlwkwong@hku.hk-
dc.identifier.authorityKwong, DLW=rp00414-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1259/bjr.20140732-
dc.identifier.pmid26539630-
dc.identifier.pmcidPMC4985939-
dc.identifier.scopuseid_2-s2.0-84951049575-
dc.identifier.hkuros266975-
dc.identifier.volume89-
dc.identifier.issue1057-
dc.identifier.spagearticle no. 20140732-
dc.identifier.epagearticle no. 20140732-
dc.identifier.isiWOS:000368418500003-
dc.publisher.placeUnited Kingdom-
dc.identifier.issnl0007-1285-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats