File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Automated segmentation of optical coherence tomography images

TitleAutomated segmentation of optical coherence tomography images
Authors
Issue Date2019
PublisherOptical Society of America for Chinese Optical Society. The Journal's web site is located at https://www.osapublishing.org/col/home.cfm
Citation
Chinese Optics Letters, 2019, v. 17 n. 1, p. 011701:1-011701:6 How to Cite?
AbstractWe propose a fast and accurate automated algorithm to segment retinal pigment epithelium and internal limiting membrane layers from spectral domain optical coherence tomography (SDOCT) B-scan images. A hybrid algorithm, which combines intensity thresholding and graph-based algorithms, was used to process and analyze SDOCT radial scans (120 B scans) images obtained from twenty patients. The relative difference in position of the layers segmented by the proposed hybrid algorithm and by the clinical expert was 1.49% ± 0.01%. The processing time of the hybrid algorithm was 9.3 s for six B scans. Dice’s coefficient of the hybrid algorithm was 96.7% ± 1.6%. The proposed hybrid algorithm for the segmentation of SDOCT images had good agreement with manual segmentation and reduced processing time.
Persistent Identifierhttp://hdl.handle.net/10722/266501
ISSN
2023 Impact Factor: 3.3
2023 SCImago Journal Rankings: 0.742
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorKharmyssov, C-
dc.contributor.authorKo, MWL-
dc.contributor.authorKim, JR-
dc.date.accessioned2019-01-18T08:20:55Z-
dc.date.available2019-01-18T08:20:55Z-
dc.date.issued2019-
dc.identifier.citationChinese Optics Letters, 2019, v. 17 n. 1, p. 011701:1-011701:6-
dc.identifier.issn1671-7694-
dc.identifier.urihttp://hdl.handle.net/10722/266501-
dc.description.abstractWe propose a fast and accurate automated algorithm to segment retinal pigment epithelium and internal limiting membrane layers from spectral domain optical coherence tomography (SDOCT) B-scan images. A hybrid algorithm, which combines intensity thresholding and graph-based algorithms, was used to process and analyze SDOCT radial scans (120 B scans) images obtained from twenty patients. The relative difference in position of the layers segmented by the proposed hybrid algorithm and by the clinical expert was 1.49% ± 0.01%. The processing time of the hybrid algorithm was 9.3 s for six B scans. Dice’s coefficient of the hybrid algorithm was 96.7% ± 1.6%. The proposed hybrid algorithm for the segmentation of SDOCT images had good agreement with manual segmentation and reduced processing time.-
dc.languageeng-
dc.publisherOptical Society of America for Chinese Optical Society. The Journal's web site is located at https://www.osapublishing.org/col/home.cfm-
dc.relation.ispartofChinese Optics Letters-
dc.titleAutomated segmentation of optical coherence tomography images-
dc.typeArticle-
dc.identifier.emailKo, MWL: matchko@hku.hk-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.3788/COL201917.011701-
dc.identifier.scopuseid_2-s2.0-85063052416-
dc.identifier.hkuros296713-
dc.identifier.volume17-
dc.identifier.issue1-
dc.identifier.spage011701:1-
dc.identifier.epage011701:6-
dc.identifier.isiWOS:000459550800014-
dc.publisher.placeChina-
dc.identifier.issnl1671-7694-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats