Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/156185
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cahyo, Dheo A. Y. | en_US |
dc.contributor.author | Yow, Ai Ping | en_US |
dc.contributor.author | Saw, Seang-Mei | en_US |
dc.contributor.author | Ang, Marcus | en_US |
dc.contributor.author | Girard, Michael | en_US |
dc.contributor.author | Schmetterer, Leopold | en_US |
dc.contributor.author | Wong, Damon Wing Kee | en_US |
dc.date.accessioned | 2022-04-11T01:31:55Z | - |
dc.date.available | 2022-04-11T01:31:55Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Cahyo, D. A. Y., Yow, A. P., Saw, S., Ang, M., Girard, M., Schmetterer, L. & Wong, D. W. K. (2021). Multi-task learning approach for volumetric segmentation and reconstruction in 3D OCT images. Biomedical Optics Express, 12(12), 7348-7360. https://dx.doi.org/10.1364/BOE.428140 | en_US |
dc.identifier.issn | 2156-7085 | en_US |
dc.identifier.uri | https://hdl.handle.net/10356/156185 | - |
dc.description.abstract | The choroid is the vascular layer of the eye that supplies photoreceptors with oxygen. Changes in the choroid are associated with many pathologies including myopia where the choroid progressively thins due to axial elongation. To quantize these changes, there is a need to automatically and accurately segment the choroidal layer from optical coherence tomography (OCT) images. In this paper, we propose a multi-task learning approach to segment the choroid from three-dimensional OCT images. Our proposed architecture aggregates the spatial context from adjacent cross-sectional slices to reconstruct the central slice. Spatial context learned by this reconstruction mechanism is then fused with a U-Net based architecture for segmentation. The proposed approach was evaluated on volumetric OCT scans of 166 myopic eyes acquired with a commercial OCT system, and achieved a cross-validation Intersection over Union (IoU) score of 94.69% which significantly outperformed (p<0.001) the other state-of-the-art methods on the same data set. Choroidal thickness maps generated by our approach also achieved a better structural similarity index (SSIM) of 72.11% with respect to the groundtruth. In particular, our approach performs well for highly challenging eyes with thinner choroids. Compared to other methods, our proposed approach also requires lesser processing time and has lower computational requirements. The results suggest that our proposed approach could potentially be used as a fast and reliable method for automated choroidal segmentation. | en_US |
dc.description.sponsorship | Agency for Science, Technology and Research (A*STAR) | en_US |
dc.description.sponsorship | Nanyang Technological University | en_US |
dc.description.sponsorship | National Medical Research Council (NMRC) | en_US |
dc.description.sponsorship | National Research Foundation (NRF) | en_US |
dc.language.iso | en | en_US |
dc.relation | CG/C010A/2017_SERI | en_US |
dc.relation | MOH-000249-00 | en_US |
dc.relation | MOH-OFIRG20nov-0014 | en_US |
dc.relation | OFIRG/0048/2017 | en_US |
dc.relation | OFLCG/004c/2018 | en_US |
dc.relation | TA/MOH-000249-00/2018 | en_US |
dc.relation | NRF2019-THE002-0006 | en_US |
dc.relation | NRF-CRP24-2020-0001 | en_US |
dc.relation | A20H4b0141 | en_US |
dc.relation | LF1019-1 | en_US |
dc.relation | Duke-NUS-KP(Coll)/2018/0009A | en_US |
dc.relation.ispartof | Biomedical Optics Express | en_US |
dc.rights | © 2021 Optical Society of America under the terms of the Open Access Publishing Agreement. Users may use, reuse, and build upon the article, or use the article for text or data mining, so long as such uses are for noncommercial purposes and appropriate attribution is maintained. All other rights are reserved. | en_US |
dc.subject | Engineering::Chemical engineering | en_US |
dc.subject | Engineering::Electrical and electronic engineering::Optics, optoelectronics, photonics | en_US |
dc.title | Multi-task learning approach for volumetric segmentation and reconstruction in 3D OCT images | en_US |
dc.type | Journal Article | - |
dc.contributor.school | School of Chemical and Biomedical Engineering | en_US |
dc.contributor.organization | Singapore National Eye Centre | en_US |
dc.contributor.research | Institute for Digital Molecular Analytics and Science (IDMxS) | en_US |
dc.contributor.research | Singapore Centre for Environmental Life Sciences and Engineering (SCELSE) | en_US |
dc.contributor.research | SERI-NTU Advanced Ocular Engineering (STANCE) | en_US |
dc.identifier.doi | 10.1364/BOE.428140 | - |
dc.description.version | Published version | en_US |
dc.identifier.pmid | 35003838 | - |
dc.identifier.scopus | 2-s2.0-85120003267 | - |
dc.identifier.issue | 12 | en_US |
dc.identifier.volume | 12 | en_US |
dc.identifier.spage | 7348 | en_US |
dc.identifier.epage | 7360 | en_US |
dc.subject.keywords | Image Reconstruction | en_US |
dc.subject.keywords | Optical Tomography | en_US |
dc.description.acknowledgement | National Medical Research Council (CG/C010A/2017_SERI, MOH-000249-00, MOH-OFIRG20nov-0014, OFIRG/0048/2017, OFLCG/004c/2018, TA/MOH-000249-00/2018); Singapore Eye Research Institute & Nanyang Technological University (SERI-NTU Advanced Ocular Engineering Program); National Research Foundation Singapore (NRF2019-THE002-0006, NRF-CRP24-2020-0001); Agency for Science, Technology and Research (A20H4b0141); SERI-Lee Foundation (LF1019-1); Duke-NUS Medical School (Duke-NUS-KP(Coll)/2018/0009A). | en_US |
item.fulltext | With Fulltext | - |
item.grantfulltext | open | - |
Appears in Collections: | IDMxS Journal Articles SCBE Journal Articles SCELSE Journal Articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Multi-task learning approach for volumetric segmentation and reconstruction in 3D OCT images.pdf | 3.02 MB | Adobe PDF | View/Open |
SCOPUSTM
Citations
50
1
Updated on Mar 24, 2024
Web of ScienceTM
Citations
50
1
Updated on Oct 26, 2023
Page view(s)
187
Updated on Mar 28, 2024
Download(s) 50
62
Updated on Mar 28, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.