Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226376189> ?p ?o ?g. }
- W4226376189 endingPage "7348" @default.
- W4226376189 startingPage "7348" @default.
- W4226376189 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." @default.
- W4226376189 created "2022-05-05" @default.
- W4226376189 creator A5005936176 @default.
- W4226376189 creator A5007639938 @default.
- W4226376189 creator A5015017045 @default.
- W4226376189 creator A5036933697 @default.
- W4226376189 creator A5054878311 @default.
- W4226376189 creator A5064124202 @default.
- W4226376189 creator A5072153875 @default.
- W4226376189 date "2021-11-08" @default.
- W4226376189 modified "2023-10-16" @default.
- W4226376189 title "Multi-task learning approach for volumetric segmentation and reconstruction in 3D OCT images" @default.
- W4226376189 cites W1986506811 @default.
- W4226376189 cites W1991208188 @default.
- W4226376189 cites W2006828663 @default.
- W4226376189 cites W2009667531 @default.
- W4226376189 cites W2044488346 @default.
- W4226376189 cites W2045639482 @default.
- W4226376189 cites W2061581949 @default.
- W4226376189 cites W2084620323 @default.
- W4226376189 cites W2084816571 @default.
- W4226376189 cites W2096985690 @default.
- W4226376189 cites W2100756624 @default.
- W4226376189 cites W2313377119 @default.
- W4226376189 cites W2587010042 @default.
- W4226376189 cites W2625430291 @default.
- W4226376189 cites W2904540960 @default.
- W4226376189 cites W2908621325 @default.
- W4226376189 cites W2910847698 @default.
- W4226376189 cites W2967445385 @default.
- W4226376189 cites W2973920946 @default.
- W4226376189 cites W2977357418 @default.
- W4226376189 cites W3101756320 @default.
- W4226376189 doi "https://doi.org/10.1364/boe.428140" @default.
- W4226376189 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35003838" @default.
- W4226376189 hasPublicationYear "2021" @default.
- W4226376189 type Work @default.
- W4226376189 citedByCount "2" @default.
- W4226376189 countsByYear W42263761892023 @default.
- W4226376189 crossrefType "journal-article" @default.
- W4226376189 hasAuthorship W4226376189A5005936176 @default.
- W4226376189 hasAuthorship W4226376189A5007639938 @default.
- W4226376189 hasAuthorship W4226376189A5015017045 @default.
- W4226376189 hasAuthorship W4226376189A5036933697 @default.
- W4226376189 hasAuthorship W4226376189A5054878311 @default.
- W4226376189 hasAuthorship W4226376189A5064124202 @default.
- W4226376189 hasAuthorship W4226376189A5072153875 @default.
- W4226376189 hasBestOaLocation W42263761891 @default.
- W4226376189 hasConcept C108583219 @default.
- W4226376189 hasConcept C118487528 @default.
- W4226376189 hasConcept C120665830 @default.
- W4226376189 hasConcept C121332964 @default.
- W4226376189 hasConcept C124504099 @default.
- W4226376189 hasConcept C127313418 @default.
- W4226376189 hasConcept C151730666 @default.
- W4226376189 hasConcept C153180895 @default.
- W4226376189 hasConcept C154945302 @default.
- W4226376189 hasConcept C2776694393 @default.
- W4226376189 hasConcept C2777093970 @default.
- W4226376189 hasConcept C2778818243 @default.
- W4226376189 hasConcept C2779343474 @default.
- W4226376189 hasConcept C31972630 @default.
- W4226376189 hasConcept C41008148 @default.
- W4226376189 hasConcept C71924100 @default.
- W4226376189 hasConcept C89600930 @default.
- W4226376189 hasConceptScore W4226376189C108583219 @default.
- W4226376189 hasConceptScore W4226376189C118487528 @default.
- W4226376189 hasConceptScore W4226376189C120665830 @default.
- W4226376189 hasConceptScore W4226376189C121332964 @default.
- W4226376189 hasConceptScore W4226376189C124504099 @default.
- W4226376189 hasConceptScore W4226376189C127313418 @default.
- W4226376189 hasConceptScore W4226376189C151730666 @default.
- W4226376189 hasConceptScore W4226376189C153180895 @default.
- W4226376189 hasConceptScore W4226376189C154945302 @default.
- W4226376189 hasConceptScore W4226376189C2776694393 @default.
- W4226376189 hasConceptScore W4226376189C2777093970 @default.
- W4226376189 hasConceptScore W4226376189C2778818243 @default.
- W4226376189 hasConceptScore W4226376189C2779343474 @default.
- W4226376189 hasConceptScore W4226376189C31972630 @default.
- W4226376189 hasConceptScore W4226376189C41008148 @default.
- W4226376189 hasConceptScore W4226376189C71924100 @default.
- W4226376189 hasConceptScore W4226376189C89600930 @default.
- W4226376189 hasFunder F4320316262 @default.
- W4226376189 hasFunder F4320320696 @default.
- W4226376189 hasFunder F4320320709 @default.
- W4226376189 hasFunder F4320334737 @default.
- W4226376189 hasIssue "12" @default.
- W4226376189 hasLocation W42263761891 @default.
- W4226376189 hasLocation W42263761892 @default.
- W4226376189 hasLocation W42263761893 @default.
- W4226376189 hasLocation W42263761894 @default.
- W4226376189 hasOpenAccess W4226376189 @default.
- W4226376189 hasPrimaryLocation W42263761891 @default.
- W4226376189 hasRelatedWork W150054347 @default.
- W4226376189 hasRelatedWork W1522196789 @default.
- W4226376189 hasRelatedWork W2080412801 @default.
- W4226376189 hasRelatedWork W2348498086 @default.
- W4226376189 hasRelatedWork W3093461874 @default.