Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387335053> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4387335053 endingPage "103852" @default.
- W4387335053 startingPage "103852" @default.
- W4387335053 abstract "Training deep learning methods for optical coherence tomography (OCT) retinal and choroidal layer segmentation is a challenge when data is scarce. In medical image analysis, this is often the case with a lack of data sharing due to confidentiality agreements and data privacy concerns which is further exacerbated in cases of rare pathologies. Even where OCT data is readily available, performing the requisite annotations is time consuming, costly, and error-prone. Data augmentation and semi-supervised learning (SSL) are two techniques employed in deep learning to enhance training in these situations. In this study, we extend our previous work proposing an enhanced StyleGAN2-based data augmentation method for OCT images by employing SSL through a novel cross-localisation technique. The technique increases the diversity of the synthetic data by automatically incorporating styles from unlabeled data with those from labelled data. The method can be used to extend StyleGAN2 as the core idea is simple, yet highly performant. In this work, we optimize the method through a set of ablations and propose the use of a targeted task-specific model selection technique for more optimal generator selection, further boosting performance. The method is applied to OCT retinal and choroidal layer segmentation, demonstrating its effectiveness through substantial patch classification performance improvements as well as significant reductions in choroidal layer segmentation error." @default.
- W4387335053 created "2023-10-05" @default.
- W4387335053 creator A5022009973 @default.
- W4387335053 creator A5026925842 @default.
- W4387335053 creator A5041138389 @default.
- W4387335053 creator A5074839699 @default.
- W4387335053 creator A5093000949 @default.
- W4387335053 date "2023-12-01" @default.
- W4387335053 modified "2023-10-18" @default.
- W4387335053 title "Enhanced OCT chorio-retinal segmentation in low-data settings with semi-supervised GAN augmentation using cross-localisation" @default.
- W4387335053 cites W1900665324 @default.
- W4387335053 cites W2013436069 @default.
- W4387335053 cites W2606534623 @default.
- W4387335053 cites W2608854843 @default.
- W4387335053 cites W2808330913 @default.
- W4387335053 cites W2898575988 @default.
- W4387335053 cites W2905660188 @default.
- W4387335053 cites W2973920946 @default.
- W4387335053 cites W2998648213 @default.
- W4387335053 cites W3035131250 @default.
- W4387335053 cites W3035574324 @default.
- W4387335053 cites W3036782889 @default.
- W4387335053 cites W3122440835 @default.
- W4387335053 cites W3135700368 @default.
- W4387335053 cites W3163368546 @default.
- W4387335053 cites W4220747310 @default.
- W4387335053 cites W4304808902 @default.
- W4387335053 doi "https://doi.org/10.1016/j.cviu.2023.103852" @default.
- W4387335053 hasPublicationYear "2023" @default.
- W4387335053 type Work @default.
- W4387335053 citedByCount "0" @default.
- W4387335053 crossrefType "journal-article" @default.
- W4387335053 hasAuthorship W4387335053A5022009973 @default.
- W4387335053 hasAuthorship W4387335053A5026925842 @default.
- W4387335053 hasAuthorship W4387335053A5041138389 @default.
- W4387335053 hasAuthorship W4387335053A5074839699 @default.
- W4387335053 hasAuthorship W4387335053A5093000949 @default.
- W4387335053 hasBestOaLocation W43873350531 @default.
- W4387335053 hasConcept C108583219 @default.
- W4387335053 hasConcept C118487528 @default.
- W4387335053 hasConcept C119857082 @default.
- W4387335053 hasConcept C153180895 @default.
- W4387335053 hasConcept C154945302 @default.
- W4387335053 hasConcept C2776145971 @default.
- W4387335053 hasConcept C2778818243 @default.
- W4387335053 hasConcept C41008148 @default.
- W4387335053 hasConcept C46686674 @default.
- W4387335053 hasConcept C58489278 @default.
- W4387335053 hasConcept C58973888 @default.
- W4387335053 hasConcept C71924100 @default.
- W4387335053 hasConcept C89600930 @default.
- W4387335053 hasConceptScore W4387335053C108583219 @default.
- W4387335053 hasConceptScore W4387335053C118487528 @default.
- W4387335053 hasConceptScore W4387335053C119857082 @default.
- W4387335053 hasConceptScore W4387335053C153180895 @default.
- W4387335053 hasConceptScore W4387335053C154945302 @default.
- W4387335053 hasConceptScore W4387335053C2776145971 @default.
- W4387335053 hasConceptScore W4387335053C2778818243 @default.
- W4387335053 hasConceptScore W4387335053C41008148 @default.
- W4387335053 hasConceptScore W4387335053C46686674 @default.
- W4387335053 hasConceptScore W4387335053C58489278 @default.
- W4387335053 hasConceptScore W4387335053C58973888 @default.
- W4387335053 hasConceptScore W4387335053C71924100 @default.
- W4387335053 hasConceptScore W4387335053C89600930 @default.
- W4387335053 hasLocation W43873350531 @default.
- W4387335053 hasOpenAccess W4387335053 @default.
- W4387335053 hasPrimaryLocation W43873350531 @default.
- W4387335053 hasRelatedWork W1991049327 @default.
- W4387335053 hasRelatedWork W2074435087 @default.
- W4387335053 hasRelatedWork W2186210338 @default.
- W4387335053 hasRelatedWork W2365028544 @default.
- W4387335053 hasRelatedWork W2371815184 @default.
- W4387335053 hasRelatedWork W2760891738 @default.
- W4387335053 hasRelatedWork W2949671220 @default.
- W4387335053 hasRelatedWork W34092691 @default.
- W4387335053 hasRelatedWork W4282977123 @default.
- W4387335053 hasRelatedWork W4309984931 @default.
- W4387335053 hasVolume "237" @default.
- W4387335053 isParatext "false" @default.
- W4387335053 isRetracted "false" @default.
- W4387335053 workType "article" @default.