Matches in SemOpenAlex for { <https://semopenalex.org/work/W4211088096> ?p ?o ?g. }
- W4211088096 endingPage "1881" @default.
- W4211088096 startingPage "1870" @default.
- W4211088096 abstract "OCT fluid segmentation is a crucial task for diagnosis and therapy in ophthalmology. The current convolutional neural networks (CNNs) supervised by pixel-wise annotated masks achieve great success in OCT fluid segmentation. However, requiring pixel-wise masks from OCT images is time-consuming, expensive and expertise needed. This paper proposes an Intra- and inter-Slice Contrastive Learning Network (ISCLNet) for OCT fluid segmentation with only point supervision. Our ISCLNet learns visual representation by designing contrastive tasks that exploit the inherent similarity or dissimilarity from unlabeled OCT data. Specifically, we propose an intra-slice contrastive learning strategy to leverage the fluid-background similarity and the retinal layer-background dissimilarity. Moreover, we construct an inter-slice contrastive learning architecture to learn the similarity of adjacent OCT slices from one OCT volume. Finally, an end-to-end model combining intra- and inter-slice contrastive learning processes learns to segment fluid under the point supervision. The experimental results on two public OCT fluid segmentation datasets (i.e., AI Challenger and RETOUCH) demonstrate that the ISCLNet bridges the gap between fully-supervised and weakly-supervised OCT fluid segmentation and outperforms other well-known point-supervised segmentation methods." @default.
- W4211088096 created "2022-02-13" @default.
- W4211088096 creator A5024224542 @default.
- W4211088096 creator A5027769937 @default.
- W4211088096 creator A5032352025 @default.
- W4211088096 creator A5065061505 @default.
- W4211088096 date "2022-01-01" @default.
- W4211088096 modified "2023-10-15" @default.
- W4211088096 title "Intra- and Inter-Slice Contrastive Learning for Point Supervised OCT Fluid Segmentation" @default.
- W4211088096 cites W1495267108 @default.
- W4211088096 cites W1613696384 @default.
- W4211088096 cites W1783315696 @default.
- W4211088096 cites W1869500417 @default.
- W4211088096 cites W1945608308 @default.
- W4211088096 cites W1965555277 @default.
- W4211088096 cites W1991374664 @default.
- W4211088096 cites W2026411462 @default.
- W4211088096 cites W2104231843 @default.
- W4211088096 cites W2109255472 @default.
- W4211088096 cites W2132683124 @default.
- W4211088096 cites W2133059825 @default.
- W4211088096 cites W2134542952 @default.
- W4211088096 cites W2152883336 @default.
- W4211088096 cites W2295107390 @default.
- W4211088096 cites W2321533354 @default.
- W4211088096 cites W2337429362 @default.
- W4211088096 cites W2337570847 @default.
- W4211088096 cites W2395611524 @default.
- W4211088096 cites W2412782625 @default.
- W4211088096 cites W2418802570 @default.
- W4211088096 cites W2552414813 @default.
- W4211088096 cites W2592517646 @default.
- W4211088096 cites W2606534623 @default.
- W4211088096 cites W2742087205 @default.
- W4211088096 cites W2742126485 @default.
- W4211088096 cites W2742820103 @default.
- W4211088096 cites W2772059204 @default.
- W4211088096 cites W2806398633 @default.
- W4211088096 cites W2884436604 @default.
- W4211088096 cites W2886281300 @default.
- W4211088096 cites W2896435145 @default.
- W4211088096 cites W2898829509 @default.
- W4211088096 cites W2907100905 @default.
- W4211088096 cites W2917393555 @default.
- W4211088096 cites W2919070891 @default.
- W4211088096 cites W2944774584 @default.
- W4211088096 cites W2949122205 @default.
- W4211088096 cites W2963687373 @default.
- W4211088096 cites W2963881378 @default.
- W4211088096 cites W2963891777 @default.
- W4211088096 cites W2964744899 @default.
- W4211088096 cites W2966037847 @default.
- W4211088096 cites W2982430624 @default.
- W4211088096 cites W3023371261 @default.
- W4211088096 cites W3033671339 @default.
- W4211088096 cites W3035131250 @default.
- W4211088096 cites W3035703639 @default.
- W4211088096 cites W3036883289 @default.
- W4211088096 cites W3083149714 @default.
- W4211088096 cites W3092486982 @default.
- W4211088096 cites W3100040694 @default.
- W4211088096 cites W3114632476 @default.
- W4211088096 cites W3165736781 @default.
- W4211088096 cites W3189659869 @default.
- W4211088096 doi "https://doi.org/10.1109/tip.2022.3148814" @default.
- W4211088096 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35139015" @default.
- W4211088096 hasPublicationYear "2022" @default.
- W4211088096 type Work @default.
- W4211088096 citedByCount "15" @default.
- W4211088096 countsByYear W42110880962022 @default.
- W4211088096 countsByYear W42110880962023 @default.
- W4211088096 crossrefType "journal-article" @default.
- W4211088096 hasAuthorship W4211088096A5024224542 @default.
- W4211088096 hasAuthorship W4211088096A5027769937 @default.
- W4211088096 hasAuthorship W4211088096A5032352025 @default.
- W4211088096 hasAuthorship W4211088096A5065061505 @default.
- W4211088096 hasConcept C103278499 @default.
- W4211088096 hasConcept C108583219 @default.
- W4211088096 hasConcept C115961682 @default.
- W4211088096 hasConcept C124504099 @default.
- W4211088096 hasConcept C153083717 @default.
- W4211088096 hasConcept C153180895 @default.
- W4211088096 hasConcept C154945302 @default.
- W4211088096 hasConcept C41008148 @default.
- W4211088096 hasConcept C81363708 @default.
- W4211088096 hasConcept C89600930 @default.
- W4211088096 hasConceptScore W4211088096C103278499 @default.
- W4211088096 hasConceptScore W4211088096C108583219 @default.
- W4211088096 hasConceptScore W4211088096C115961682 @default.
- W4211088096 hasConceptScore W4211088096C124504099 @default.
- W4211088096 hasConceptScore W4211088096C153083717 @default.
- W4211088096 hasConceptScore W4211088096C153180895 @default.
- W4211088096 hasConceptScore W4211088096C154945302 @default.
- W4211088096 hasConceptScore W4211088096C41008148 @default.
- W4211088096 hasConceptScore W4211088096C81363708 @default.
- W4211088096 hasConceptScore W4211088096C89600930 @default.
- W4211088096 hasFunder F4320321001 @default.
- W4211088096 hasLocation W42110880961 @default.