Matches in SemOpenAlex for { <https://semopenalex.org/work/W4223504785> ?p ?o ?g. }
- W4223504785 endingPage "3883" @default.
- W4223504785 startingPage "3872" @default.
- W4223504785 abstract "Automated layer segmentation plays an important role for retinal disease diagnosis in optical coherence tomography (OCT) images. However, the severe retinal diseases result in the performance degeneration of automated layer segmentation approaches. In this paper, we present a robust semi-supervised layer segmentation network to relieve the model failures on abnormal retinas. We obtain the lesion features from the labeled images with disease-balanced distribution, and utilize the unlabeled images to supplement the layer structure information. Specifically, in our method, the cross-consistency training is utilized over the predictions of different decoders, and we enforce a consistency between different decoder predictions to improve the encoder's representation. Then, we propose a sequence prediction branch based on self-supervised manner, which is designed to predict the position of each jigsaw puzzle to obtain sensory perception of the retinal layer structure. To this task, a layer spatial pyramid pooling (LSPP) module is designed to extract multi-scale layer spatial features. Furthermore, we use the optical coherence tomography angiography (OCTA) to supplement the information damaged by diseases. The experimental results illustrate that our method achieves more robust results compared with current supervised segmentation methods. Meanwhile, advanced segmentation performance can be obtained compared with state-of-the-art semi-supervised segmentation methods." @default.
- W4223504785 created "2022-04-15" @default.
- W4223504785 creator A5006184025 @default.
- W4223504785 creator A5016927979 @default.
- W4223504785 creator A5017254269 @default.
- W4223504785 creator A5042551057 @default.
- W4223504785 creator A5050474631 @default.
- W4223504785 creator A5060018005 @default.
- W4223504785 date "2022-08-01" @default.
- W4223504785 modified "2023-10-11" @default.
- W4223504785 title "Self-Supervised Sequence Recovery for Semi-Supervised Retinal Layer Segmentation" @default.
- W4223504785 cites W1903029394 @default.
- W4223504785 cites W1999377661 @default.
- W4223504785 cites W2000642633 @default.
- W4223504785 cites W2032756844 @default.
- W4223504785 cites W2063440562 @default.
- W4223504785 cites W2074598933 @default.
- W4223504785 cites W2083181574 @default.
- W4223504785 cites W2085232786 @default.
- W4223504785 cites W2086295185 @default.
- W4223504785 cites W2100756624 @default.
- W4223504785 cites W2105274562 @default.
- W4223504785 cites W2118978333 @default.
- W4223504785 cites W2157979199 @default.
- W4223504785 cites W2300921526 @default.
- W4223504785 cites W2414755904 @default.
- W4223504785 cites W2418802570 @default.
- W4223504785 cites W2512345558 @default.
- W4223504785 cites W2592517646 @default.
- W4223504785 cites W2592729436 @default.
- W4223504785 cites W2606534623 @default.
- W4223504785 cites W2608854843 @default.
- W4223504785 cites W2769497098 @default.
- W4223504785 cites W2775636951 @default.
- W4223504785 cites W2782158523 @default.
- W4223504785 cites W2790408330 @default.
- W4223504785 cites W2888905826 @default.
- W4223504785 cites W2963239200 @default.
- W4223504785 cites W2966495887 @default.
- W4223504785 cites W2979568061 @default.
- W4223504785 cites W2995808743 @default.
- W4223504785 cites W2996290406 @default.
- W4223504785 cites W3035680157 @default.
- W4223504785 cites W3049117435 @default.
- W4223504785 cites W3090488062 @default.
- W4223504785 cites W3116279133 @default.
- W4223504785 cites W3136011173 @default.
- W4223504785 cites W3138785910 @default.
- W4223504785 cites W3162527784 @default.
- W4223504785 doi "https://doi.org/10.1109/jbhi.2022.3166778" @default.
- W4223504785 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35412994" @default.
- W4223504785 hasPublicationYear "2022" @default.
- W4223504785 type Work @default.
- W4223504785 citedByCount "5" @default.
- W4223504785 countsByYear W42235047852022 @default.
- W4223504785 countsByYear W42235047852023 @default.
- W4223504785 crossrefType "journal-article" @default.
- W4223504785 hasAuthorship W4223504785A5006184025 @default.
- W4223504785 hasAuthorship W4223504785A5016927979 @default.
- W4223504785 hasAuthorship W4223504785A5017254269 @default.
- W4223504785 hasAuthorship W4223504785A5042551057 @default.
- W4223504785 hasAuthorship W4223504785A5050474631 @default.
- W4223504785 hasAuthorship W4223504785A5060018005 @default.
- W4223504785 hasConcept C111919701 @default.
- W4223504785 hasConcept C118487528 @default.
- W4223504785 hasConcept C118505674 @default.
- W4223504785 hasConcept C124504099 @default.
- W4223504785 hasConcept C142575187 @default.
- W4223504785 hasConcept C153180895 @default.
- W4223504785 hasConcept C154945302 @default.
- W4223504785 hasConcept C2524010 @default.
- W4223504785 hasConcept C2778818243 @default.
- W4223504785 hasConcept C31972630 @default.
- W4223504785 hasConcept C33923547 @default.
- W4223504785 hasConcept C41008148 @default.
- W4223504785 hasConcept C65885262 @default.
- W4223504785 hasConcept C70437156 @default.
- W4223504785 hasConcept C71924100 @default.
- W4223504785 hasConcept C89600930 @default.
- W4223504785 hasConceptScore W4223504785C111919701 @default.
- W4223504785 hasConceptScore W4223504785C118487528 @default.
- W4223504785 hasConceptScore W4223504785C118505674 @default.
- W4223504785 hasConceptScore W4223504785C124504099 @default.
- W4223504785 hasConceptScore W4223504785C142575187 @default.
- W4223504785 hasConceptScore W4223504785C153180895 @default.
- W4223504785 hasConceptScore W4223504785C154945302 @default.
- W4223504785 hasConceptScore W4223504785C2524010 @default.
- W4223504785 hasConceptScore W4223504785C2778818243 @default.
- W4223504785 hasConceptScore W4223504785C31972630 @default.
- W4223504785 hasConceptScore W4223504785C33923547 @default.
- W4223504785 hasConceptScore W4223504785C41008148 @default.
- W4223504785 hasConceptScore W4223504785C65885262 @default.
- W4223504785 hasConceptScore W4223504785C70437156 @default.
- W4223504785 hasConceptScore W4223504785C71924100 @default.
- W4223504785 hasConceptScore W4223504785C89600930 @default.
- W4223504785 hasFunder F4320321001 @default.
- W4223504785 hasFunder F4320325437 @default.
- W4223504785 hasFunder F4320335787 @default.