Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387394362> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4387394362 endingPage "107542" @default.
- W4387394362 startingPage "107542" @default.
- W4387394362 abstract "Medical images, especially intricate vascular structures, are costly and time-consuming to annotate manually. It is beneficial to investigate an unsupervised method for vessel segmentation, one that circumvents the manual annotation yet remains valuable for disease detection. In this study, we design an unsupervised retinal vessel segmentation model based on the Swin-Unet framework and game theory. First, we construct two extreme pseudo-mapping functions by changing the contrast of the images and obtain their corresponding pseudo-masks based the on binary segmentation method and mathematical morphology, then we prove that there exists a mapping function between pseudo-mappings such that its corresponding mask is closest to the ground true mask. To acquire the best-predicted mask, based on which, we second develop a model based on the Swin-Unet frame to solve the optimal mapping function, and introduce an Image Colorization proxy task to assist the learning of pixel-level feature representations. Third, since to the instability of two pseudo-masks, the predicted mask will inevitably have errors, inspired by the two-player, non-zero-sum, non-cooperative Neighbor's Collision game in game theory, a game filter is proposed in this paper to reduce the errors in the final predicted mask. Finally, we verify the effectiveness of the presented unsupervised retinal vessel segmentation model on DRIVE, STARE and CHASE_DB1 datasets, and extensive experiments show that has obvious advantages over image segmentation and conventional unsupervised models." @default.
- W4387394362 created "2023-10-07" @default.
- W4387394362 creator A5008891189 @default.
- W4387394362 creator A5078981797 @default.
- W4387394362 date "2023-11-01" @default.
- W4387394362 modified "2023-10-14" @default.
- W4387394362 title "SURVS: A Swin-Unet and game theory-based unsupervised segmentation method for retinal vessel" @default.
- W4387394362 cites W2045227075 @default.
- W4387394362 cites W2145305441 @default.
- W4387394362 cites W2150769593 @default.
- W4387394362 cites W2488605601 @default.
- W4387394362 cites W2587662788 @default.
- W4387394362 cites W2618530766 @default.
- W4387394362 cites W2899507630 @default.
- W4387394362 cites W2919006661 @default.
- W4387394362 cites W3023371261 @default.
- W4387394362 cites W3025177399 @default.
- W4387394362 cites W3088540525 @default.
- W4387394362 cites W3099193570 @default.
- W4387394362 cites W3106135578 @default.
- W4387394362 cites W3111741353 @default.
- W4387394362 cites W3128776197 @default.
- W4387394362 cites W3148874463 @default.
- W4387394362 cites W3197865018 @default.
- W4387394362 cites W4293677672 @default.
- W4387394362 cites W4309768783 @default.
- W4387394362 doi "https://doi.org/10.1016/j.compbiomed.2023.107542" @default.
- W4387394362 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37826953" @default.
- W4387394362 hasPublicationYear "2023" @default.
- W4387394362 type Work @default.
- W4387394362 citedByCount "0" @default.
- W4387394362 crossrefType "journal-article" @default.
- W4387394362 hasAuthorship W4387394362A5008891189 @default.
- W4387394362 hasAuthorship W4387394362A5078981797 @default.
- W4387394362 hasConcept C124504099 @default.
- W4387394362 hasConcept C153180895 @default.
- W4387394362 hasConcept C154945302 @default.
- W4387394362 hasConcept C31972630 @default.
- W4387394362 hasConcept C41008148 @default.
- W4387394362 hasConcept C8038995 @default.
- W4387394362 hasConcept C89600930 @default.
- W4387394362 hasConceptScore W4387394362C124504099 @default.
- W4387394362 hasConceptScore W4387394362C153180895 @default.
- W4387394362 hasConceptScore W4387394362C154945302 @default.
- W4387394362 hasConceptScore W4387394362C31972630 @default.
- W4387394362 hasConceptScore W4387394362C41008148 @default.
- W4387394362 hasConceptScore W4387394362C8038995 @default.
- W4387394362 hasConceptScore W4387394362C89600930 @default.
- W4387394362 hasFunder F4320321001 @default.
- W4387394362 hasFunder F4320335777 @default.
- W4387394362 hasLocation W43873943621 @default.
- W4387394362 hasLocation W43873943622 @default.
- W4387394362 hasOpenAccess W4387394362 @default.
- W4387394362 hasPrimaryLocation W43873943621 @default.
- W4387394362 hasRelatedWork W1522196789 @default.
- W4387394362 hasRelatedWork W2070902896 @default.
- W4387394362 hasRelatedWork W2113201962 @default.
- W4387394362 hasRelatedWork W2501551404 @default.
- W4387394362 hasRelatedWork W2799953226 @default.
- W4387394362 hasRelatedWork W4298131179 @default.
- W4387394362 hasRelatedWork W4324315429 @default.
- W4387394362 hasRelatedWork W4366829857 @default.
- W4387394362 hasRelatedWork W4379231730 @default.
- W4387394362 hasRelatedWork W4385583601 @default.
- W4387394362 hasVolume "166" @default.
- W4387394362 isParatext "false" @default.
- W4387394362 isRetracted "false" @default.
- W4387394362 workType "article" @default.