Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296102014> ?p ?o ?g. }
- W4296102014 abstract "Abstract Deep learning has shown excellent performance in analysing medical images. However, datasets are difficult to obtain due privacy issues, standardization problems, and lack of annotations. We address these problems by producing realistic synthetic images using a combination of 3D technologies and generative adversarial networks. We propose CUT‐seg, a joint training where a segmentation model and a generative model are jointly trained to produce realistic images while learning to segment polyps. We take advantage of recent one‐sided translation models because they use significantly less memory, allowing us to add a segmentation model in the training loop. CUT‐seg performs better, is computationally less expensive, and requires less real images than other memory‐intensive image translation approaches that require two stage training. Promising results are achieved on five real polyp segmentation datasets using only one real image and zero real annotations. As a part of this study we release Synth‐Colon, an entirely synthetic dataset that includes 20,000 realistic colon images and additional details about depth and 3D geometry: https://enric1994.github.io/synth-colon" @default.
- W4296102014 created "2022-09-17" @default.
- W4296102014 creator A5015739552 @default.
- W4296102014 creator A5056543513 @default.
- W4296102014 creator A5073924795 @default.
- W4296102014 creator A5081902636 @default.
- W4296102014 date "2022-09-08" @default.
- W4296102014 modified "2023-10-12" @default.
- W4296102014 title "Joint one‐sided synthetic unpaired image translation and segmentation for colorectal cancer prevention" @default.
- W4296102014 cites W1538580923 @default.
- W4296102014 cites W1901129140 @default.
- W4296102014 cites W2008359794 @default.
- W4296102014 cites W2021088830 @default.
- W4296102014 cites W2106904071 @default.
- W4296102014 cites W2141350700 @default.
- W4296102014 cites W2209594346 @default.
- W4296102014 cites W2285968993 @default.
- W4296102014 cites W2560328367 @default.
- W4296102014 cites W2593488799 @default.
- W4296102014 cites W2884436604 @default.
- W4296102014 cites W2919115771 @default.
- W4296102014 cites W2939157633 @default.
- W4296102014 cites W2962793481 @default.
- W4296102014 cites W2963112696 @default.
- W4296102014 cites W2963693541 @default.
- W4296102014 cites W2963846885 @default.
- W4296102014 cites W2963890275 @default.
- W4296102014 cites W2979515228 @default.
- W4296102014 cites W2982041717 @default.
- W4296102014 cites W2987175876 @default.
- W4296102014 cites W2997286550 @default.
- W4296102014 cites W3092344722 @default.
- W4296102014 cites W3108316907 @default.
- W4296102014 cites W3133178343 @default.
- W4296102014 cites W3159890710 @default.
- W4296102014 cites W3161648721 @default.
- W4296102014 cites W3175737276 @default.
- W4296102014 doi "https://doi.org/10.1111/exsy.13137" @default.
- W4296102014 hasPublicationYear "2022" @default.
- W4296102014 type Work @default.
- W4296102014 citedByCount "1" @default.
- W4296102014 countsByYear W42961020142023 @default.
- W4296102014 crossrefType "journal-article" @default.
- W4296102014 hasAuthorship W4296102014A5015739552 @default.
- W4296102014 hasAuthorship W4296102014A5056543513 @default.
- W4296102014 hasAuthorship W4296102014A5073924795 @default.
- W4296102014 hasAuthorship W4296102014A5081902636 @default.
- W4296102014 hasBestOaLocation W42961020142 @default.
- W4296102014 hasConcept C104317684 @default.
- W4296102014 hasConcept C105580179 @default.
- W4296102014 hasConcept C108583219 @default.
- W4296102014 hasConcept C111919701 @default.
- W4296102014 hasConcept C115961682 @default.
- W4296102014 hasConcept C119857082 @default.
- W4296102014 hasConcept C127413603 @default.
- W4296102014 hasConcept C149364088 @default.
- W4296102014 hasConcept C153180895 @default.
- W4296102014 hasConcept C154945302 @default.
- W4296102014 hasConcept C167966045 @default.
- W4296102014 hasConcept C170154142 @default.
- W4296102014 hasConcept C18555067 @default.
- W4296102014 hasConcept C185592680 @default.
- W4296102014 hasConcept C188087704 @default.
- W4296102014 hasConcept C2779757391 @default.
- W4296102014 hasConcept C31972630 @default.
- W4296102014 hasConcept C39890363 @default.
- W4296102014 hasConcept C41008148 @default.
- W4296102014 hasConcept C55493867 @default.
- W4296102014 hasConcept C89600930 @default.
- W4296102014 hasConceptScore W4296102014C104317684 @default.
- W4296102014 hasConceptScore W4296102014C105580179 @default.
- W4296102014 hasConceptScore W4296102014C108583219 @default.
- W4296102014 hasConceptScore W4296102014C111919701 @default.
- W4296102014 hasConceptScore W4296102014C115961682 @default.
- W4296102014 hasConceptScore W4296102014C119857082 @default.
- W4296102014 hasConceptScore W4296102014C127413603 @default.
- W4296102014 hasConceptScore W4296102014C149364088 @default.
- W4296102014 hasConceptScore W4296102014C153180895 @default.
- W4296102014 hasConceptScore W4296102014C154945302 @default.
- W4296102014 hasConceptScore W4296102014C167966045 @default.
- W4296102014 hasConceptScore W4296102014C170154142 @default.
- W4296102014 hasConceptScore W4296102014C18555067 @default.
- W4296102014 hasConceptScore W4296102014C185592680 @default.
- W4296102014 hasConceptScore W4296102014C188087704 @default.
- W4296102014 hasConceptScore W4296102014C2779757391 @default.
- W4296102014 hasConceptScore W4296102014C31972630 @default.
- W4296102014 hasConceptScore W4296102014C39890363 @default.
- W4296102014 hasConceptScore W4296102014C41008148 @default.
- W4296102014 hasConceptScore W4296102014C55493867 @default.
- W4296102014 hasConceptScore W4296102014C89600930 @default.
- W4296102014 hasFunder F4320320847 @default.
- W4296102014 hasIssue "6" @default.
- W4296102014 hasLocation W42961020141 @default.
- W4296102014 hasLocation W42961020142 @default.
- W4296102014 hasOpenAccess W4296102014 @default.
- W4296102014 hasPrimaryLocation W42961020141 @default.
- W4296102014 hasRelatedWork W2280377497 @default.
- W4296102014 hasRelatedWork W2967848559 @default.
- W4296102014 hasRelatedWork W3014948380 @default.
- W4296102014 hasRelatedWork W3174044702 @default.