Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209684920> ?p ?o ?g. }
- W3209684920 abstract "Despite the great success of convolutional neural networks (CNN) in 3D medical image segmentation tasks, the methods currently in use are still not robust enough to the different protocols utilized by different scanners, and to the variety of image properties or artefacts they produce. To this end, we introduce OOCS-enhanced networks, a novel architecture inspired by the innate nature of visual processing in the vertebrates. With different 3D U-Net variants as the base, we add two 3D residual components to the second encoder blocks: on and off center-surround (OOCS). They generalise the ganglion pathways in the retina to a 3D setting. The use of 2D-OOCS in any standard CNN network complements the feedforward framework with sharp edge-detection inductive biases. The use of 3D-OOCS also helps 3D U-Nets to scrutinise and delineate anatomical structures present in 3D images with increased accuracy.We compared the state-of-the-art 3D U-Nets with their 3D-OOCS extensions and showed the superior accuracy and robustness of the latter in automatic prostate segmentation from 3D Magnetic Resonance Images (MRIs). For a fair comparison, we trained and tested all the investigated 3D U-Nets with the same pipeline, including automatic hyperparameter optimisation and data augmentation." @default.
- W3209684920 created "2021-11-08" @default.
- W3209684920 creator A5017091430 @default.
- W3209684920 creator A5020035339 @default.
- W3209684920 creator A5034362557 @default.
- W3209684920 creator A5036099762 @default.
- W3209684920 creator A5059357294 @default.
- W3209684920 creator A5082142516 @default.
- W3209684920 creator A5085968028 @default.
- W3209684920 date "2021-10-29" @default.
- W3209684920 modified "2023-09-26" @default.
- W3209684920 title "3D-OOCS: Learning Prostate Segmentation with Inductive Bias" @default.
- W3209684920 cites W1522734439 @default.
- W3209684920 cites W1604149110 @default.
- W3209684920 cites W1901129140 @default.
- W3209684920 cites W1909740415 @default.
- W3209684920 cites W1965673217 @default.
- W3209684920 cites W2051206390 @default.
- W3209684920 cites W2100247957 @default.
- W3209684920 cites W2102283130 @default.
- W3209684920 cites W2106033751 @default.
- W3209684920 cites W2115135943 @default.
- W3209684920 cites W2136048835 @default.
- W3209684920 cites W2140253240 @default.
- W3209684920 cites W2163605009 @default.
- W3209684920 cites W2212384750 @default.
- W3209684920 cites W2412748630 @default.
- W3209684920 cites W2432481613 @default.
- W3209684920 cites W2592929672 @default.
- W3209684920 cites W2597490979 @default.
- W3209684920 cites W2734349601 @default.
- W3209684920 cites W2738724892 @default.
- W3209684920 cites W2768282280 @default.
- W3209684920 cites W2795126069 @default.
- W3209684920 cites W2798122215 @default.
- W3209684920 cites W2803522971 @default.
- W3209684920 cites W2884436604 @default.
- W3209684920 cites W2915126261 @default.
- W3209684920 cites W2946147212 @default.
- W3209684920 cites W2949117887 @default.
- W3209684920 cites W2951839332 @default.
- W3209684920 cites W2963423218 @default.
- W3209684920 cites W2964121744 @default.
- W3209684920 cites W2970971581 @default.
- W3209684920 cites W2987213766 @default.
- W3209684920 cites W2989769843 @default.
- W3209684920 cites W3012412627 @default.
- W3209684920 cites W3015015331 @default.
- W3209684920 cites W3034265573 @default.
- W3209684920 cites W3035475567 @default.
- W3209684920 cites W3106013875 @default.
- W3209684920 cites W3112701542 @default.
- W3209684920 cites W3136424010 @default.
- W3209684920 cites W3148499377 @default.
- W3209684920 cites W3170554394 @default.
- W3209684920 cites W3186867303 @default.
- W3209684920 hasPublicationYear "2021" @default.
- W3209684920 type Work @default.
- W3209684920 sameAs 3209684920 @default.
- W3209684920 citedByCount "0" @default.
- W3209684920 crossrefType "posted-content" @default.
- W3209684920 hasAuthorship W3209684920A5017091430 @default.
- W3209684920 hasAuthorship W3209684920A5020035339 @default.
- W3209684920 hasAuthorship W3209684920A5034362557 @default.
- W3209684920 hasAuthorship W3209684920A5036099762 @default.
- W3209684920 hasAuthorship W3209684920A5059357294 @default.
- W3209684920 hasAuthorship W3209684920A5082142516 @default.
- W3209684920 hasAuthorship W3209684920A5085968028 @default.
- W3209684920 hasConcept C104317684 @default.
- W3209684920 hasConcept C119857082 @default.
- W3209684920 hasConcept C153180895 @default.
- W3209684920 hasConcept C154945302 @default.
- W3209684920 hasConcept C185592680 @default.
- W3209684920 hasConcept C199360897 @default.
- W3209684920 hasConcept C31972630 @default.
- W3209684920 hasConcept C41008148 @default.
- W3209684920 hasConcept C43521106 @default.
- W3209684920 hasConcept C55493867 @default.
- W3209684920 hasConcept C63479239 @default.
- W3209684920 hasConcept C81363708 @default.
- W3209684920 hasConcept C89600930 @default.
- W3209684920 hasConceptScore W3209684920C104317684 @default.
- W3209684920 hasConceptScore W3209684920C119857082 @default.
- W3209684920 hasConceptScore W3209684920C153180895 @default.
- W3209684920 hasConceptScore W3209684920C154945302 @default.
- W3209684920 hasConceptScore W3209684920C185592680 @default.
- W3209684920 hasConceptScore W3209684920C199360897 @default.
- W3209684920 hasConceptScore W3209684920C31972630 @default.
- W3209684920 hasConceptScore W3209684920C41008148 @default.
- W3209684920 hasConceptScore W3209684920C43521106 @default.
- W3209684920 hasConceptScore W3209684920C55493867 @default.
- W3209684920 hasConceptScore W3209684920C63479239 @default.
- W3209684920 hasConceptScore W3209684920C81363708 @default.
- W3209684920 hasConceptScore W3209684920C89600930 @default.
- W3209684920 hasLocation W32096849201 @default.
- W3209684920 hasOpenAccess W3209684920 @default.
- W3209684920 hasPrimaryLocation W32096849201 @default.
- W3209684920 hasRelatedWork W1679528986 @default.
- W3209684920 hasRelatedWork W2226808373 @default.
- W3209684920 hasRelatedWork W2432481613 @default.