Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200922958> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3200922958 endingPage "54" @default.
- W3200922958 startingPage "44" @default.
- W3200922958 abstract "Multi-modal and multi-contrast imaging datasets have diverse voxel-wise intensities. For example, quantitative MRI acquisition protocols are designed specifically to yield multiple images with widely-varying contrast that inform models relating MR signals to tissue characteristics. The large variance across images in such data prevents the use of standard normalisation techniques, making super resolution highly challenging. We propose a novel self-supervised mixture-of-experts (SS-MoE) paradigm for deep neural networks, and hence present a method enabling improved super resolution of data where image intensities are diverse and have large variance. Unlike the conventional MoE that automatically aggregates expert results for each input, we explicitly assign an input to the corresponding expert based on the predictive pseudo error labels in a self-supervised fashion. A new gater module is trained to discriminate the error levels of inputs estimated by Multiscale Quantile Segmentation. We show that our new paradigm reduces the error and improves the robustness when super resolving combined diffusion-relaxometry MRI data from the Super MUDI dataset. Our approach is suitable for a wide range of quantitative MRI techniques, and multi-contrast or multi-modal imaging techniques in general. It could be applied to super resolve images with inadequate resolution, or reduce the scanning time needed to acquire images of the required resolution. The source code and the trained models are available at https://github.com/hongxiangharry/SS-MoE." @default.
- W3200922958 created "2021-09-27" @default.
- W3200922958 creator A5025866366 @default.
- W3200922958 creator A5033449704 @default.
- W3200922958 creator A5047882326 @default.
- W3200922958 creator A5087083706 @default.
- W3200922958 date "2021-01-01" @default.
- W3200922958 modified "2023-09-23" @default.
- W3200922958 title "Generalised Super Resolution for Quantitative MRI Using Self-supervised Mixture of Experts" @default.
- W3200922958 cites W2024729467 @default.
- W3200922958 cites W2150884987 @default.
- W3200922958 cites W2194775991 @default.
- W3200922958 cites W2462044004 @default.
- W3200922958 cites W2503339013 @default.
- W3200922958 cites W2591999117 @default.
- W3200922958 cites W2610571781 @default.
- W3200922958 cites W2625354324 @default.
- W3200922958 cites W2791626939 @default.
- W3200922958 cites W2885097243 @default.
- W3200922958 cites W2903804687 @default.
- W3200922958 cites W2939984249 @default.
- W3200922958 cites W2953031404 @default.
- W3200922958 cites W2953427271 @default.
- W3200922958 cites W2963254338 @default.
- W3200922958 cites W2963731031 @default.
- W3200922958 cites W2964297772 @default.
- W3200922958 cites W2982362131 @default.
- W3200922958 cites W3011648454 @default.
- W3200922958 cites W3021820897 @default.
- W3200922958 cites W3031827021 @default.
- W3200922958 cites W3092596753 @default.
- W3200922958 cites W3102018640 @default.
- W3200922958 cites W3113090360 @default.
- W3200922958 cites W3203113855 @default.
- W3200922958 doi "https://doi.org/10.1007/978-3-030-87231-1_5" @default.
- W3200922958 hasPublicationYear "2021" @default.
- W3200922958 type Work @default.
- W3200922958 sameAs 3200922958 @default.
- W3200922958 citedByCount "2" @default.
- W3200922958 countsByYear W32009229582023 @default.
- W3200922958 crossrefType "book-chapter" @default.
- W3200922958 hasAuthorship W3200922958A5025866366 @default.
- W3200922958 hasAuthorship W3200922958A5033449704 @default.
- W3200922958 hasAuthorship W3200922958A5047882326 @default.
- W3200922958 hasAuthorship W3200922958A5087083706 @default.
- W3200922958 hasBestOaLocation W32009229582 @default.
- W3200922958 hasConcept C104317684 @default.
- W3200922958 hasConcept C121955636 @default.
- W3200922958 hasConcept C144133560 @default.
- W3200922958 hasConcept C153180895 @default.
- W3200922958 hasConcept C154945302 @default.
- W3200922958 hasConcept C185592680 @default.
- W3200922958 hasConcept C196083921 @default.
- W3200922958 hasConcept C2776502983 @default.
- W3200922958 hasConcept C41008148 @default.
- W3200922958 hasConcept C54170458 @default.
- W3200922958 hasConcept C55493867 @default.
- W3200922958 hasConcept C63479239 @default.
- W3200922958 hasConcept C89600930 @default.
- W3200922958 hasConceptScore W3200922958C104317684 @default.
- W3200922958 hasConceptScore W3200922958C121955636 @default.
- W3200922958 hasConceptScore W3200922958C144133560 @default.
- W3200922958 hasConceptScore W3200922958C153180895 @default.
- W3200922958 hasConceptScore W3200922958C154945302 @default.
- W3200922958 hasConceptScore W3200922958C185592680 @default.
- W3200922958 hasConceptScore W3200922958C196083921 @default.
- W3200922958 hasConceptScore W3200922958C2776502983 @default.
- W3200922958 hasConceptScore W3200922958C41008148 @default.
- W3200922958 hasConceptScore W3200922958C54170458 @default.
- W3200922958 hasConceptScore W3200922958C55493867 @default.
- W3200922958 hasConceptScore W3200922958C63479239 @default.
- W3200922958 hasConceptScore W3200922958C89600930 @default.
- W3200922958 hasLocation W32009229581 @default.
- W3200922958 hasLocation W32009229582 @default.
- W3200922958 hasLocation W32009229583 @default.
- W3200922958 hasOpenAccess W3200922958 @default.
- W3200922958 hasPrimaryLocation W32009229581 @default.
- W3200922958 hasRelatedWork W118753260 @default.
- W3200922958 hasRelatedWork W2041273352 @default.
- W3200922958 hasRelatedWork W2091724545 @default.
- W3200922958 hasRelatedWork W2146691973 @default.
- W3200922958 hasRelatedWork W2510758617 @default.
- W3200922958 hasRelatedWork W2673946014 @default.
- W3200922958 hasRelatedWork W2753174232 @default.
- W3200922958 hasRelatedWork W2897195263 @default.
- W3200922958 hasRelatedWork W3015910149 @default.
- W3200922958 hasRelatedWork W4206076898 @default.
- W3200922958 isParatext "false" @default.
- W3200922958 isRetracted "false" @default.
- W3200922958 magId "3200922958" @default.
- W3200922958 workType "book-chapter" @default.