FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297450596> ?p ?o ?g. }

• W4297450596 endingPage "222" @default.
• W4297450596 startingPage "213" @default.
• W4297450596 abstract "Acquiring incomplete k-space matrices is an effective way to accelerate Magnetic Resonance Imaging (MRI). It is an important and challenging task to accurately reconstruct images from such under-sampled k-space matrices. On the one hand, neither image-domain oriented nor frequency-domain oriented deep Convolutional Neural Networks can simultaneously employ both frequency features and spatial features for cooperatively improving reconstruction accuracy. On the other hand, existing dual-domain reconstruction methods adopt heavy encoder-decoder frameworks, resulting in low efficiency and information loss in the process of pooling. To deal with these problems, in this paper, we propose a full-resolution dual-domain reconstruction network, called DIIK-Net. The DIIK-Net consists of a full-resolution frequency-domain branch, a full-resolution image-domain branch, and cross-domain interaction modules between the two branches. The first novelty of the proposed method is that the features of each block of frequency-domain branch are extracted by 1×1 filters, which reduces computational cost and captures rich contextual information. Due to the fact that an element in frequency domain conveys information of the whole image, 1×1 convolutional blocks are able to extract large contextual information with the interaction of image domain. The second novelty is that the image-domain branch consists of a very small number of 3×3 convolutional blocks and each block has very large field of perception due to integration of frequency domain. The third novelty lies in the simple and effective cross-domain interaction module. Experimental results on the challenging fastMRI dataset demonstrate that the proposed method is capable of achieving higher reconstruction accuracy with a few number of parameters." @default.
• W4297450596 created "2022-09-28" @default.
• W4297450596 creator A5018073672 @default.
• W4297450596 creator A5049510575 @default.
• W4297450596 creator A5078121940 @default.
• W4297450596 creator A5082580072 @default.
• W4297450596 creator A5086887025 @default.
• W4297450596 date "2023-01-01" @default.
• W4297450596 modified "2023-10-18" @default.
• W4297450596 title "DIIK-Net: A full-resolution cross-domain deep interaction convolutional neural network for MR image reconstruction" @default.
• W4297450596 cites W1497904071 @default.
• W4297450596 cites W1758598986 @default.
• W4297450596 cites W2011181254 @default.
• W4297450596 cites W2073266250 @default.
• W4297450596 cites W2111388536 @default.
• W4297450596 cites W2117649283 @default.
• W4297450596 cites W2145020729 @default.
• W4297450596 cites W2330813655 @default.
• W4297450596 cites W2442117232 @default.
• W4297450596 cites W2594014149 @default.
• W4297450596 cites W2778924750 @default.
• W4297450596 cites W2791621240 @default.
• W4297450596 cites W2795380527 @default.
• W4297450596 cites W2883105305 @default.
• W4297450596 cites W2889937475 @default.
• W4297450596 cites W2900790473 @default.
• W4297450596 cites W2928045706 @default.
• W4297450596 cites W2963682501 @default.
• W4297450596 cites W2964859579 @default.
• W4297450596 cites W2972061446 @default.
• W4297450596 cites W3000764918 @default.
• W4297450596 cites W3000998666 @default.
• W4297450596 cites W3004715589 @default.
• W4297450596 cites W3022291895 @default.
• W4297450596 cites W3034546843 @default.
• W4297450596 cites W3045888007 @default.
• W4297450596 cites W3084719027 @default.
• W4297450596 cites W3110568504 @default.
• W4297450596 cites W3134103558 @default.
• W4297450596 cites W3202807692 @default.
• W4297450596 cites W3212593512 @default.
• W4297450596 cites W4200194904 @default.
• W4297450596 cites W4223589960 @default.
• W4297450596 cites W4226133625 @default.
• W4297450596 cites W4233764193 @default.
• W4297450596 cites W4249760698 @default.
• W4297450596 cites W4281606280 @default.
• W4297450596 cites W1587232669 @default.
• W4297450596 doi "https://doi.org/10.1016/j.neucom.2022.09.048" @default.
• W4297450596 hasPublicationYear "2023" @default.
• W4297450596 type Work @default.
• W4297450596 citedByCount "3" @default.
• W4297450596 countsByYear W42974505962023 @default.
• W4297450596 crossrefType "journal-article" @default.
• W4297450596 hasAuthorship W4297450596A5018073672 @default.
• W4297450596 hasAuthorship W4297450596A5049510575 @default.
• W4297450596 hasAuthorship W4297450596A5078121940 @default.
• W4297450596 hasAuthorship W4297450596A5082580072 @default.
• W4297450596 hasAuthorship W4297450596A5086887025 @default.
• W4297450596 hasConcept C11413529 @default.
• W4297450596 hasConcept C115961682 @default.
• W4297450596 hasConcept C134306372 @default.
• W4297450596 hasConcept C141379421 @default.
• W4297450596 hasConcept C153180895 @default.
• W4297450596 hasConcept C154945302 @default.
• W4297450596 hasConcept C19118579 @default.
• W4297450596 hasConcept C2524010 @default.
• W4297450596 hasConcept C2777210771 @default.
• W4297450596 hasConcept C31972630 @default.
• W4297450596 hasConcept C33923547 @default.
• W4297450596 hasConcept C36503486 @default.
• W4297450596 hasConcept C41008148 @default.
• W4297450596 hasConcept C70437156 @default.
• W4297450596 hasConcept C81363708 @default.
• W4297450596 hasConceptScore W4297450596C11413529 @default.
• W4297450596 hasConceptScore W4297450596C115961682 @default.
• W4297450596 hasConceptScore W4297450596C134306372 @default.
• W4297450596 hasConceptScore W4297450596C141379421 @default.
• W4297450596 hasConceptScore W4297450596C153180895 @default.
• W4297450596 hasConceptScore W4297450596C154945302 @default.
• W4297450596 hasConceptScore W4297450596C19118579 @default.
• W4297450596 hasConceptScore W4297450596C2524010 @default.
• W4297450596 hasConceptScore W4297450596C2777210771 @default.
• W4297450596 hasConceptScore W4297450596C31972630 @default.
• W4297450596 hasConceptScore W4297450596C33923547 @default.
• W4297450596 hasConceptScore W4297450596C36503486 @default.
• W4297450596 hasConceptScore W4297450596C41008148 @default.
• W4297450596 hasConceptScore W4297450596C70437156 @default.
• W4297450596 hasConceptScore W4297450596C81363708 @default.
• W4297450596 hasLocation W42974505961 @default.
• W4297450596 hasOpenAccess W4297450596 @default.
• W4297450596 hasPrimaryLocation W42974505961 @default.
• W4297450596 hasRelatedWork W2291847203 @default.
• W4297450596 hasRelatedWork W2424871898 @default.
• W4297450596 hasRelatedWork W2517027266 @default.
• W4297450596 hasRelatedWork W2756241593 @default.
• W4297450596 hasRelatedWork W2767651786 @default.
• W4297450596 hasRelatedWork W2912288872 @default.

• next