FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328127106> ?p ?o ?g. }

• W4328127106 abstract "Abstract Background Recent convolutional neural network (CNN) performs low-error reconstruction in fast magnetic resonance imaging (MRI). Most of them convolve the image with kernels and have successfully explored the local information. However, the non-local image information, which is embed among image patches that are relatively far from each other, may be lost since the convolution kernel size is usually small. We aim to incorporate a graph to represent non-local information, and improve the reconstructed images by Enhanced Self-Similarity Using Graph Convolutional Network (GCESS). Methods First, image is reconstructed into graph to extract the non-local self-similarity in the image. Second, GCESS uses graph convolution and spatial convolution to process the information in the image, so that local and non-local information can be effectively utilized. The network strengthens the non-local similarity between similar image patches while reconstructing images, making the reconstruction details more reliable. Results Experimental results on in vivo knee and brain data demonstrate that the proposed method achieves better artifacts suppression and details preservation than state-of-the-art methods, both visually and quantitatively. Under 1D Cartesian sampling with 4x acceleration (AF=4), the PSNR of knee data reached 34.19 dB, 1.05 dB higher than that of the compared methods; the SSIM achieved 0.8994, 2% higher than the compared methods. Similar results were obtained for the reconstructed images under other sampling templates as demonstrated in our experiment. Conclusions The proposed method successfully construct a hybrid graph convolution and spatial convolution network to reconstruct images. Along with the network training, the non-local self-similarities are enhanced, and will benefit the image details reconstruction. Experiments demonstrate that the proposed method outperforms the state-of-the-art reconstruction method in suppressing artifacts, as well as in preserving image details." @default.
• W4328127106 created "2023-03-22" @default.
• W4328127106 creator A5013555971 @default.
• W4328127106 creator A5020623402 @default.
• W4328127106 creator A5032730480 @default.
• W4328127106 creator A5036516823 @default.
• W4328127106 creator A5046887099 @default.
• W4328127106 creator A5054297041 @default.
• W4328127106 creator A5080788001 @default.
• W4328127106 date "2023-03-21" @default.
• W4328127106 modified "2023-10-18" @default.
• W4328127106 title "MRI Reconstruction with Enhanced Self-Similarity Using Graph Convolutional Network" @default.
• W4328127106 cites W2021942040 @default.
• W4328127106 cites W2047544187 @default.
• W4328127106 cites W2051398769 @default.
• W4328127106 cites W2079929986 @default.
• W4328127106 cites W2093621384 @default.
• W4328127106 cites W2101675075 @default.
• W4328127106 cites W2117649283 @default.
• W4328127106 cites W2133665775 @default.
• W4328127106 cites W2158787690 @default.
• W4328127106 cites W2168668658 @default.
• W4328127106 cites W2191349405 @default.
• W4328127106 cites W2604388535 @default.
• W4328127106 cites W2610522009 @default.
• W4328127106 cites W2611467245 @default.
• W4328127106 cites W2763211003 @default.
• W4328127106 cites W3001554227 @default.
• W4328127106 cites W3035990856 @default.
• W4328127106 cites W3044508608 @default.
• W4328127106 cites W3089225552 @default.
• W4328127106 cites W3100730608 @default.
• W4328127106 cites W3183777577 @default.
• W4328127106 cites W4200635639 @default.
• W4328127106 cites W4322490801 @default.
• W4328127106 cites W639708223 @default.
• W4328127106 doi "https://doi.org/10.21203/rs.3.rs-2702846/v1" @default.
• W4328127106 hasPublicationYear "2023" @default.
• W4328127106 type Work @default.
• W4328127106 citedByCount "0" @default.
• W4328127106 crossrefType "posted-content" @default.
• W4328127106 hasAuthorship W4328127106A5013555971 @default.
• W4328127106 hasAuthorship W4328127106A5020623402 @default.
• W4328127106 hasAuthorship W4328127106A5032730480 @default.
• W4328127106 hasAuthorship W4328127106A5036516823 @default.
• W4328127106 hasAuthorship W4328127106A5046887099 @default.
• W4328127106 hasAuthorship W4328127106A5054297041 @default.
• W4328127106 hasAuthorship W4328127106A5080788001 @default.
• W4328127106 hasBestOaLocation W43281271061 @default.
• W4328127106 hasConcept C103278499 @default.
• W4328127106 hasConcept C114614502 @default.
• W4328127106 hasConcept C115961682 @default.
• W4328127106 hasConcept C132525143 @default.
• W4328127106 hasConcept C141379421 @default.
• W4328127106 hasConcept C153180895 @default.
• W4328127106 hasConcept C154945302 @default.
• W4328127106 hasConcept C205372480 @default.
• W4328127106 hasConcept C31972630 @default.
• W4328127106 hasConcept C33923547 @default.
• W4328127106 hasConcept C41008148 @default.
• W4328127106 hasConcept C45347329 @default.
• W4328127106 hasConcept C50644808 @default.
• W4328127106 hasConcept C74193536 @default.
• W4328127106 hasConcept C80444323 @default.
• W4328127106 hasConcept C81363708 @default.
• W4328127106 hasConceptScore W4328127106C103278499 @default.
• W4328127106 hasConceptScore W4328127106C114614502 @default.
• W4328127106 hasConceptScore W4328127106C115961682 @default.
• W4328127106 hasConceptScore W4328127106C132525143 @default.
• W4328127106 hasConceptScore W4328127106C141379421 @default.
• W4328127106 hasConceptScore W4328127106C153180895 @default.
• W4328127106 hasConceptScore W4328127106C154945302 @default.
• W4328127106 hasConceptScore W4328127106C205372480 @default.
• W4328127106 hasConceptScore W4328127106C31972630 @default.
• W4328127106 hasConceptScore W4328127106C33923547 @default.
• W4328127106 hasConceptScore W4328127106C41008148 @default.
• W4328127106 hasConceptScore W4328127106C45347329 @default.
• W4328127106 hasConceptScore W4328127106C50644808 @default.
• W4328127106 hasConceptScore W4328127106C74193536 @default.
• W4328127106 hasConceptScore W4328127106C80444323 @default.
• W4328127106 hasConceptScore W4328127106C81363708 @default.
• W4328127106 hasLocation W43281271061 @default.
• W4328127106 hasOpenAccess W4328127106 @default.
• W4328127106 hasPrimaryLocation W43281271061 @default.
• W4328127106 hasRelatedWork W2000166524 @default.
• W4328127106 hasRelatedWork W2099840350 @default.
• W4328127106 hasRelatedWork W2810384904 @default.
• W4328127106 hasRelatedWork W2949189996 @default.
• W4328127106 hasRelatedWork W3004564283 @default.
• W4328127106 hasRelatedWork W3093612317 @default.
• W4328127106 hasRelatedWork W3200375696 @default.
• W4328127106 hasRelatedWork W4293794540 @default.
• W4328127106 hasRelatedWork W4312417841 @default.
• W4328127106 hasRelatedWork W4319071265 @default.
• W4328127106 isParatext "false" @default.
• W4328127106 isRetracted "false" @default.
• W4328127106 workType "article" @default.