Matches in SemOpenAlex for { <https://semopenalex.org/work/W2773567899> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2773567899 abstract "Accelerating the data acquisition of dynamic magnetic resonance imaging (MRI) leads to a challenging ill-posed inverse problem, which has received great interest from both the signal processing and machine learning community over the last decades. The key ingredient to the problem is how to exploit the temporal correlation of the MR sequence to resolve the aliasing artefact. Traditionally, such observation led to a formulation of a non-convex optimisation problem, which were solved using iterative algorithms. Recently, however, deep learning based-approaches have gained significant popularity due to its ability to solve general inversion problems. In this work, we propose a unique, novel convolutional recurrent neural network (CRNN) architecture which reconstructs high quality cardiac MR images from highly undersampled k-space data by jointly exploiting the dependencies of the temporal sequences as well as the iterative nature of the traditional optimisation algorithms. In particular, the proposed architecture embeds the structure of the traditional iterative algorithms, efficiently modelling the recurrence of the iterative reconstruction stages by using recurrent hidden connections over such iterations. In addition, spatiotemporal dependencies are simultaneously learnt by exploiting bidirectional recurrent hidden connections across time sequences. The proposed algorithm is able to learn both the temporal dependency and the iterative reconstruction process effectively with only a very small number of parameters, while outperforming current MR reconstruction methods in terms of computational complexity, reconstruction accuracy and speed." @default.
- W2773567899 created "2017-12-22" @default.
- W2773567899 creator A5000486289 @default.
- W2773567899 creator A5006461848 @default.
- W2773567899 creator A5010565192 @default.
- W2773567899 creator A5028293439 @default.
- W2773567899 creator A5037038047 @default.
- W2773567899 creator A5057304825 @default.
- W2773567899 date "2017-12-05" @default.
- W2773567899 modified "2023-09-24" @default.
- W2773567899 title "Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction" @default.
- W2773567899 cites W1677182931 @default.
- W2773567899 cites W1850742715 @default.
- W2773567899 cites W1901129140 @default.
- W2773567899 cites W1934184906 @default.
- W2773567899 cites W2110485445 @default.
- W2773567899 cites W2117882039 @default.
- W2773567899 cites W2155268695 @default.
- W2773567899 cites W2156739854 @default.
- W2773567899 cites W2168668658 @default.
- W2773567899 cites W2168903001 @default.
- W2773567899 cites W2184360182 @default.
- W2773567899 cites W2342171291 @default.
- W2773567899 cites W2552808051 @default.
- W2773567899 cites W2592358735 @default.
- W2773567899 cites W2593222352 @default.
- W2773567899 cites W2594014149 @default.
- W2773567899 cites W2605364158 @default.
- W2773567899 cites W2770205545 @default.
- W2773567899 cites W2950936580 @default.
- W2773567899 cites W2951070760 @default.
- W2773567899 cites W2952781412 @default.
- W2773567899 cites W2964121744 @default.
- W2773567899 cites W3101765447 @default.
- W2773567899 cites W3103586216 @default.
- W2773567899 cites W54257720 @default.
- W2773567899 doi "https://doi.org/10.48550/arxiv.1712.01751" @default.
- W2773567899 hasPublicationYear "2017" @default.
- W2773567899 type Work @default.
- W2773567899 sameAs 2773567899 @default.
- W2773567899 citedByCount "1" @default.
- W2773567899 countsByYear W27735678992018 @default.
- W2773567899 crossrefType "posted-content" @default.
- W2773567899 hasAuthorship W2773567899A5000486289 @default.
- W2773567899 hasAuthorship W2773567899A5006461848 @default.
- W2773567899 hasAuthorship W2773567899A5010565192 @default.
- W2773567899 hasAuthorship W2773567899A5028293439 @default.
- W2773567899 hasAuthorship W2773567899A5037038047 @default.
- W2773567899 hasAuthorship W2773567899A5057304825 @default.
- W2773567899 hasBestOaLocation W27735678991 @default.
- W2773567899 hasConcept C108583219 @default.
- W2773567899 hasConcept C11413529 @default.
- W2773567899 hasConcept C115903868 @default.
- W2773567899 hasConcept C134306372 @default.
- W2773567899 hasConcept C135252773 @default.
- W2773567899 hasConcept C141379421 @default.
- W2773567899 hasConcept C143587482 @default.
- W2773567899 hasConcept C147168706 @default.
- W2773567899 hasConcept C153180895 @default.
- W2773567899 hasConcept C154945302 @default.
- W2773567899 hasConcept C159694833 @default.
- W2773567899 hasConcept C33923547 @default.
- W2773567899 hasConcept C41008148 @default.
- W2773567899 hasConcept C50644808 @default.
- W2773567899 hasConcept C81363708 @default.
- W2773567899 hasConceptScore W2773567899C108583219 @default.
- W2773567899 hasConceptScore W2773567899C11413529 @default.
- W2773567899 hasConceptScore W2773567899C115903868 @default.
- W2773567899 hasConceptScore W2773567899C134306372 @default.
- W2773567899 hasConceptScore W2773567899C135252773 @default.
- W2773567899 hasConceptScore W2773567899C141379421 @default.
- W2773567899 hasConceptScore W2773567899C143587482 @default.
- W2773567899 hasConceptScore W2773567899C147168706 @default.
- W2773567899 hasConceptScore W2773567899C153180895 @default.
- W2773567899 hasConceptScore W2773567899C154945302 @default.
- W2773567899 hasConceptScore W2773567899C159694833 @default.
- W2773567899 hasConceptScore W2773567899C33923547 @default.
- W2773567899 hasConceptScore W2773567899C41008148 @default.
- W2773567899 hasConceptScore W2773567899C50644808 @default.
- W2773567899 hasConceptScore W2773567899C81363708 @default.
- W2773567899 hasLocation W27735678991 @default.
- W2773567899 hasLocation W27735678992 @default.
- W2773567899 hasOpenAccess W2773567899 @default.
- W2773567899 hasPrimaryLocation W27735678991 @default.
- W2773567899 hasRelatedWork W2121460486 @default.
- W2773567899 hasRelatedWork W2532315310 @default.
- W2773567899 hasRelatedWork W2731899572 @default.
- W2773567899 hasRelatedWork W2999805992 @default.
- W2773567899 hasRelatedWork W3116150086 @default.
- W2773567899 hasRelatedWork W3133861977 @default.
- W2773567899 hasRelatedWork W3205591509 @default.
- W2773567899 hasRelatedWork W4200173597 @default.
- W2773567899 hasRelatedWork W4312417841 @default.
- W2773567899 hasRelatedWork W4321369474 @default.
- W2773567899 isParatext "false" @default.
- W2773567899 isRetracted "false" @default.
- W2773567899 magId "2773567899" @default.
- W2773567899 workType "article" @default.