Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198792130> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3198792130 abstract "Deep neural networks have been extensively studied for undersampled MRI reconstruction. While achieving state-of-the-art performance, they are trained and deployed specifically for one anatomy with limited generalization ability to another anatomy. Rather than building multiple models, a universal model that reconstructs images across different anatomies is highly desirable for efficient deployment and better generalization. Simply mixing images from multiple anatomies for training a single network does not lead to an ideal universal model due to the statistical shift among datasets of various anatomies, the need to retrain from scratch on all datasets with the addition of a new dataset, and the difficulty in dealing with imbalanced sampling when the new dataset is further of a smaller size. In this paper, for the first time, we propose a framework to learn a universal deep neural network for undersampled MRI reconstruction. Specifically, anatomy-specific instance normalization is proposed to compensate for statistical shift and allow easy generalization to new datasets. Moreover, the universal model is trained by distilling knowledge from available independent models to further exploit representations across anatomies. Experimental results show the proposed universal model can reconstruct both brain and knee images with high image quality. Also, it is easy to adapt the trained model to new datasets of smaller size, i.e., abdomen, cardiac and prostate, with little effort and superior performance." @default.
- W3198792130 created "2021-09-13" @default.
- W3198792130 creator A5019104510 @default.
- W3198792130 creator A5032775389 @default.
- W3198792130 creator A5037677450 @default.
- W3198792130 creator A5060470951 @default.
- W3198792130 date "2021-03-08" @default.
- W3198792130 modified "2023-09-25" @default.
- W3198792130 title "Universal Undersampled MRI Reconstruction" @default.
- W3198792130 cites W2101675075 @default.
- W3198792130 cites W2442117232 @default.
- W3198792130 cites W2502312327 @default.
- W3198792130 cites W2552808051 @default.
- W3198792130 cites W2594014149 @default.
- W3198792130 cites W2603777577 @default.
- W3198792130 cites W2604388535 @default.
- W3198792130 cites W2778924750 @default.
- W3198792130 cites W2804047627 @default.
- W3198792130 cites W2804263814 @default.
- W3198792130 cites W2900756484 @default.
- W3198792130 cites W2915126261 @default.
- W3198792130 cites W2917020315 @default.
- W3198792130 cites W2962734274 @default.
- W3198792130 cites W2964308363 @default.
- W3198792130 cites W2979447087 @default.
- W3198792130 cites W2988306446 @default.
- W3198792130 cites W2996927594 @default.
- W3198792130 cites W2999511788 @default.
- W3198792130 cites W3002569343 @default.
- W3198792130 cites W3003650457 @default.
- W3198792130 cites W3034223847 @default.
- W3198792130 cites W3034546843 @default.
- W3198792130 cites W3092530614 @default.
- W3198792130 cites W3100730608 @default.
- W3198792130 cites W3110024720 @default.
- W3198792130 cites W3134475970 @default.
- W3198792130 doi "https://doi.org/10.48550/arxiv.2103.05214" @default.
- W3198792130 hasPublicationYear "2021" @default.
- W3198792130 type Work @default.
- W3198792130 sameAs 3198792130 @default.
- W3198792130 citedByCount "0" @default.
- W3198792130 crossrefType "posted-content" @default.
- W3198792130 hasAuthorship W3198792130A5019104510 @default.
- W3198792130 hasAuthorship W3198792130A5032775389 @default.
- W3198792130 hasAuthorship W3198792130A5037677450 @default.
- W3198792130 hasAuthorship W3198792130A5060470951 @default.
- W3198792130 hasBestOaLocation W31987921301 @default.
- W3198792130 hasConcept C119857082 @default.
- W3198792130 hasConcept C126838900 @default.
- W3198792130 hasConcept C134306372 @default.
- W3198792130 hasConcept C136886441 @default.
- W3198792130 hasConcept C143409427 @default.
- W3198792130 hasConcept C144024400 @default.
- W3198792130 hasConcept C153180895 @default.
- W3198792130 hasConcept C154945302 @default.
- W3198792130 hasConcept C165696696 @default.
- W3198792130 hasConcept C177148314 @default.
- W3198792130 hasConcept C19165224 @default.
- W3198792130 hasConcept C2984842247 @default.
- W3198792130 hasConcept C2988762625 @default.
- W3198792130 hasConcept C33923547 @default.
- W3198792130 hasConcept C38652104 @default.
- W3198792130 hasConcept C41008148 @default.
- W3198792130 hasConcept C50644808 @default.
- W3198792130 hasConcept C71924100 @default.
- W3198792130 hasConceptScore W3198792130C119857082 @default.
- W3198792130 hasConceptScore W3198792130C126838900 @default.
- W3198792130 hasConceptScore W3198792130C134306372 @default.
- W3198792130 hasConceptScore W3198792130C136886441 @default.
- W3198792130 hasConceptScore W3198792130C143409427 @default.
- W3198792130 hasConceptScore W3198792130C144024400 @default.
- W3198792130 hasConceptScore W3198792130C153180895 @default.
- W3198792130 hasConceptScore W3198792130C154945302 @default.
- W3198792130 hasConceptScore W3198792130C165696696 @default.
- W3198792130 hasConceptScore W3198792130C177148314 @default.
- W3198792130 hasConceptScore W3198792130C19165224 @default.
- W3198792130 hasConceptScore W3198792130C2984842247 @default.
- W3198792130 hasConceptScore W3198792130C2988762625 @default.
- W3198792130 hasConceptScore W3198792130C33923547 @default.
- W3198792130 hasConceptScore W3198792130C38652104 @default.
- W3198792130 hasConceptScore W3198792130C41008148 @default.
- W3198792130 hasConceptScore W3198792130C50644808 @default.
- W3198792130 hasConceptScore W3198792130C71924100 @default.
- W3198792130 hasLocation W31987921301 @default.
- W3198792130 hasOpenAccess W3198792130 @default.
- W3198792130 hasPrimaryLocation W31987921301 @default.
- W3198792130 hasRelatedWork W1863050261 @default.
- W3198792130 hasRelatedWork W1991269640 @default.
- W3198792130 hasRelatedWork W2016839265 @default.
- W3198792130 hasRelatedWork W2018445155 @default.
- W3198792130 hasRelatedWork W2058991683 @default.
- W3198792130 hasRelatedWork W2626335822 @default.
- W3198792130 hasRelatedWork W2946038180 @default.
- W3198792130 hasRelatedWork W1629725936 @default.
- W3198792130 hasRelatedWork W2185993203 @default.
- W3198792130 hasRelatedWork W2508457823 @default.
- W3198792130 isParatext "false" @default.
- W3198792130 isRetracted "false" @default.
- W3198792130 magId "3198792130" @default.
- W3198792130 workType "article" @default.