FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048371841> ?p ?o ?g. }

• W3048371841 abstract "Self-supervised learning has shown great promise because of its ability to train deep learning (DL) magnetic resonance imaging (MRI) reconstruction methods without fully sampled data. Current self-supervised learning methods for physics-guided reconstruction networks split acquired undersampled data into two disjoint sets, where one is used for data consistency (DC) in the unrolled network, while the other is used to define the training loss. In this study, we propose an improved self-supervised learning strategy that more efficiently uses the acquired data to train a physics-guided reconstruction network without a database of fully sampled data. The proposed multi-mask self-supervised learning via data undersampling (SSDU) applies a holdout masking operation on the acquired measurements to split them into multiple pairs of disjoint sets for each training sample, while using one of these pairs for DC units and the other for defining loss, thereby more efficiently using the undersampled data. Multi-mask SSDU is applied on fully sampled 3D knee and prospectively undersampled 3D brain MRI datasets, for various acceleration rates and patterns, and compared with the parallel imaging method, CG-SENSE, and single-mask SSDU DL-MRI, as well as supervised DL-MRI when fully sampled data are available. The results on knee MRI show that the proposed multi-mask SSDU outperforms SSDU and performs as well as supervised DL-MRI. A clinical reader study further ranks the multi-mask SSDU higher than supervised DL-MRI in terms of signal-to-noise ratio and aliasing artifacts. Results on brain MRI show that multi-mask SSDU achieves better reconstruction quality compared with SSDU. The reader study demonstrates that multi-mask SSDU at R = 8 significantly improves reconstruction compared with single-mask SSDU at R = 8, as well as CG-SENSE at R = 2." @default.
• W3048371841 created "2020-08-18" @default.
• W3048371841 creator A5031984988 @default.
• W3048371841 creator A5038369687 @default.
• W3048371841 creator A5044571053 @default.
• W3048371841 creator A5054800712 @default.
• W3048371841 creator A5070460781 @default.
• W3048371841 creator A5086301767 @default.
• W3048371841 date "2022-07-17" @default.
• W3048371841 modified "2023-10-17" @default.
• W3048371841 title "Multi‐mask self‐supervised learning for physics‐guided neural networks in highly accelerated magnetic resonance imaging" @default.
• W3048371841 cites W1959447026 @default.
• W3048371841 cites W1987263024 @default.
• W3048371841 cites W1993053013 @default.
• W3048371841 cites W2006330194 @default.
• W3048371841 cites W2042965174 @default.
• W3048371841 cites W2047544187 @default.
• W3048371841 cites W2070678378 @default.
• W3048371841 cites W2101675075 @default.
• W3048371841 cites W2107906890 @default.
• W3048371841 cites W2111388536 @default.
• W3048371841 cites W2117649283 @default.
• W3048371841 cites W2132122471 @default.
• W3048371841 cites W2159285706 @default.
• W3048371841 cites W2160288818 @default.
• W3048371841 cites W2160566999 @default.
• W3048371841 cites W2170059438 @default.
• W3048371841 cites W2331924070 @default.
• W3048371841 cites W2442117232 @default.
• W3048371841 cites W2604388535 @default.
• W3048371841 cites W2755115574 @default.
• W3048371841 cites W2889995282 @default.
• W3048371841 cites W2910683834 @default.
• W3048371841 cites W2962734274 @default.
• W3048371841 cites W2964013315 @default.
• W3048371841 cites W2979878910 @default.
• W3048371841 cites W2980318461 @default.
• W3048371841 cites W2996927594 @default.
• W3048371841 cites W2999167634 @default.
• W3048371841 cites W2999511788 @default.
• W3048371841 cites W3001319253 @default.
• W3048371841 cites W3012209675 @default.
• W3048371841 cites W3015212533 @default.
• W3048371841 cites W3034781633 @default.
• W3048371841 cites W3035524453 @default.
• W3048371841 cites W3035596626 @default.
• W3048371841 cites W3039236647 @default.
• W3048371841 cites W3041018972 @default.
• W3048371841 cites W3045099931 @default.
• W3048371841 cites W3048371841 @default.
• W3048371841 cites W3048384642 @default.
• W3048371841 cites W3097192134 @default.
• W3048371841 cites W3100075319 @default.
• W3048371841 cites W3100730608 @default.
• W3048371841 cites W3101847293 @default.
• W3048371841 cites W3133902371 @default.
• W3048371841 cites W3162880680 @default.
• W3048371841 cites W3176923149 @default.
• W3048371841 cites W3188455524 @default.
• W3048371841 cites W4213412343 @default.
• W3048371841 cites W4226133625 @default.
• W3048371841 cites W4249760698 @default.
• W3048371841 doi "https://doi.org/10.1002/nbm.4798" @default.
• W3048371841 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35789133" @default.
• W3048371841 hasPublicationYear "2022" @default.
• W3048371841 type Work @default.
• W3048371841 sameAs 3048371841 @default.
• W3048371841 citedByCount "10" @default.
• W3048371841 countsByYear W30483718412021 @default.
• W3048371841 countsByYear W30483718412022 @default.
• W3048371841 countsByYear W30483718412023 @default.
• W3048371841 crossrefType "journal-article" @default.
• W3048371841 hasAuthorship W3048371841A5031984988 @default.
• W3048371841 hasAuthorship W3048371841A5038369687 @default.
• W3048371841 hasAuthorship W3048371841A5044571053 @default.
• W3048371841 hasAuthorship W3048371841A5054800712 @default.
• W3048371841 hasAuthorship W3048371841A5070460781 @default.
• W3048371841 hasAuthorship W3048371841A5086301767 @default.
• W3048371841 hasBestOaLocation W30483718411 @default.
• W3048371841 hasConcept C108583219 @default.
• W3048371841 hasConcept C111919701 @default.
• W3048371841 hasConcept C114614502 @default.
• W3048371841 hasConcept C119857082 @default.
• W3048371841 hasConcept C124851039 @default.
• W3048371841 hasConcept C126838900 @default.
• W3048371841 hasConcept C136389625 @default.
• W3048371841 hasConcept C136536468 @default.
• W3048371841 hasConcept C143409427 @default.
• W3048371841 hasConcept C153180895 @default.
• W3048371841 hasConcept C154945302 @default.
• W3048371841 hasConcept C33923547 @default.
• W3048371841 hasConcept C4069607 @default.
• W3048371841 hasConcept C41008148 @default.
• W3048371841 hasConcept C45340560 @default.
• W3048371841 hasConcept C50644808 @default.
• W3048371841 hasConcept C71924100 @default.
• W3048371841 hasConcept C93361087 @default.
• W3048371841 hasConceptScore W3048371841C108583219 @default.
• W3048371841 hasConceptScore W3048371841C111919701 @default.
• W3048371841 hasConceptScore W3048371841C114614502 @default.

• next