Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904707615> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2904707615 abstract "Deep learning holds great promise in the reconstruction of undersampled Magnetic Resonance Imaging (MRI) data, providing new opportunities to escalate the performance of rapid MRI. In existing deep learning-based reconstruction methods, supervised training is performed using artifact-free reference images and their corresponding undersampled pairs. The undersampled images are generated by a fixed undersampling pattern in the training, and the trained network is then applied to reconstruct new images acquired with the same pattern in the inference. While such a training strategy can maintain a favorable reconstruction for a pre-selected undersampling pattern, the robustness of the trained network against any discrepancy of undersampling schemes is typically poor. We developed a novel deep learning-based reconstruction framework called SANTIS for efficient MR image reconstruction with improved robustness against sampling pattern discrepancy. SANTIS uses a data cycle-consistent adversarial network combining efficient end-to-end convolutional neural network mapping, data fidelity enforcement and adversarial training for reconstructing accelerated MR images more faithfully. A training strategy employing sampling augmentation with extensive variation of undersampling patterns was further introduced to promote the robustness of the trained network. Compared to conventional reconstruction and standard deep learning methods, SANTIS achieved consistent better reconstruction performance, with lower errors, greater image sharpness and higher similarity with respect to the reference regardless of the undersampling patterns during inference. This novel concept behind SANTIS can particularly be useful towards improving the robustness of deep learning-based image reconstruction against discrepancy between training and evaluation, which is currently an important but less studied open question." @default.
- W2904707615 created "2018-12-22" @default.
- W2904707615 creator A5039127636 @default.
- W2904707615 creator A5047282717 @default.
- W2904707615 creator A5060273388 @default.
- W2904707615 creator A5087257261 @default.
- W2904707615 date "2018-12-08" @default.
- W2904707615 modified "2023-09-26" @default.
- W2904707615 title "SANTIS: Sampling-Augmented Neural neTwork with Incoherent Structure for MR image reconstruction" @default.
- W2904707615 cites W1482297123 @default.
- W2904707615 cites W1514015969 @default.
- W2904707615 cites W1677182931 @default.
- W2904707615 cites W1901129140 @default.
- W2904707615 cites W1979954835 @default.
- W2904707615 cites W2047544187 @default.
- W2904707615 cites W2101584562 @default.
- W2904707615 cites W2101675075 @default.
- W2904707615 cites W2105199122 @default.
- W2904707615 cites W2111388536 @default.
- W2904707615 cites W2323929895 @default.
- W2904707615 cites W2493683088 @default.
- W2904707615 cites W2556016755 @default.
- W2904707615 cites W2559794190 @default.
- W2904707615 cites W2594014149 @default.
- W2904707615 cites W2604388535 @default.
- W2904707615 cites W2608231518 @default.
- W2904707615 cites W2611467245 @default.
- W2904707615 cites W2737373222 @default.
- W2904707615 cites W2770723355 @default.
- W2904707615 cites W2778924750 @default.
- W2904707615 cites W2789565832 @default.
- W2904707615 cites W2791621240 @default.
- W2904707615 cites W2794613614 @default.
- W2904707615 cites W2794990008 @default.
- W2904707615 cites W2795380527 @default.
- W2904707615 cites W2803328900 @default.
- W2904707615 cites W2804263814 @default.
- W2904707615 cites W2885303411 @default.
- W2904707615 cites W2886281300 @default.
- W2904707615 cites W2962793481 @default.
- W2904707615 cites W2964308363 @default.
- W2904707615 cites W2093641699 @default.
- W2904707615 cites W2168887049 @default.
- W2904707615 doi "https://doi.org/10.48550/arxiv.1812.03278" @default.
- W2904707615 hasPublicationYear "2018" @default.
- W2904707615 type Work @default.
- W2904707615 sameAs 2904707615 @default.
- W2904707615 citedByCount "0" @default.
- W2904707615 crossrefType "posted-content" @default.
- W2904707615 hasAuthorship W2904707615A5039127636 @default.
- W2904707615 hasAuthorship W2904707615A5047282717 @default.
- W2904707615 hasAuthorship W2904707615A5060273388 @default.
- W2904707615 hasAuthorship W2904707615A5087257261 @default.
- W2904707615 hasBestOaLocation W29047076151 @default.
- W2904707615 hasConcept C104317684 @default.
- W2904707615 hasConcept C108583219 @default.
- W2904707615 hasConcept C136536468 @default.
- W2904707615 hasConcept C141379421 @default.
- W2904707615 hasConcept C153180895 @default.
- W2904707615 hasConcept C154945302 @default.
- W2904707615 hasConcept C185592680 @default.
- W2904707615 hasConcept C2776214188 @default.
- W2904707615 hasConcept C31972630 @default.
- W2904707615 hasConcept C41008148 @default.
- W2904707615 hasConcept C50644808 @default.
- W2904707615 hasConcept C55493867 @default.
- W2904707615 hasConcept C63479239 @default.
- W2904707615 hasConcept C81363708 @default.
- W2904707615 hasConceptScore W2904707615C104317684 @default.
- W2904707615 hasConceptScore W2904707615C108583219 @default.
- W2904707615 hasConceptScore W2904707615C136536468 @default.
- W2904707615 hasConceptScore W2904707615C141379421 @default.
- W2904707615 hasConceptScore W2904707615C153180895 @default.
- W2904707615 hasConceptScore W2904707615C154945302 @default.
- W2904707615 hasConceptScore W2904707615C185592680 @default.
- W2904707615 hasConceptScore W2904707615C2776214188 @default.
- W2904707615 hasConceptScore W2904707615C31972630 @default.
- W2904707615 hasConceptScore W2904707615C41008148 @default.
- W2904707615 hasConceptScore W2904707615C50644808 @default.
- W2904707615 hasConceptScore W2904707615C55493867 @default.
- W2904707615 hasConceptScore W2904707615C63479239 @default.
- W2904707615 hasConceptScore W2904707615C81363708 @default.
- W2904707615 hasLocation W29047076151 @default.
- W2904707615 hasLocation W29047076152 @default.
- W2904707615 hasOpenAccess W2904707615 @default.
- W2904707615 hasPrimaryLocation W29047076151 @default.
- W2904707615 hasRelatedWork W2541791370 @default.
- W2904707615 hasRelatedWork W2731899572 @default.
- W2904707615 hasRelatedWork W2738221750 @default.
- W2904707615 hasRelatedWork W3116150086 @default.
- W2904707615 hasRelatedWork W3133861977 @default.
- W2904707615 hasRelatedWork W3156786002 @default.
- W2904707615 hasRelatedWork W4200173597 @default.
- W2904707615 hasRelatedWork W4312417841 @default.
- W2904707615 hasRelatedWork W4321369474 @default.
- W2904707615 hasRelatedWork W564581980 @default.
- W2904707615 isParatext "false" @default.
- W2904707615 isRetracted "false" @default.
- W2904707615 magId "2904707615" @default.
- W2904707615 workType "article" @default.