Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204148491> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3204148491 endingPage "12" @default.
- W3204148491 startingPage "3" @default.
- W3204148491 abstract "The thick-slice magnetic resonance (MR) images are often structurally blurred in coronal and sagittal views, which causes harm to diagnosis and image post-processing. Deep learning (DL) has shown great potential to reconstruct the high-resolution (HR) thin-slice MR images from those low-resolution (LR) cases, which we refer to as the slice interpolation task in this work. However, since it is generally difficult to sample abundant paired LR-HR MR images, the classical fully supervised DL-based models cannot be effectively trained to get robust performance. To this end, we propose a novel Two-stage Self-supervised Cycle-consistency Network (TSCNet) for MR slice interpolation, in which a two-stage self-supervised learning (SSL) strategy is developed for unsupervised DL network training. The paired LR-HR images are synthesized along the sagittal and coronal directions of input LR images for network pretraining in the first-stage SSL, and then a cyclic interpolation procedure based on triplet axial slices is designed in the second-stage SSL for further refinement. More training samples with rich contexts along all directions are exploited as guidance to guarantee the improved interpolation performance. Moreover, a new cycle-consistency constraint is proposed to supervise this cyclic procedure, which encourages the network to reconstruct more realistic HR images. The experimental results on a real MRI dataset indicate that TSCNet achieves superior performance over the conventional and other SSL-based algorithms, and obtains competitive qualitative and quantitative results compared with the fully supervised algorithm." @default.
- W3204148491 created "2021-10-11" @default.
- W3204148491 creator A5000937401 @default.
- W3204148491 creator A5027187705 @default.
- W3204148491 creator A5032832318 @default.
- W3204148491 creator A5042241049 @default.
- W3204148491 creator A5043315738 @default.
- W3204148491 date "2021-01-01" @default.
- W3204148491 modified "2023-10-17" @default.
- W3204148491 title "Two-Stage Self-supervised Cycle-Consistency Network for Reconstruction of Thin-Slice MR Images" @default.
- W3204148491 cites W1930824406 @default.
- W3204148491 cites W2078524519 @default.
- W3204148491 cites W2134584543 @default.
- W3204148491 cites W2146299228 @default.
- W3204148491 cites W2581386739 @default.
- W3204148491 cites W2751679535 @default.
- W3204148491 cites W2807184855 @default.
- W3204148491 cites W2887695188 @default.
- W3204148491 cites W2891378267 @default.
- W3204148491 cites W2942080485 @default.
- W3204148491 cites W2962903125 @default.
- W3204148491 cites W2963470893 @default.
- W3204148491 cites W2963671574 @default.
- W3204148491 cites W2964101377 @default.
- W3204148491 cites W2979891860 @default.
- W3204148491 cites W2981362942 @default.
- W3204148491 cites W3023371261 @default.
- W3204148491 cites W3035505623 @default.
- W3204148491 cites W3098848838 @default.
- W3204148491 cites W3101204238 @default.
- W3204148491 doi "https://doi.org/10.1007/978-3-030-87231-1_1" @default.
- W3204148491 hasPublicationYear "2021" @default.
- W3204148491 type Work @default.
- W3204148491 sameAs 3204148491 @default.
- W3204148491 citedByCount "8" @default.
- W3204148491 countsByYear W32041484912022 @default.
- W3204148491 countsByYear W32041484912023 @default.
- W3204148491 crossrefType "book-chapter" @default.
- W3204148491 hasAuthorship W3204148491A5000937401 @default.
- W3204148491 hasAuthorship W3204148491A5027187705 @default.
- W3204148491 hasAuthorship W3204148491A5032832318 @default.
- W3204148491 hasAuthorship W3204148491A5042241049 @default.
- W3204148491 hasAuthorship W3204148491A5043315738 @default.
- W3204148491 hasBestOaLocation W32041484912 @default.
- W3204148491 hasConcept C111472728 @default.
- W3204148491 hasConcept C11413529 @default.
- W3204148491 hasConcept C115961682 @default.
- W3204148491 hasConcept C126838900 @default.
- W3204148491 hasConcept C137800194 @default.
- W3204148491 hasConcept C138885662 @default.
- W3204148491 hasConcept C153180895 @default.
- W3204148491 hasConcept C154945302 @default.
- W3204148491 hasConcept C178910020 @default.
- W3204148491 hasConcept C2776436953 @default.
- W3204148491 hasConcept C31972630 @default.
- W3204148491 hasConcept C41008148 @default.
- W3204148491 hasConcept C71924100 @default.
- W3204148491 hasConcept C75553542 @default.
- W3204148491 hasConceptScore W3204148491C111472728 @default.
- W3204148491 hasConceptScore W3204148491C11413529 @default.
- W3204148491 hasConceptScore W3204148491C115961682 @default.
- W3204148491 hasConceptScore W3204148491C126838900 @default.
- W3204148491 hasConceptScore W3204148491C137800194 @default.
- W3204148491 hasConceptScore W3204148491C138885662 @default.
- W3204148491 hasConceptScore W3204148491C153180895 @default.
- W3204148491 hasConceptScore W3204148491C154945302 @default.
- W3204148491 hasConceptScore W3204148491C178910020 @default.
- W3204148491 hasConceptScore W3204148491C2776436953 @default.
- W3204148491 hasConceptScore W3204148491C31972630 @default.
- W3204148491 hasConceptScore W3204148491C41008148 @default.
- W3204148491 hasConceptScore W3204148491C71924100 @default.
- W3204148491 hasConceptScore W3204148491C75553542 @default.
- W3204148491 hasLocation W32041484911 @default.
- W3204148491 hasLocation W32041484912 @default.
- W3204148491 hasOpenAccess W3204148491 @default.
- W3204148491 hasPrimaryLocation W32041484911 @default.
- W3204148491 hasRelatedWork W1974056099 @default.
- W3204148491 hasRelatedWork W2053950117 @default.
- W3204148491 hasRelatedWork W2386077341 @default.
- W3204148491 hasRelatedWork W2949638731 @default.
- W3204148491 hasRelatedWork W2951102138 @default.
- W3204148491 hasRelatedWork W2954004777 @default.
- W3204148491 hasRelatedWork W4299447939 @default.
- W3204148491 hasRelatedWork W563589758 @default.
- W3204148491 hasRelatedWork W5922282 @default.
- W3204148491 hasRelatedWork W62490179 @default.
- W3204148491 isParatext "false" @default.
- W3204148491 isRetracted "false" @default.
- W3204148491 magId "3204148491" @default.
- W3204148491 workType "book-chapter" @default.