FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211202> ?p ?o ?g. }

• W4387211202 endingPage "447" @default.
• W4387211202 startingPage "438" @default.
• W4387211202 abstract "High-resolution (HR) MRI scans obtained from research-grade medical centers provide precise information about imaged tissues. However, routine clinical MRI scans are typically in low-resolution (LR) and vary greatly in contrast and spatial resolution due to the adjustments of the scanning parameters to the local needs of the medical center. End-to-end deep learning methods for MRI super-resolution (SR) have been proposed, but they require re-training each time there is a shift in the input distribution. To address this issue, we propose a novel approach that leverages a state-of-the-art 3D brain generative model, the latent diffusion model (LDM) from [21] trained on UK BioBank, to increase the resolution of clinical MRI scans. The LDM acts as a generative prior, which has the ability to capture the prior distribution of 3D T1-weighted brain MRI. Based on the architecture of the brain LDM, we find that different methods are suitable for different settings of MRI SR, and thus propose two novel strategies: 1) for SR with more sparsity, we invert through both the decoder $$mathcal {D}$$ of the LDM and also through a deterministic Denoising Diffusion Implicit Models (DDIM), an approach we will call InverseSR (LDM); 2) for SR with less sparsity, we invert only through the LDM decoder $$mathcal {D}$$ , an approach we will call InverseSR(Decoder). These two approaches search different latent spaces in the LDM model to find the optimal latent code to map the given LR MRI into HR. The training process of the generative model is independent of the MRI under-sampling process, ensuring the generalization of our method to many MRI SR problems with different input measurements. We validate our method on over 100 brain T1w MRIs from the IXI dataset. Our method can demonstrate that powerful priors given by LDM can be used for MRI reconstruction. Our source code is available online: https://github.com/BioMedAI-UCSC/InverseSR ." @default.
• W4387211202 created "2023-10-01" @default.
• W4387211202 creator A5034976119 @default.
• W4387211202 creator A5047180446 @default.
• W4387211202 creator A5064542601 @default.
• W4387211202 creator A5074184782 @default.
• W4387211202 creator A5077080413 @default.
• W4387211202 creator A5088193137 @default.
• W4387211202 date "2023-01-01" @default.
• W4387211202 modified "2023-10-17" @default.
• W4387211202 title "InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model" @default.
• W4387211202 cites W2082704080 @default.
• W4387211202 cites W2133665775 @default.
• W4387211202 cites W2301358467 @default.
• W4387211202 cites W2608353599 @default.
• W4387211202 cites W2886527657 @default.
• W4387211202 cites W2962785568 @default.
• W4387211202 cites W2964297772 @default.
• W4387211202 cites W2985068832 @default.
• W4387211202 cites W3020887200 @default.
• W4387211202 cites W3034352949 @default.
• W4387211202 cites W3098848838 @default.
• W4387211202 cites W3101204238 @default.
• W4387211202 cites W3165593106 @default.
• W4387211202 cites W3180355996 @default.
• W4387211202 cites W3183434090 @default.
• W4387211202 cites W4212809682 @default.
• W4387211202 cites W4282936583 @default.
• W4387211202 cites W4312497550 @default.
• W4387211202 cites W4312749295 @default.
• W4387211202 cites W4312933868 @default.
• W4387211202 cites W4386076532 @default.
• W4387211202 doi "https://doi.org/10.1007/978-3-031-43999-5_42" @default.
• W4387211202 hasPublicationYear "2023" @default.
• W4387211202 type Work @default.
• W4387211202 citedByCount "0" @default.
• W4387211202 crossrefType "book-chapter" @default.
• W4387211202 hasAuthorship W4387211202A5034976119 @default.
• W4387211202 hasAuthorship W4387211202A5047180446 @default.
• W4387211202 hasAuthorship W4387211202A5064542601 @default.
• W4387211202 hasAuthorship W4387211202A5074184782 @default.
• W4387211202 hasAuthorship W4387211202A5077080413 @default.
• W4387211202 hasAuthorship W4387211202A5088193137 @default.
• W4387211202 hasConcept C115961682 @default.
• W4387211202 hasConcept C126838900 @default.
• W4387211202 hasConcept C138268822 @default.
• W4387211202 hasConcept C141239990 @default.
• W4387211202 hasConcept C143409427 @default.
• W4387211202 hasConcept C149550507 @default.
• W4387211202 hasConcept C153180895 @default.
• W4387211202 hasConcept C154945302 @default.
• W4387211202 hasConcept C157787499 @default.
• W4387211202 hasConcept C167966045 @default.
• W4387211202 hasConcept C205372480 @default.
• W4387211202 hasConcept C31972630 @default.
• W4387211202 hasConcept C39890363 @default.
• W4387211202 hasConcept C41008148 @default.
• W4387211202 hasConcept C71924100 @default.
• W4387211202 hasConceptScore W4387211202C115961682 @default.
• W4387211202 hasConceptScore W4387211202C126838900 @default.
• W4387211202 hasConceptScore W4387211202C138268822 @default.
• W4387211202 hasConceptScore W4387211202C141239990 @default.
• W4387211202 hasConceptScore W4387211202C143409427 @default.
• W4387211202 hasConceptScore W4387211202C149550507 @default.
• W4387211202 hasConceptScore W4387211202C153180895 @default.
• W4387211202 hasConceptScore W4387211202C154945302 @default.
• W4387211202 hasConceptScore W4387211202C157787499 @default.
• W4387211202 hasConceptScore W4387211202C167966045 @default.
• W4387211202 hasConceptScore W4387211202C205372480 @default.
• W4387211202 hasConceptScore W4387211202C31972630 @default.
• W4387211202 hasConceptScore W4387211202C39890363 @default.
• W4387211202 hasConceptScore W4387211202C41008148 @default.
• W4387211202 hasConceptScore W4387211202C71924100 @default.
• W4387211202 hasLocation W43872112021 @default.
• W4387211202 hasOpenAccess W4387211202 @default.
• W4387211202 hasPrimaryLocation W43872112021 @default.
• W4387211202 hasRelatedWork W1582542229 @default.
• W4387211202 hasRelatedWork W1604511055 @default.
• W4387211202 hasRelatedWork W2026847083 @default.
• W4387211202 hasRelatedWork W2141020570 @default.
• W4387211202 hasRelatedWork W2147047527 @default.
• W4387211202 hasRelatedWork W2164918837 @default.
• W4387211202 hasRelatedWork W2799135699 @default.
• W4387211202 hasRelatedWork W3208367840 @default.
• W4387211202 hasRelatedWork W4312298769 @default.
• W4387211202 hasRelatedWork W2143529858 @default.
• W4387211202 isParatext "false" @default.
• W4387211202 isRetracted "false" @default.
• W4387211202 workType "book-chapter" @default.