Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386564665> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4386564665 abstract "Deep learning-based approaches are increasingly being used for the reconstruction of accelerated MRI scans. However, presented analyses are frequently lacking in-detail evaluation of basal measures like resolution or signal-to-noise ratio. To help closing this gap, spatially resolved maps of image resolution and noise enhancement (g-factor) are determined and assessed for typical model- and data-driven MR reconstruction methods in this paper. MR data from a routine brain scan of a patient were undersampled in retrospect at R = 4 and reconstructed using two data-driven (variational network (VN), U-Net) and two model based reconstructions methods (GRAPPA, TV-constrained compressed sensing). Local resolution was estimated by the width of the main-lobe of a local point-spread function, which was determined for every single pixel by reconstructing images with an additional small perturbation. G-factor maps were determined using a multiple replica method. GRAPPA showed good spatial resolution, but increased g-factors (1.43–1.84, 75% quartile) over all other methods. The images delivered from compressed sensing suffered most from low local resolution, in particular in homogeneous areas of the image. VN and U-Net show similar resolution with mostly moderate local blurring, slightly better for U-Net. For all methods except GRAPPA the resolution as well as the g-factors depend on the anatomy and the direction of undersampling. Objective image quality parameters, local resolution and g-factors have been determined. The examined data driven methods show less local blurring than compressed sensing. The noise enhancement for reconstructions using CS, VN and U-Net is elevated at anatomical contours but is drastically reduced with respect to GRAPPA. Overall, the applied framework provides the possibility for more detailed analysis of novel reconstruction approaches incorporating non-linear and non-stationary transformations." @default.
- W4386564665 created "2023-09-10" @default.
- W4386564665 creator A5027648225 @default.
- W4386564665 creator A5027801019 @default.
- W4386564665 creator A5046721830 @default.
- W4386564665 creator A5049212556 @default.
- W4386564665 creator A5078094908 @default.
- W4386564665 creator A5089412502 @default.
- W4386564665 date "2023-09-01" @default.
- W4386564665 modified "2023-10-16" @default.
- W4386564665 title "Assessment of resolution and noise in magnetic resonance images reconstructed by data driven approaches" @default.
- W4386564665 cites W1971495826 @default.
- W4386564665 cites W2006330194 @default.
- W4386564665 cites W2111388536 @default.
- W4386564665 cites W2111422394 @default.
- W4386564665 cites W2115769026 @default.
- W4386564665 cites W2121570028 @default.
- W4386564665 cites W2594014149 @default.
- W4386564665 cites W2604388535 @default.
- W4386564665 cites W3130554284 @default.
- W4386564665 cites W3157723514 @default.
- W4386564665 cites W3165032792 @default.
- W4386564665 cites W4282590304 @default.
- W4386564665 cites W4324018677 @default.
- W4386564665 doi "https://doi.org/10.1016/j.zemedi.2023.08.007" @default.
- W4386564665 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37684119" @default.
- W4386564665 hasPublicationYear "2023" @default.
- W4386564665 type Work @default.
- W4386564665 citedByCount "0" @default.
- W4386564665 crossrefType "journal-article" @default.
- W4386564665 hasAuthorship W4386564665A5027648225 @default.
- W4386564665 hasAuthorship W4386564665A5027801019 @default.
- W4386564665 hasAuthorship W4386564665A5046721830 @default.
- W4386564665 hasAuthorship W4386564665A5049212556 @default.
- W4386564665 hasAuthorship W4386564665A5078094908 @default.
- W4386564665 hasAuthorship W4386564665A5089412502 @default.
- W4386564665 hasBestOaLocation W43865646651 @default.
- W4386564665 hasConcept C115961682 @default.
- W4386564665 hasConcept C124851039 @default.
- W4386564665 hasConcept C136536468 @default.
- W4386564665 hasConcept C141379421 @default.
- W4386564665 hasConcept C154945302 @default.
- W4386564665 hasConcept C160633673 @default.
- W4386564665 hasConcept C205372480 @default.
- W4386564665 hasConcept C31972630 @default.
- W4386564665 hasConcept C41008148 @default.
- W4386564665 hasConcept C55020928 @default.
- W4386564665 hasConcept C99498987 @default.
- W4386564665 hasConceptScore W4386564665C115961682 @default.
- W4386564665 hasConceptScore W4386564665C124851039 @default.
- W4386564665 hasConceptScore W4386564665C136536468 @default.
- W4386564665 hasConceptScore W4386564665C141379421 @default.
- W4386564665 hasConceptScore W4386564665C154945302 @default.
- W4386564665 hasConceptScore W4386564665C160633673 @default.
- W4386564665 hasConceptScore W4386564665C205372480 @default.
- W4386564665 hasConceptScore W4386564665C31972630 @default.
- W4386564665 hasConceptScore W4386564665C41008148 @default.
- W4386564665 hasConceptScore W4386564665C55020928 @default.
- W4386564665 hasConceptScore W4386564665C99498987 @default.
- W4386564665 hasFunder F4320321114 @default.
- W4386564665 hasFunder F4320326494 @default.
- W4386564665 hasLocation W43865646651 @default.
- W4386564665 hasLocation W43865646652 @default.
- W4386564665 hasOpenAccess W4386564665 @default.
- W4386564665 hasPrimaryLocation W43865646651 @default.
- W4386564665 hasRelatedWork W1604511055 @default.
- W4386564665 hasRelatedWork W1994141795 @default.
- W4386564665 hasRelatedWork W2042965174 @default.
- W4386564665 hasRelatedWork W2095072456 @default.
- W4386564665 hasRelatedWork W2098025213 @default.
- W4386564665 hasRelatedWork W2164918837 @default.
- W4386564665 hasRelatedWork W2891364229 @default.
- W4386564665 hasRelatedWork W2907262162 @default.
- W4386564665 hasRelatedWork W4230961646 @default.
- W4386564665 hasRelatedWork W3102546458 @default.
- W4386564665 isParatext "false" @default.
- W4386564665 isRetracted "false" @default.
- W4386564665 workType "article" @default.