Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290725208> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4290725208 abstract "Following their success in numerous imaging and computer vision applications, deep-learning (DL) techniques have emerged as one of the most prominent strategies for accelerated MRI reconstruction. These methods have been shown to outperform conventional regularized methods based on compressed sensing (CS). However, in most comparisons, CS is implemented with two or three hand-tuned parameters, while DL methods enjoy a plethora of advanced data science tools. In this work, we revisit <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML display=inline overflow=scroll><mml:mrow><mml:msub><mml:mi>ℓ</mml:mi><mml:mn>1</mml:mn></mml:msub></mml:mrow></mml:math> -wavelet CS reconstruction using these modern tools. Using ideas such as algorithm unrolling and advanced optimization methods over large databases that DL algorithms utilize, along with conventional insights from wavelet representations and CS theory, we show that <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML display=inline overflow=scroll><mml:mrow><mml:msub><mml:mi>ℓ</mml:mi><mml:mn>1</mml:mn></mml:msub></mml:mrow></mml:math> -wavelet CS can be fine-tuned to a level close to DL reconstruction for accelerated MRI. The optimized <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML display=inline overflow=scroll><mml:mrow><mml:msub><mml:mi>ℓ</mml:mi><mml:mn>1</mml:mn></mml:msub></mml:mrow></mml:math> -wavelet CS method uses only 128 parameters compared to >500,000 for DL, employs a convex reconstruction at inference time, and performs within <1% of a DL approach that has been used in multiple studies in terms of quantitative quality metrics." @default.
- W4290725208 created "2022-08-09" @default.
- W4290725208 creator A5010556232 @default.
- W4290725208 creator A5031984988 @default.
- W4290725208 creator A5038369687 @default.
- W4290725208 creator A5044571053 @default.
- W4290725208 creator A5054800712 @default.
- W4290725208 creator A5070460781 @default.
- W4290725208 date "2022-08-08" @default.
- W4290725208 modified "2023-10-12" @default.
- W4290725208 title "Revisiting ℓ1-wavelet compressed-sensing MRI in the era of deep learning" @default.
- W4290725208 cites W2101675075 @default.
- W4290725208 cites W2107861471 @default.
- W4290725208 cites W2117649283 @default.
- W4290725208 cites W2594014149 @default.
- W4290725208 cites W2604388535 @default.
- W4290725208 cites W2911290743 @default.
- W4290725208 cites W2971503239 @default.
- W4290725208 cites W2999167634 @default.
- W4290725208 cites W3001554227 @default.
- W4290725208 cites W3003650457 @default.
- W4290725208 cites W3039236647 @default.
- W4290725208 cites W3104340120 @default.
- W4290725208 cites W3157723514 @default.
- W4290725208 cites W4200205439 @default.
- W4290725208 cites W4290725208 @default.
- W4290725208 cites W59771946 @default.
- W4290725208 doi "https://doi.org/10.1073/pnas.2201062119" @default.
- W4290725208 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35939712" @default.
- W4290725208 hasPublicationYear "2022" @default.
- W4290725208 type Work @default.
- W4290725208 citedByCount "6" @default.
- W4290725208 countsByYear W42907252082022 @default.
- W4290725208 countsByYear W42907252082023 @default.
- W4290725208 crossrefType "journal-article" @default.
- W4290725208 hasAuthorship W4290725208A5010556232 @default.
- W4290725208 hasAuthorship W4290725208A5031984988 @default.
- W4290725208 hasAuthorship W4290725208A5038369687 @default.
- W4290725208 hasAuthorship W4290725208A5044571053 @default.
- W4290725208 hasAuthorship W4290725208A5054800712 @default.
- W4290725208 hasAuthorship W4290725208A5070460781 @default.
- W4290725208 hasBestOaLocation W42907252081 @default.
- W4290725208 hasConcept C11413529 @default.
- W4290725208 hasConcept C119857082 @default.
- W4290725208 hasConcept C124851039 @default.
- W4290725208 hasConcept C154945302 @default.
- W4290725208 hasConcept C41008148 @default.
- W4290725208 hasConceptScore W4290725208C11413529 @default.
- W4290725208 hasConceptScore W4290725208C119857082 @default.
- W4290725208 hasConceptScore W4290725208C124851039 @default.
- W4290725208 hasConceptScore W4290725208C154945302 @default.
- W4290725208 hasConceptScore W4290725208C41008148 @default.
- W4290725208 hasFunder F4320306076 @default.
- W4290725208 hasFunder F4320337338 @default.
- W4290725208 hasFunder F4320337363 @default.
- W4290725208 hasIssue "33" @default.
- W4290725208 hasLocation W42907252081 @default.
- W4290725208 hasLocation W42907252082 @default.
- W4290725208 hasLocation W42907252083 @default.
- W4290725208 hasOpenAccess W4290725208 @default.
- W4290725208 hasPrimaryLocation W42907252081 @default.
- W4290725208 hasRelatedWork W2961085424 @default.
- W4290725208 hasRelatedWork W3046775127 @default.
- W4290725208 hasRelatedWork W3170094116 @default.
- W4290725208 hasRelatedWork W3209574120 @default.
- W4290725208 hasRelatedWork W4205958290 @default.
- W4290725208 hasRelatedWork W4285260836 @default.
- W4290725208 hasRelatedWork W4286629047 @default.
- W4290725208 hasRelatedWork W4306321456 @default.
- W4290725208 hasRelatedWork W4306674287 @default.
- W4290725208 hasRelatedWork W4224009465 @default.
- W4290725208 hasVolume "119" @default.
- W4290725208 isParatext "false" @default.
- W4290725208 isRetracted "false" @default.
- W4290725208 workType "article" @default.