FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3018872390> ?p ?o ?g. }

• W3018872390 abstract "Reconstructing high-quality magnetic resonance images (MRI) from undersampled raw data is of great interest from both technical and clinical point of views. To this date, however, it is still a mathematically and computationally challenging problem due to its severe ill-posedness, resulting from the highly undersampled data leading to significantly missing information. Whilst a number of techniques have been presented to improve image reconstruction, they only account for spatio-temporal regularisation, which shows its limitations in several relevant scenarios including dynamic data. In this work, we propose a new mathematical model for the reconstruction of high-quality medical MRI from few measurements. Our proposed approach combines - textit{in a multi-task and hybrid model} - the traditional compressed sensing formulation for the reconstruction of dynamic MRI with motion compensation by learning an optical flow approximation. More precisely, we propose to encode the dynamics in the form of an optical flow model that is sparsely represented over a learned dictionary. This has the advantage that ground truth data is not required in the training of the optical flow term. Furthermore, we present an efficient optimisation scheme to tackle the non-convex problem based on an alternating splitting method. We demonstrate the potentials of our approach through an extensive set of numerical results using different datasets and acceleration factors. Our combined approach reaches and outperforms several state of the art techniques. Finally, we show the ability of our technique to transfer phantom based knowledge to real datasets." @default.
• W3018872390 created "2020-05-01" @default.
• W3018872390 creator A5013015879 @default.
• W3018872390 creator A5032908544 @default.
• W3018872390 creator A5044481058 @default.
• W3018872390 creator A5065199290 @default.
• W3018872390 creator A5078055009 @default.
• W3018872390 date "2020-07-06" @default.
• W3018872390 modified "2023-10-15" @default.
• W3018872390 title "Learning Optical Flow for Fast MRI Reconstruction" @default.
• W3018872390 cites W1540764732 @default.
• W3018872390 cites W1812490466 @default.
• W3018872390 cites W1878263927 @default.
• W3018872390 cites W1904063580 @default.
• W3018872390 cites W1959070854 @default.
• W3018872390 cites W1967612560 @default.
• W3018872390 cites W1967706683 @default.
• W3018872390 cites W1970296336 @default.
• W3018872390 cites W1979954835 @default.
• W3018872390 cites W1982839888 @default.
• W3018872390 cites W1983135584 @default.
• W3018872390 cites W1983923103 @default.
• W3018872390 cites W1985055181 @default.
• W3018872390 cites W2000305870 @default.
• W3018872390 cites W2008257035 @default.
• W3018872390 cites W2019371831 @default.
• W3018872390 cites W2028209420 @default.
• W3018872390 cites W2035969841 @default.
• W3018872390 cites W2047544187 @default.
• W3018872390 cites W2049895195 @default.
• W3018872390 cites W2051384873 @default.
• W3018872390 cites W2054077806 @default.
• W3018872390 cites W2056775112 @default.
• W3018872390 cites W2059612594 @default.
• W3018872390 cites W2060185911 @default.
• W3018872390 cites W2065585898 @default.
• W3018872390 cites W2070678378 @default.
• W3018872390 cites W2070894671 @default.
• W3018872390 cites W2072211586 @default.
• W3018872390 cites W2073708032 @default.
• W3018872390 cites W2077121089 @default.
• W3018872390 cites W2092663520 @default.
• W3018872390 cites W2096621047 @default.
• W3018872390 cites W2100467058 @default.
• W3018872390 cites W2101675075 @default.
• W3018872390 cites W2108565035 @default.
• W3018872390 cites W2111161580 @default.
• W3018872390 cites W2115167851 @default.
• W3018872390 cites W2117406892 @default.
• W3018872390 cites W2128904129 @default.
• W3018872390 cites W2132122471 @default.
• W3018872390 cites W2132529238 @default.
• W3018872390 cites W2133665775 @default.
• W3018872390 cites W2133782326 @default.
• W3018872390 cites W2145889472 @default.
• W3018872390 cites W2145962650 @default.
• W3018872390 cites W2151726536 @default.
• W3018872390 cites W2153663612 @default.
• W3018872390 cites W2156739854 @default.
• W3018872390 cites W2164452299 @default.
• W3018872390 cites W2168903001 @default.
• W3018872390 cites W2209264614 @default.
• W3018872390 cites W2291260727 @default.
• W3018872390 cites W2294623389 @default.
• W3018872390 cites W2296166993 @default.
• W3018872390 cites W2296616510 @default.
• W3018872390 cites W2301025128 @default.
• W3018872390 cites W2415447328 @default.
• W3018872390 cites W2473606915 @default.
• W3018872390 cites W2479702039 @default.
• W3018872390 cites W2528340832 @default.
• W3018872390 cites W2536599074 @default.
• W3018872390 cites W2560474170 @default.
• W3018872390 cites W2583092776 @default.
• W3018872390 cites W2751023760 @default.
• W3018872390 cites W2783834599 @default.
• W3018872390 cites W2892127492 @default.
• W3018872390 cites W2892236409 @default.
• W3018872390 cites W2892297559 @default.
• W3018872390 cites W2898504672 @default.
• W3018872390 cites W2913340405 @default.
• W3018872390 cites W2954146638 @default.
• W3018872390 cites W2963782415 @default.
• W3018872390 cites W2970854840 @default.
• W3018872390 cites W2995359922 @default.
• W3018872390 cites W2996488097 @default.
• W3018872390 hasPublicationYear "2020" @default.
• W3018872390 type Work @default.
• W3018872390 sameAs 3018872390 @default.
• W3018872390 citedByCount "0" @default.
• W3018872390 crossrefType "proceedings-article" @default.
• W3018872390 hasAuthorship W3018872390A5013015879 @default.
• W3018872390 hasAuthorship W3018872390A5032908544 @default.
• W3018872390 hasAuthorship W3018872390A5044481058 @default.
• W3018872390 hasAuthorship W3018872390A5065199290 @default.
• W3018872390 hasAuthorship W3018872390A5078055009 @default.
• W3018872390 hasBestOaLocation W30188723901 @default.
• W3018872390 hasConcept C115961682 @default.
• W3018872390 hasConcept C121332964 @default.
• W3018872390 hasConcept C154945302 @default.

• next