Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386411270> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4386411270 abstract "Abstract Background Deep learning methods driven by the low‐rank regularization have achieved attractive performance in dynamic magnetic resonance (MR) imaging. The effectiveness of existing methods lies mainly in their ability to capture interframe relationships using network modules, which are lack interpretability. Purpose This study aims to design an interpretable methodology for modeling interframe relationships using convolutiona networks, namely Annihilation‐Net and use it for accelerating dynamic MRI. Methods Based on the equivalence between Hankel matrix product and convolution, we utilize convolutional networks to learn the null space transform for characterizing low‐rankness. We employ low‐rankness to represent interframe correlations in dynamic MR imaging, while combining with sparse constraints in the compressed sensing framework. The corresponding optimization problem is solved in an iterative form with the semi‐quadratic splitting method (HQS). The iterative steps are unrolled into a network, dubbed Annihilation‐Net. All the regularization parameters and null space transforms are set as learnable in the Annihilation‐Net. Results Experiments on the cardiac cine dataset show that the proposed model outperforms other competing methods both quantitatively and qualitatively. The training set and test set have 800 and 118 images, respectively. Conclusions The proposed Annihilation‐Net improves the reconstruction quality of accelerated dynamic MRI with better interpretability." @default.
- W4386411270 created "2023-09-05" @default.
- W4386411270 creator A5023484910 @default.
- W4386411270 creator A5024945492 @default.
- W4386411270 creator A5031293241 @default.
- W4386411270 creator A5047536759 @default.
- W4386411270 creator A5060413435 @default.
- W4386411270 creator A5087850504 @default.
- W4386411270 date "2023-09-04" @default.
- W4386411270 modified "2023-10-16" @default.
- W4386411270 title "Annihilation‐Net: Learned annihilation relation for dynamic MR imaging" @default.
- W4386411270 cites W1497904071 @default.
- W4386411270 cites W1758598986 @default.
- W4386411270 cites W1943431218 @default.
- W4386411270 cites W19536506 @default.
- W4386411270 cites W1970948570 @default.
- W4386411270 cites W2008257035 @default.
- W4386411270 cites W2117406892 @default.
- W4386411270 cites W2133665775 @default.
- W4386411270 cites W2143488385 @default.
- W4386411270 cites W2158928439 @default.
- W4386411270 cites W2165142794 @default.
- W4386411270 cites W2168903001 @default.
- W4386411270 cites W2442117232 @default.
- W4386411270 cites W2594014149 @default.
- W4386411270 cites W2611467245 @default.
- W4386411270 cites W2757509933 @default.
- W4386411270 cites W2795380527 @default.
- W4386411270 cites W2803224943 @default.
- W4386411270 cites W2808596234 @default.
- W4386411270 cites W2896004214 @default.
- W4386411270 cites W2902719825 @default.
- W4386411270 cites W2951401720 @default.
- W4386411270 cites W2962734274 @default.
- W4386411270 cites W2962903101 @default.
- W4386411270 cites W2964308363 @default.
- W4386411270 cites W2979703761 @default.
- W4386411270 cites W2991630443 @default.
- W4386411270 cites W2999220188 @default.
- W4386411270 cites W2999708269 @default.
- W4386411270 cites W3001319253 @default.
- W4386411270 cites W3045099931 @default.
- W4386411270 cites W3047706622 @default.
- W4386411270 cites W3100017730 @default.
- W4386411270 cites W3100730608 @default.
- W4386411270 cites W3179813600 @default.
- W4386411270 cites W3184682426 @default.
- W4386411270 cites W4226199202 @default.
- W4386411270 doi "https://doi.org/10.1002/mp.16723" @default.
- W4386411270 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37665786" @default.
- W4386411270 hasPublicationYear "2023" @default.
- W4386411270 type Work @default.
- W4386411270 citedByCount "0" @default.
- W4386411270 crossrefType "journal-article" @default.
- W4386411270 hasAuthorship W4386411270A5023484910 @default.
- W4386411270 hasAuthorship W4386411270A5024945492 @default.
- W4386411270 hasAuthorship W4386411270A5031293241 @default.
- W4386411270 hasAuthorship W4386411270A5047536759 @default.
- W4386411270 hasAuthorship W4386411270A5060413435 @default.
- W4386411270 hasAuthorship W4386411270A5087850504 @default.
- W4386411270 hasConcept C11413529 @default.
- W4386411270 hasConcept C121332964 @default.
- W4386411270 hasConcept C141379421 @default.
- W4386411270 hasConcept C154945302 @default.
- W4386411270 hasConcept C201941533 @default.
- W4386411270 hasConcept C2776135515 @default.
- W4386411270 hasConcept C2781067378 @default.
- W4386411270 hasConcept C33923547 @default.
- W4386411270 hasConcept C41008148 @default.
- W4386411270 hasConcept C62520636 @default.
- W4386411270 hasConceptScore W4386411270C11413529 @default.
- W4386411270 hasConceptScore W4386411270C121332964 @default.
- W4386411270 hasConceptScore W4386411270C141379421 @default.
- W4386411270 hasConceptScore W4386411270C154945302 @default.
- W4386411270 hasConceptScore W4386411270C201941533 @default.
- W4386411270 hasConceptScore W4386411270C2776135515 @default.
- W4386411270 hasConceptScore W4386411270C2781067378 @default.
- W4386411270 hasConceptScore W4386411270C33923547 @default.
- W4386411270 hasConceptScore W4386411270C41008148 @default.
- W4386411270 hasConceptScore W4386411270C62520636 @default.
- W4386411270 hasFunder F4320321001 @default.
- W4386411270 hasFunder F4320335777 @default.
- W4386411270 hasLocation W43864112701 @default.
- W4386411270 hasLocation W43864112702 @default.
- W4386411270 hasOpenAccess W4386411270 @default.
- W4386411270 hasPrimaryLocation W43864112701 @default.
- W4386411270 hasRelatedWork W2787767549 @default.
- W4386411270 hasRelatedWork W2947762898 @default.
- W4386411270 hasRelatedWork W2963041618 @default.
- W4386411270 hasRelatedWork W2968260065 @default.
- W4386411270 hasRelatedWork W3095748505 @default.
- W4386411270 hasRelatedWork W4206534706 @default.
- W4386411270 hasRelatedWork W4229079080 @default.
- W4386411270 hasRelatedWork W4385957992 @default.
- W4386411270 hasRelatedWork W4385965371 @default.
- W4386411270 hasRelatedWork W4386025632 @default.
- W4386411270 isParatext "false" @default.
- W4386411270 isRetracted "false" @default.
- W4386411270 workType "article" @default.