Publications
Detailed Information
Simultaneously optimizing sampling pattern for joint acceleration of multi-contrast MRI using model-based deep learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Seo, Sunghun | - |
dc.contributor.author | Luu, Huan Minh | - |
dc.contributor.author | Choi, Seung Hong | - |
dc.contributor.author | Park, Sung-Hong | - |
dc.date.accessioned | 2022-10-19T05:03:32Z | - |
dc.date.available | 2022-10-19T05:03:32Z | - |
dc.date.created | 2022-10-07 | - |
dc.date.issued | 2022-09 | - |
dc.identifier.citation | Medical Physics, Vol.49 No.9, pp.5964-5980 | - |
dc.identifier.issn | 0094-2405 | - |
dc.identifier.uri | https://hdl.handle.net/10371/186484 | - |
dc.description.abstract | Background Acceleration of MR imaging (MRI) is a popular research area, and usage of deep learning for acceleration has become highly widespread in the MR community. Joint acceleration of multiple-acquisition MRI was proven to be effective over a single-acquisition approach. Also, optimization in the sampling pattern demonstrated its advantage over conventional undersampling pattern. However, optimizing the sampling patterns for joint acceleration of multiple-acquisition MRI has not been investigated well. Purpose To develop a model-based deep learning scheme to optimize sampling patterns for a joint acceleration of multi-contrast MRI. Methods The proposed scheme combines sampling pattern optimization and multi-contrast MRI reconstruction. It was extended from the physics-guided method of the joint model-based deep learning (J-MoDL) scheme to optimize the separate sampling pattern for each of multiple contrasts simultaneously for their joint reconstruction. Tests were performed with three contrasts of T2-weighted, FLAIR, and T1-weighted images. The proposed multi-contrast method was compared to (i) single-contrast method with sampling optimization (baseline J-MoDL), (ii) multi-contrast method without sampling optimization, and (iii) multi-contrast method with single common sampling optimization for all contrasts. The optimized sampling patterns were analyzed for sampling location overlap across contrasts. The scheme was also tested in a data-driven scenario, where the inversion between input and label was learned from the under-sampled data directly and tested on knee datasets for generalization test. Results The proposed scheme demonstrated a quantitative and qualitative advantage over the single-contrast scheme with sampling pattern optimization and the multi-contrast scheme without sampling pattern optimization. Optimizing the separate sampling pattern for each of the multi-contrasts was superior to optimizing only one common sampling pattern for all contrasts. The proposed scheme showed less overlap in sampling locations than the single-contrast scheme. The main hypothesis was also held in the data-driven situation as well. The brain-trained model worked well on the knee images, demonstrating its generalizability. Conclusion Our study introduced an effective scheme that combines the sampling optimization and the multi-contrast acceleration. The seamless combination resulted in superior performance over the other existing methods. | - |
dc.language | 영어 | - |
dc.publisher | American Association of Physicists in Medicine | - |
dc.title | Simultaneously optimizing sampling pattern for joint acceleration of multi-contrast MRI using model-based deep learning | - |
dc.type | Article | - |
dc.identifier.doi | 10.1002/mp.15790 | - |
dc.citation.journaltitle | Medical Physics | - |
dc.identifier.wosid | 000812924400001 | - |
dc.identifier.scopusid | 2-s2.0-85132110695 | - |
dc.citation.endpage | 5980 | - |
dc.citation.number | 9 | - |
dc.citation.startpage | 5964 | - |
dc.citation.volume | 49 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Choi, Seung Hong | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.