File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-031-34344-5_28
- Scopus: eid_2-s2.0-85163962633
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Book Chapter: Generalized Deep Learning-Based Proximal Gradient Descent for MR Reconstruction
Title | Generalized Deep Learning-Based Proximal Gradient Descent for MR Reconstruction |
---|---|
Authors | |
Keywords | Deep Learning Image reconstruction Learned regularization term Magnetic Resonance Imaging Proximal gradient descent |
Issue Date | 5-Jun-2023 |
Publisher | Springer |
Abstract | The data consistency for the physical forward model is crucial in inverse problems, especially in MR imaging reconstruction. The standard way is to unroll an iterative algorithm into a neural network with a forward model embedded. The forward model always changes in clinical practice, so the learning component’s entanglement with the forward model makes the reconstruction hard to generalize. The deep learning-based proximal gradient descent was proposed and use a network as regularization term that is independent of the forward model, which makes it more generalizable for different MR acquisition settings. This one-time pre-trained regularization is applied to different MR acquisition settings and was compared to conventional ℓ1 regularization showing ~3 dB improvement in the peak signal-to-noise ratio. We also demonstrated the flexibility of the proposed method in choosing different undersampling patterns. |
Persistent Identifier | http://hdl.handle.net/10722/338217 |
ISBN | |
ISSN | 2020 SCImago Journal Rankings: 0.249 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Luo, Guanxiong | - |
dc.contributor.author | Kuang, Mengmeng | - |
dc.contributor.author | Cao, Peng | - |
dc.date.accessioned | 2024-03-11T10:27:08Z | - |
dc.date.available | 2024-03-11T10:27:08Z | - |
dc.date.issued | 2023-06-05 | - |
dc.identifier.isbn | 9783031343438 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/338217 | - |
dc.description.abstract | <p>The data consistency for the physical forward model is crucial in inverse problems, especially in MR imaging reconstruction. The standard way is to unroll an iterative algorithm into a neural network with a forward model embedded. The forward model always changes in clinical practice, so the learning component’s entanglement with the forward model makes the reconstruction hard to generalize. The deep learning-based proximal gradient descent was proposed and use a network as regularization term that is independent of the forward model, which makes it more generalizable for different MR acquisition settings. This one-time pre-trained regularization is applied to different MR acquisition settings and was compared to conventional ℓ1 regularization showing ~3 dB improvement in the peak signal-to-noise ratio. We also demonstrated the flexibility of the proposed method in choosing different undersampling patterns.<br></p> | - |
dc.language | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Artificial Intelligence in Medicine | - |
dc.subject | Deep Learning | - |
dc.subject | Image reconstruction | - |
dc.subject | Learned regularization term | - |
dc.subject | Magnetic Resonance Imaging | - |
dc.subject | Proximal gradient descent | - |
dc.title | Generalized Deep Learning-Based Proximal Gradient Descent for MR Reconstruction | - |
dc.type | Book_Chapter | - |
dc.identifier.doi | 10.1007/978-3-031-34344-5_28 | - |
dc.identifier.scopus | eid_2-s2.0-85163962633 | - |
dc.identifier.volume | 13897 LNAI | - |
dc.identifier.spage | 239 | - |
dc.identifier.epage | 244 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.identifier.eisbn | 9783031343445 | - |
dc.identifier.issnl | 0302-9743 | - |