File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.mri.2019.05.023
- Scopus: eid_2-s2.0-85067286440
- PMID: 31175927
- WOS: WOS:000502191300011
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Dual-domain convolutional neural networks for improving structural information in 3 T MRI
Title | Dual-domain convolutional neural networks for improving structural information in 3 T MRI |
---|---|
Authors | |
Keywords | Convolutional neural network Deep learning Image super-resolution Image synthesis Magnetic resonance imaging |
Issue Date | 2019 |
Citation | Magnetic Resonance Imaging, 2019, v. 64, p. 90-100 How to Cite? |
Abstract | We propose a novel dual-domain convolutional neural network framework to improve structural information of routine 3 T images. We introduce a parameter-efficient butterfly network that involves two complementary domains: a spatial domain and a frequency domain. The butterfly network allows the interaction of these two domains in learning the complex mapping from 3 T to 7 T images. We verified the efficacy of the dual-domain strategy and butterfly network using 3 T and 7 T image pairs. Experimental results demonstrate that the proposed framework generates synthetic 7 T-like images and achieves performance superior to state-of-the-art methods. |
Persistent Identifier | http://hdl.handle.net/10722/325437 |
ISSN | 2023 Impact Factor: 2.1 2023 SCImago Journal Rankings: 0.647 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, Yongqin | - |
dc.contributor.author | Yap, Pew Thian | - |
dc.contributor.author | Qu, Liangqiong | - |
dc.contributor.author | Cheng, Jie Zhi | - |
dc.contributor.author | Shen, Dinggang | - |
dc.date.accessioned | 2023-02-27T07:33:17Z | - |
dc.date.available | 2023-02-27T07:33:17Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Magnetic Resonance Imaging, 2019, v. 64, p. 90-100 | - |
dc.identifier.issn | 0730-725X | - |
dc.identifier.uri | http://hdl.handle.net/10722/325437 | - |
dc.description.abstract | We propose a novel dual-domain convolutional neural network framework to improve structural information of routine 3 T images. We introduce a parameter-efficient butterfly network that involves two complementary domains: a spatial domain and a frequency domain. The butterfly network allows the interaction of these two domains in learning the complex mapping from 3 T to 7 T images. We verified the efficacy of the dual-domain strategy and butterfly network using 3 T and 7 T image pairs. Experimental results demonstrate that the proposed framework generates synthetic 7 T-like images and achieves performance superior to state-of-the-art methods. | - |
dc.language | eng | - |
dc.relation.ispartof | Magnetic Resonance Imaging | - |
dc.subject | Convolutional neural network | - |
dc.subject | Deep learning | - |
dc.subject | Image super-resolution | - |
dc.subject | Image synthesis | - |
dc.subject | Magnetic resonance imaging | - |
dc.title | Dual-domain convolutional neural networks for improving structural information in 3 T MRI | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.mri.2019.05.023 | - |
dc.identifier.pmid | 31175927 | - |
dc.identifier.scopus | eid_2-s2.0-85067286440 | - |
dc.identifier.volume | 64 | - |
dc.identifier.spage | 90 | - |
dc.identifier.epage | 100 | - |
dc.identifier.eissn | 1873-5894 | - |
dc.identifier.isi | WOS:000502191300011 | - |