DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2399
- Type
- D - Journal article
- DOI
-
10.1109/TMI.2017.2785879
- Title of journal
- IEEE Transactions on Medical Imaging
- Article number
- -
- First page
- 1310
- Volume
- 37
- Issue
- 6
- ISSN
- 0278-0062
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
10.1109/TMI.2017.2785879
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
10
- Research group(s)
-
-
- Citation count
- 221
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The described method is the first reconstruction algorithm for CS-image based on deep generative models, which demonstrated superior reconstruction with preserved perceptual image details and real-time performance compared to conventional CS-MRI reconstruction. The prototype of the system has also been released as open-source software and adopted in various medical imaging research and practice.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
