Learning-based quality control for cardiac MR images
- Submitting institution
-
City, University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 828
- Type
- D - Journal article
- DOI
-
10.1109/TMI.2018.2878509
- Title of journal
- IEEE Transactions on Medical Imaging
- Article number
- -
- First page
- 1127
- Volume
- 38
- Issue
- 5
- ISSN
- 0278-0062
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
11
- Research group(s)
-
-
- Citation count
- 13
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is significant because it presents the first AI approach for quality control of cardiac MR images, allowing the automated detection of unusable scans. It was validated on two datasets (up to 3000 subjects) against expert interpreters. It was featured on the front page of IEEE TMI’s website (top journal in the field) and “inspired” new research ideas (as stated by Luo et al., Med Image Anal 2020: 59, 101591). It was cited in top journals (Med Image Anal, IEEE TMI) and by top researchers (Frangi, A. King). Study supported by “SmartHeart” EPSRC and British Heart Foundation grants.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
