Automated cardiovascular magnetic resonance image analysis with fully convolutional networks 08 Information and Computing Sciences
- Submitting institution
-
City, University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 829
- Type
- D - Journal article
- DOI
-
10.1186/s12968-018-0471-x
- Title of journal
- Journal of Cardiovascular Magnetic Resonance
- Article number
- -
- First page
- 65
- Volume
- 20
- Issue
- 1
- ISSN
- 1097-6647
- Open access status
- Compliant
- Month of publication
- September
- 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
-
22
- Research group(s)
-
-
- Citation count
- 131
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first paper demonstrating that AI can achieve human-level performance in extracting cardiac metrics from MR images, paving the way for AI-based clinical assessments. The proposed AI was validated on a large dataset (almost 5000 subjects, orders of magnitude larger than previous datasets). The paper was cited in top journals (Nature Medicine, IEEE TMI, Med Image Anal) and by top researchers (Frangi, Tsaftaris). The developed AI was later applied to the UK Biobank study (100,000 subjects) and enabled AI-driven association studies improving our understanding of cardiovascular diseases. Study supported by “SmartHeart” EPSRC, Wellcome Trust and British Heart Foundation.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
