Quantitative CMR population imaging on 20,000 subjects of the UK Biobank imaging study: LV/RV quantification pipeline and its evaluation
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-3874
- Type
- D - Journal article
- DOI
-
10.1016/j.media.2019.05.006
- Title of journal
- Medical Image Analysis
- Article number
- -
- First page
- 26
- Volume
- 56
- Issue
- -
- ISSN
- 1361-8415
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2019
- 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
- Yes
- Number of additional authors
-
15
- Research group(s)
-
C - BMH (Applied Computing in Biology, Medicine and Health)
- Citation count
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Publications on fully automatic cardiac image analysis (i.e., cardiac segmentation/qualification) before 2018 were performed/evaluated in fewer than 100 subjects and fewer than 5 methods were tested on 100-300 cases (https://doi.org/10.1016/j.media.2017.10.001). First automatic pipeline quantifying biventricular cardiac MRI on over 20,000 cardiac MRI studies with 50 cardiac phases in UK Biobank. Derived quantitative imaging biomarkers are indistinguishable from manual quantification yet overcoming tedious, subjective, and error-prone human assessment. Derived imaging biomarkers available to the scientific community through UK Biobank and was a ‘Featured Publication’ on its website from 1/8/2019 for several months (https://web.archive.org/web/20190913205617/http://www.ukbiobank.ac.uk:80/published-papers/). Led to https://doi.org/10.1038/s41467-020-15948-9 in Nature Communications.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
