A multimodal spatiotemporal cardiac motion atlas from MR and ultrasound data
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 97486404
- Type
- D - Journal article
- DOI
-
10.1016/j.media.2017.06.002
- Title of journal
- Medical Image Analysis
- Article number
- -
- First page
- 96
- Volume
- 40
- Issue
- -
- ISSN
- 1361-8415
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2017
- 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
-
8
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- MR is the gold standard for cardiac imaging, but the cheapest and most widely-used modality is ultrasound. This paper was the first to demonstrate that machine learning can exploit a database of MR/ultrasound to produce an automated diagnostic tool based only on ultrasound. The method was evaluated on 1000 subjects from UK Biobank. Almost every hospital in the world has ultrasound equipment, but far fewer have MR scanners, so the technique dramatically widens access to state-of-the-art diagnosis. This paper was a milestone in machine learning/cardiology, generated commercial interest (Philips Research PhD studentship [mathieu.de_craene@philips.com]) and resulted in an EPSRC grant (EP/R005516/1).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -