A machine learning cardiac magnetic resonance approach to extract disease features and automate pulmonary arterial hypertension diagnosis
- Submitting institution
-
The University of Sheffield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 7395
- Type
- D - Journal article
- DOI
-
10.1093/ehjci/jeaa001
- Title of journal
- European Heart Journal - Cardiovascular Imaging
- Article number
- -
- First page
- 236
- Volume
- 22
- Issue
- 2
- ISSN
- 2047-2404
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2020
- 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
-
13
- Research group(s)
-
C - Machine Learning
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents the state-of-the art tensor-based machine learning approach for cardiovascular magnetic resonance imaging (CMRI). The technique significantly reduces the computational time required, while achieving diagnostic accuracy slightly higher than standard CMRI metrics. We have filed a patent on this work (IPN: WO2020084301A1, https://patentimages.storage.googleapis.com/69/33/a4/b90b6bb932a960/WO2020084301A1.pd) and obtained a £639,873 grant from the Wellcome Trust (215799/Z/19/Z, collaboration with NHS Director of the Sheffield Pulmonary Vascular Disease Unit) to extend it to prognosis and treatment response assessment, and build a prototype for further clinical evaluation.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -