Automatic CNN-based detection of cardiac MR motion artefacts using k-space data augmentation and curriculum learning
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 111676748
- Type
- D - Journal article
- DOI
-
10.1016/j.media.2019.04.009
- Title of journal
- Medical Image Analysis
- Article number
- -
- First page
- 136
- Volume
- 55
- Issue
- -
- ISSN
- 1361-8415
- Open access status
- Compliant
- Month of publication
- April
- 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
- No
- Number of additional authors
-
10
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Degraded image quality due to patient motion or imaging artefacts greatly compromise the diagnostic value of images acquired, leading to inaccurate/incomplete assessments, patient re-calls and associated healthcare costs. This is the first work that provides a rigorous deep learning framework for automated motion artefact detection on a large database (UKBiobank, >3500 subjects), using MR-physics based data augmentation. It has since been employed for large-scale quality control in a recent clinical paper (https://doi.org//10.1016/j.jcmg.2019.05.030 and is now being translated for automated data curation of whole-hospital patient databases as part of the InnovateUK London Medical Imaging and AI Centre for Value-Based Healthcare (TS/S012605/1).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -