What is it about?
Automated heart image segmentation using artificial intelligence is very promising but on occasions, it gets it wrong. This work addresses how automatically quality control could flag when automatic segmentation did not work.
Featured Image
Why is it important?
Automatic heart image analysis is key to analyse large population studies, such as UK Biobank (100,000 participants with heart imaging). When the automatic analysis fails, we can now flag them so these results can be removed from further analysis or maybe be manually edited.
Perspectives
This work is an important step towards enabling fully automated heart image analysis and quality control of the automated analysis.
Professor Steffen E Petersen
Queen Mary University of London
Read the Original
This page is a summary of: Automated quality control in image segmentation: application to the UK Biobank cardiovascular magnetic resonance imaging study, Journal of Cardiovascular Magnetic Resonance, March 2019, Springer Science + Business Media,
DOI: 10.1186/s12968-019-0523-x.
You can read the full text:
Contributors
The following have contributed to this page
