Deformable image registration by combining uncertainty estimates from supervoxel belief propagation
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 97587397
- Type
- D - Journal article
- DOI
-
10.1016/j.media.2015.09.005
- Title of journal
- Medical Image Analysis
- Article number
- -
- First page
- 57
- Volume
- 27
- Issue
- 0
- ISSN
- 1361-8415
- Open access status
- Out of scope for open access requirements
- Month of publication
- October
- Year of publication
- 2015
- 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
-
4
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Accuracy, speed and generalisability are competing algorithmic requirements for deformable medical image registration applications. This novel computational framework successfully combines fast, one-shot discrete optimisation with deformation uncertainty estimation for a range of different medical applications. It was shown to have superior performance over state-of-the-art deformable registration algorithms previously benchmarked in (https://doi.org/10.1016/j.neuroimage.2008.12.037), and has led to follow-up funding for early lung cancer detection requiring accurate nodule tracking (EPSRC EP/P023509/1, with Siemens Healthcare as industry partner).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -