Registration and Modeling from Spaced and Misaligned Image Volumes
- Submitting institution
-
Swansea University / Prifysgol Abertawe
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 28997
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2016.2586660
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 4379
- Volume
- 25
- Issue
- 9
- ISSN
- 1941-0042
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2016
- 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
-
-
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work reports an innovative framework that solves jointly the three interwined problems of registration, segmentation, and interpolation. The proposed method is robust to noise and missing data and particularly suitable for medical imaging. It is an efficient approach to object modelling from 3D and 3D+time scans that can be made up of several misaligned and sparse sequences of 2D images. This works well with reduced acquisition time, which is commonly required for example when imaging infants or requiring breath holds, and misalignments that may occur between sequences for example due to patient movements.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -