Automatic segmentation of cross-sectional coronary arterial images
- Submitting institution
-
Swansea University / Prifysgol Abertawe
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 36719
- Type
- D - Journal article
- DOI
-
10.1016/j.cviu.2017.11.004
- Title of journal
- Computer Vision and Image Understanding
- Article number
- -
- First page
- 97
- Volume
- 165
- Issue
- -
- ISSN
- 10773142
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2017
- 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
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Coronary heart disease is the leading cause of death, and IVUS and OCT are two of the most widely used imaging techniques in coronary disease diagnosis and treatment. The work introduces an efficient and robust approach to segmenting inner and outer walls of coronary vessel. We transfer a higher-dimensional segmentation problem to a lower-dimensional tracking problem that is intrinsic to catheter-based imaging, such as IVUS and OCT. The method produces global optimum and thus does not rely on user initialisation, which is highly desirable in medical applications. The preliminary work was published in MICCAI (top conference in Medical Imaging).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -