Morphological and multi-level geometrical descriptor analysis in CT and MRI volumes for automatic pancreas segmentation
- Submitting institution
-
The University of Westminster
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- qv36q
- Type
- D - Journal article
- DOI
-
10.1016/j.compmedimag.2019.04.004
- Title of journal
- Computerized Medical Imaging and Graphics
- Article number
- -
- First page
- 1
- Volume
- 75
- Issue
- -
- ISSN
- 0895-6111
- Open access status
- Compliant
- Month of publication
- May
- 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
-
2
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Automatic pancreas segmentation in medical images is a challenging task due to high structural variability of the pancreas and the similar greyscale intensity of nearby tissues. This paper is significant because it presents an approach that shows a higher accuracy, preserving contouring details, in identifying the region of interest compared with previous works. It has been demonstrated to be equally effective across different medical imaging modalities and across image-volumes with varying noise and distortion. The algorithm has been integrated in a publicly available framework (available at https://github.com/med-seg/morph-feat-extract) for the automatic extraction of morphological features to support and foster clinical studies.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
