Gaussian mixture model based probabilistic modeling of images for medical image segmentation
- Submitting institution
-
University of Sussex
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9832_89456
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2020.2967676
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 16846
- Volume
- 8
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2020
- URL
-
http://doi.org/10.1109/ACCESS.2020.2967676
- 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
-
8
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In this paper a novel image segmentation algorithm is rigorously derived. An active contour method that incorporates an external energy term based on regional contour characteristics in addition to an edge based term is formulated to provide a more robust segmentation of medical images modelled as Gaussian mixture distributions of the region of interest and background. The method has been successfully applied to the segmentation of images from three very different imaging methods, notably magnetic resonance imaging, dermatology and chromoendoscopy. Quantitative experimental results are presented to demonstrate the method achieves improved segmentation results over existing methods. User Pakistan-MOD
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
