A novel polar space random field model for the detection of glandular structures
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1329828
- Type
- D - Journal article
- DOI
-
10.1109/TMI.2013.2296572
- Title of journal
- IEEE Transactions on Medical Imaging
- Article number
- -
- First page
- 764
- Volume
- 33
- Issue
- 3
- ISSN
- 0278-0062
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2014
- 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
- Yes
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 28
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Automatic recognition of glands, the complex tubular anatomical human tissue unit, is essential to facilitate computer-aided tissue diagnosis, an important part of modern-day medicine. The shape of a gland can vary hugely, thus posing substantial challenges to computational algorithms. This work shows that by first converting the image from Cartesian space to polar space, and then learning a novel random field model to infer and a verification model to confirm the boundary of a gland, algorithms can not only detect the existence of the gland, but also locate it with pixel accuracy.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
