A cascade-learning approach for automated segmentation of tumour epithelium in colorectal cancer
- Submitting institution
-
Birmingham City University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11Z_OP_D2020
- Type
- D - Journal article
- DOI
-
10.1016/j.eswa.2018.10.030
- Title of journal
- Expert Systems with Applications
- Article number
- -
- First page
- 539-552
- Volume
- 118
- Issue
- -
- ISSN
- 0957-4174
- Open access status
- Technical exception
- Month of publication
- -
- Year of publication
- 2018
- 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
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- A novel cascaded-learning method has been proposed to automatically detect tumour regions in immunohistochemistry images of human colorectal cancer tissues. The proposed approach can encode generic meaningful information to measure the architecture structure of objects in images in a way to be invariant to staining differences. It has been shown to be robust to additive noise, intensity inhomogeneities, and can cope with a limited number of training samples. The proposed method has inspired more work in tumour parcellation and quantification (e.g., work in adapting a tool for refining biomarker analysis has been based on findings of this paper: DOI: 10.1111/his.13838).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -