Sub-Category Classifiers for Multiple-Instance Learning and its Application to Retinal Nerve Fiber Layer Visibility Classification
- Submitting institution
-
University of Dundee
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 28402756
- Type
- D - Journal article
- DOI
-
10.1109/TMI.2017.2653623
- Title of journal
- IEEE Transactions on Medical Imaging
- Article number
- -
- First page
- 1140
- Volume
- 36
- Issue
- 5
- ISSN
- 0278-0062
- Open access status
- Exception within 3 months of publication
- Month of publication
- January
- 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
-
3
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work was the first computational attempt, to our knowledge, to detect and quantify the retinal nerve fibre layer (RNFL) in fundus camera images for its evaluation as a possible biomarker for vascular dementia. The resulting evidence suggested that the RNFL does not afford sufficient visibility to provide reliable measures (beyond our specific algorithms) to be used in biomarker studies for dementia when detected automatically in fundus camera images. This work informed the choice of retinal parameters considered in clinical research on vascular dementia and retinal biomarkers (McGrory et al., Scientific Reports, 2019).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -