Multivariate regression based convolutional neural network model for fundus image quality assessment
- Submitting institution
-
Kingston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-37-1369
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2020.2982588
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 57810
- Volume
- 8
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2020
- 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
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Objectively assessing the perceptual quality of ocular fundus images is essential for the diagnosis of ocular diseases, and the diagnosis and monitoring of the progression of diabetes. This paper has two main contributions: a large annotated dataset than can be used by the scientific community and a new method to assess the quality of images and classify them in three classes based on their diagnostic quality. This work can have a high impact for the diagnosis of diabetes and for the design of relevant telemedicine systems.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -