Evidence Based Prediction and Progression Monitoring on Retinal Images from Three Nations
- Submitting institution
-
The University of Surrey
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 9003695_1
- Type
- D - Journal article
- DOI
-
10.1167/tvst.9.2.44
- Title of journal
- Translational Vision Science & Technology
- Article number
- -
- First page
- 44
- Volume
- 9
- Issue
- 2
- ISSN
- 2164-2591
- 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
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The novel deep learning approach taken in this paper was developed in tight collaboration with a clinical team. This enabled the model to be explicitly based on the identification of clinically meaningful features. Collectively this has enabled us to develop an approach that as well as having strong explanatory capability, also has a strong level of absence of bias as demonstrated here. A major international health care provider has selected our system for development into a production level service following an intensive global independent evaluation of competing approaches. This limited the technical detail that could be revealed in the paper.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -