A new unified framework for the early detection of the progression to diabetic retinopathy from fundus images
- Submitting institution
-
University of Aberdeen
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 171254389
- Type
- D - Journal article
- DOI
-
10.1016/j.compbiomed.2017.09.008
- Title of journal
- Computers in Biology and Medicine
- Article number
- -
- First page
- 98
- Volume
- 90
- Issue
- -
- ISSN
- 0010-4825
- Open access status
- Technical exception
- Month of publication
- September
- 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
-
2
- Research group(s)
-
-
- Citation count
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The approach presented stemmed from a €3.7M Marie-Sklodowska Curie project (https://cordis.europa.eu/project/id/316990) and early stages of this work was covered in press (https://tinyurl.com/y9m3ssu8, https://tinyurl.com/y79hz9oc, https://tinyurl.com/y9s64o5k).The proposed machine learning-based framework for detecting diabetic retinopathy (DR) is a very significant step towards identifying the disease progression earlier than what is currently happening. The previous work has been focusing on detecting lesions, whereas this original approach uses features extracted from the retinal vascular geometry. This is very important for detecting the disease early and also highly significant considering that DR is a leading cause of blindness, therefore early detection is paramount towards preventing blindness.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
