Automatic Cone Photoreceptor Localisation in Healthy and Stargardt Afflicted Retinas Using Deep Learning
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 101828342
- Type
- D - Journal article
- DOI
-
10.1038/s41598-018-26350-3
- Title of journal
- Scientific Reports
- Article number
- 7911
- First page
- 1
- Volume
- 8
- Issue
- 1
- ISSN
- 2045-2322
- Open access status
- Compliant
- Month of publication
- May
- 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
-
6
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Adaptive Optics enables the visualisation and spatial characterisation of millions of photoreceptors in the eye, enabling disease progression quantification and response to therapies. However, it is unrealistic to manually count photoreceptors. Our algorithm pioneered the use of memory-based networks to segment pixels into photoreceptors using contextual information, becoming state-of-the-art for both healthy and diseased retinas. We reduced day-long counting to minutes per retinal scan. Moorfields Eye Hospital (moorfields.mmichaelides@nhs.net) now uses our software (available online https://bit.ly/2Z5fLbK) for research into therapies for Leber Congenital Amaurosis (gene RPE65-LCA). Our approach could be applied wherever cell populations must be detected in cluttered environments.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -