A New Software For Automated Counting Of Glistenings In Intraocular Lenses In Vivo
Published 2022 - 40th Congress of the ESCRS
Reference: PO080 | Type: Free paper | DOI: 10.82333/xm5b-7638
Authors: Nick Stanojcic* 1 , Christopher C. Hull 2 , Eduardo Mangieri 3 , Nathan Little 3 , David O'Brart 1
1Guy's and St Thomas' NHS Foundation Trust,London,United Kingdom, 2Centre for Applied Vision Research, School of Health Sciences,City, University of London,London,United Kingdom, 3Sparca Ltd,Croydon,United Kingdom
Purpose
Setting
Methods
Results
A threshold value of 140 was determined that minimised the total deviation in the number of glistenings for the 34 images in the training set. Using this threshold value, only sight agreement was found between automated software counts and manual expert counts for the validating set of 63 images(k = 0.104,95% CI,0.040- 0.168). Ten images(15.9%) had glistenings counts that agreed between the software and manual counting. There were 49 images(77.8%) where the software overestimated the number of glistenings.
Conclusions
The low levels of agreement shown between an initial release of software used to automatically count glistenings in in vivo slit-lamp images and manual counting indicates that this is a non-trivial application. Iterative improvement involving a dialogue between software developers and experienced ophthalmologists is required to optimise agreement. Our results suggest that validation of software is necessary for studies involving semi-automatic evaluation of glistenings.