| Title: | Highly Accurate and Precise Automated Cup-to-Disc Ratio Quantification for Glaucoma Screening |
| Journal: | Ophthalmology Science |
| Published: | 27 Apr 2024 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/39051045/ |
| DOI: | https://doi.org/10.1016/j.xops.2024.100540 |
| Citations: | 1 (1 in last 2 years) as of 8 Aug 2024 |
Publication 9993
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Objective: An enlarged cup-to-disc ratio (CDR) is a hallmark of glaucomatous optic neuropathy. Manual assessment of the CDR may be less accurate and more time-consuming than automated methods. Here, we sought to develop and validate a deep learning-based algorithm to automatically determine the CDR from fundus images.</p>
Design: Algorithm development for estimating CDR using fundus data from a population-based observational study.</p>
Participants: A total of 181 768 fundus images from the United Kingdom Biobank (UKBB), Drishti_GS, and EyePACS.</p>
Methods: FastAI and PyTorch libraries were used to train a convolutional neural network-based model on fundus images from the UKBB. Models were constructed to determine image gradability (classification analysis) as well as to estimate CDR (regression analysis). The best-performing model was then validated for use in glaucoma screening using a multiethnic dataset from EyePACS and Drishti_GS.</p>
Main Outcome Measures: The area under the receiver operating characteristic curve and coefficient of determination.</p>
Results: Our gradability model vgg19_batch normalization (bn) achieved an accuracy of 97.13% on a validation set of 16 045 images, with 99.26% precision and area under the receiver operating characteristic curve of 96.56%. Using regression analysis, our best-performing model (trained on the vgg19_bn architecture) attained a coefficient of determination of 0.8514 (95% confidence interval [CI]: 0.8459-0.8568), while the mean squared error was 0.0050 (95% CI: 0.0048-0.0051) and mean absolute error was 0.0551 (95% CI: 0.0543-0.0559) on a validation set of 12 183 images for determining CDR. The regression point was converted into classification metrics using a tolerance of 0.2 for 20 classes; the classification metrics achieved an accuracy of 99.20%. The EyePACS dataset (98 172 healthy, 3270 glaucoma) was then used to externally validate the model for glaucoma classification, with an accuracy, sensitivity, and specificity of 82.49%, 72.02%, and 82.83%, respectively.</p>
Conclusions: Our models were precise in determining image gradability and estimating CDR. Although our artificial intelligence-derived CDR estimates achieve high accuracy, the CDR threshold for glaucoma screening will vary depending on other clinical parameters.</p>
Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.</p>
8 Authors
- Abadh K. Chaurasia
- Connor J. Greatbatch
- Xikun Han
- Puya Gharahkhani
- David A. Mackey
- Stuart MacGregor
- Jamie E. Craig
- Alex W. Hewitt
1 Application
| Application ID | Title |
|---|---|
| 25331 | Gene mapping and genetic correlation across complex traits |
Enabling scientific discoveries that improve human health