Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022;15 Suppl 1(Suppl 1):S43-S49.
doi: 10.1016/j.optom.2022.08.003. Epub 2022 Oct 10.

Development and validation of a pixel wise deep learning model to detect cataract on swept-source optical coherence tomography images

Pierre Zéboulon  1 , Christophe Panthier  2 , Hélène Rouger  2 , Jacques Bijon  2 , Wassim Ghazal  2 , Damien Gatinel  2
Affiliations

Development and validation of a pixel wise deep learning model to detect cataract on swept-source optical coherence tomography images

Pierre Zéboulon et al. J Optom. 2022.

Abstract

Purpose: The diagnosis of cataract is mostly clinical and there is a lack of objective and specific tool to detect and grade it automatically. The goal of this study was to develop and validate a deep learning model to detect and localize cataract on Swept Source Optical Coherance Tomography (SS-OCT) images.

Methods: We trained a convolutional network to detect cataract at the pixel level from 504 SS-OCT images of clear lens and cataract patients. The model was then validated on 1326 different images of 114 patients. The output of the model is a map repreenting the probability of cataract for each pixel of the image. We calculated the Cataract Fraction (CF), defined as the number of pixel classified as "cataract" divided by the number of pixel representing the lens for each image. Receiver Operating Characteristic Curves were plotted. Area Under the Curve (ROC AUC) sensitivity and specitivity to detect cataract were calculated.

Results: In the validsation set, mean CF was 0.024 ± 0.077 and 0.479 ± 0.230 (p < 0.001). ROC AUC was 0.98 with an optimal CF threshold of 0.14. Using that threshold, sensitivity and specificity to detect cataract were 94.4% and 94.7%, respectively.

Conclusion: We developed an automatic detection tool for cataract on SS-OCT images. Probability maps of cataract on the images provide an additional tool to help the physician in its diagnosis and surgical planning.

Keywords: Artificial intelligence; Cataract; Deep learning; Optical coherence tomogrpahy.

PubMed Disclaimer

Conflict of interest statement

Conflicts of interest The authors have no conlict of interest.

Figures

Fig 1
Fig. 1
Training curves for the training and test set for clear lens patients and cataract patients.
Fig 2
Fig. 2
Receiver operating characteristic curves for the development and validation sets. AUC: Area under the curve; Dev: Development set; Val: Validation set
Fig 3
Fig. 3
Examples of our model's results. For each case, the original image is on the left, and the model results overlayed on the original image is on the right. Hot colors indicate a high probability of cataract. A and C are cases of cortical cataracts. B and D of nuclear cataracts. E is a case of anterior cortical cataract and F is a case of cortical and posterior subcapsular cataract.
See this image and copyright information in PMC

References

    1. Chylack L.T., Wolfe J.K., Singer D.M., Leske M.C., Bullimore M.A., Bailey I.L., et al. The lens opacities classification system III. The longitudinal study of cataract study group. Arch Ophthalmol Chic. Ill 1960 1993;111:831–836. doi: 10.1001/archopht.1993.01090060119035. - DOI - PubMed
    1. Grewal D.S., Brar G.S., Grewal S.P.S. Correlation of nuclear cataract lens density using scheimpflug images with lens opacities classification system III and visual function. Ophthalmology. 2009;116:1436–1443. doi: 10.1016/j.ophtha.2009.03.002. - DOI - PubMed
    1. Pan A.P., Wang Q.M., Huang F., Huang J.H., Bao F.J., Yu A.Y. Correlation among lens opacities classification system III grading, visual function index-14, pentacam nucleus staging, and objective scatter index for cataract assessment. Am J Ophthalmol. 2015;159:241–247.e2. doi: 10.1016/j.ajo.2014.10.025. - DOI - PubMed
    1. Cabot F., Saad A., McAlinden C., Haddad N.M., Grise-Dulac A., Gatinel D. Objective assessment of crystalline lens opacity level by measuring ocular light scattering with a double-pass system. Am J Ophthalmol. 2013;155:629–635. doi: 10.1016/j.ajo.2012.11.005. e1-2. - DOI - PubMed
    1. Keenan T.D.L., Chen Q., Agrón E., Tham Y.C., Goh J.H.L., Lei X., et al. DeepLensNet: deep learning automated diagnosis and quantitative classification of cataract type and severity. Ophthalmology. 2022;129:571–584. doi: 10.1016/j.ophtha.2021.12.017. - DOI - PMC - PubMed