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
. 2023 Nov 6;13(1):19275.
doi: 10.1038/s41598-023-46063-6.

Deep learning-based prediction of the retinal structural alterations after epiretinal membrane surgery

Joseph Kim  1 , Hee Seung Chin  2
Affiliations

Deep learning-based prediction of the retinal structural alterations after epiretinal membrane surgery

Joseph Kim et al. Sci Rep. .

Erratum in

Abstract

To generate and evaluate synthesized postoperative OCT images of epiretinal membrane (ERM) based on preoperative OCT images using deep learning methodology. This study included a total 500 pairs of preoperative and postoperative optical coherence tomography (OCT) images for training a neural network. 60 preoperative OCT images were used to test the neural networks performance, and the corresponding postoperative OCT images were used to evaluate the synthesized images in terms of structural similarity index measure (SSIM). The SSIM was used to quantify how similar the synthesized postoperative OCT image was to the actual postoperative OCT image. The Pix2Pix GAN model was used to generate synthesized postoperative OCT images. Total 60 synthesized OCT images were generated with training values at 800 epochs. The mean SSIM of synthesized postoperative OCT to the actual postoperative OCT was 0.913. Pix2Pix GAN model has a possibility to generate predictive postoperative OCT images following ERM removal surgery.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Conceptual illustration of creating a paired dataset combining pre and postoperative OCT images.
Figure 2
Figure 2
A conceptual drawing of the Pix2Pix model used in our study for synthesizing predictive postoperative OCT image.
Figure 3
Figure 3
A schematic workflow for calculating structural similarity index measure.
Figure 4
Figure 4
Representative synthesized postoperative OCT images. Pre preoperative OCT, Post real an actual postoperative OCT, Post synth synthesized postoperative OCT.
Figure 5
Figure 5
SSIM B versus SSIM A. SSIM structural similarity index measure, SSIM A SSIM for preoperative to real postoperative OCT, SSIM B SSIM for synthesized postoperative to real postoperative OCT.
Figure 6
Figure 6
Representative images for SSIM A and SSIM B. SSIM structural similarity index measure, SSIM A SSIM for preoperative to real postoperative OCT, SSIM B SSIM for synthesized postoperative to real postoperative OCT, Pre preoperative OCT, Post real an actual postoperative OCT, Post synth synthesized postoperative OCT.
See this image and copyright information in PMC

References

    1. Wise GN. Clinical features of idiopathic preretinal macular fibrosis. Schoenberg lecture. Am. J. Ophthalmol. 1975;79(3):349–7. doi: 10.1016/0002-9394(75)90605-4. - DOI - PubMed
    1. Sidd RJ, Fine SL, Owens SL, Patz A. Idiopathic preretinal gliosis. Am. J. Ophthalmol. 1982;94(1):44–8. doi: 10.1016/0002-9394(82)90189-1. - DOI - PubMed
    1. McCarty DJ, Mukesh BN, Chikani V, Wang JJ, Mitchell P, Taylor HR, et al. Prevalence and associations of epiretinal membranes in the visual impairment project. Am. J. Ophthalmol. 2005;140(2):288–94. doi: 10.1016/j.ajo.2005.03.032. - DOI - PubMed
    1. You Q, Xu L, Jonas JB. Prevalence and associations of epiretinal membranes in adult Chinese: The Beijing eye study. Eye (Lond.) 2008;22(7):874–9. doi: 10.1038/sj.eye.6702786. - DOI - PubMed
    1. Kawasaki R, Wang JJ, Sato H, Mitchell P, Kato T, Kawata S, et al. Prevalence and associations of epiretinal membranes in an adult Japanese population: The Funagata study. Eye (Lond.) 2009;23(5):1045–51. doi: 10.1038/eye.2008.238. - DOI - PubMed

Publication types