June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
A Deep Autoencoder Model to Denoise Visual Fields in Glaucoma
Author Affiliations & Notes
  • Vishal Sharma
    Schepens Eye Research Institute of Massachusetts Eye and Ear,, Harvard Medical School, Boston, Massachusetts, United States
  • Lucy Q Shen
    Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts, United States
  • Louis Pasquale
    Eye and Vision Research Institute, Icahn School of Medicine at Mount Sinai, New York, New York, United States
  • Tobias Elze
    Schepens Eye Research Institute of Massachusetts Eye and Ear,, Harvard Medical School, Boston, Massachusetts, United States
  • Michael V Boland
    Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts, United States
  • Sarah R Wellik
    Bascom Palmer Eye Institute, University of Miami School of Medicine, Miami, Florida, United States
  • Gustavo De Moraes
    Edward S. Harkness Eye Institute, Columbia University Irving Medical Center, New York, New York, United States
  • Jonathan S Myers
    Wills Eye Hospital, Thomas Jefferson University, Philadelphia, Pennsylvania, United States
  • Siamak Yousefi
    Hamilton Eye Institute, The University of Tennessee Health Science Center, Memphis, Tennessee, United States
  • Mengyu Wang
    Schepens Eye Research Institute of Massachusetts Eye and Ear,, Harvard Medical School, Boston, Massachusetts, United States
  • Footnotes
    Commercial Relationships   Vishal Sharma None; Lucy Shen Topcon, Code F (Financial Support); Louis Pasquale Eyenovia-Advisory Board Member, Twenty-Twenty and Emerald Biosciences, Code C (Consultant/Contractor); Tobias Elze Genentech, Code F (Financial Support); Michael Boland Carl Zeiss Meditec and Topcon, Code C (Consultant/Contractor); Sarah Wellik None; Gustavo De Moraes Novartis, Thea, Allergan, Reichert, Carl Zeiss and Perfuse Therapeutics, Code C (Consultant/Contractor), Heidelberg and Topcon, Code F (Financial Support); Jonathan Myers Haag Streit, Code C (Consultant/Contractor), Haag Streit, Code F (Financial Support); Siamak Yousefi None; Mengyu Wang Genentech, Code F (Financial Support)
  • Footnotes
    Support  This work was supported by NIH K99 EY028631, NIH R00 EY028631, Research to Prevent Blindness Departmental Funding for Massachusetts Eye and Ear, Alcon Young Investigator Grant, NIH R21 EY030631, NIH R01 EY030575, NIH R01 EY015473, NIH R21 EY031725, NIH R01 EY033005 and NIH P30 EY003790.
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 2010 – A0451. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Vishal Sharma, Lucy Q Shen, Louis Pasquale, Tobias Elze, Michael V Boland, Sarah R Wellik, Gustavo De Moraes, Jonathan S Myers, Siamak Yousefi, Mengyu Wang; A Deep Autoencoder Model to Denoise Visual Fields in Glaucoma. Invest. Ophthalmol. Vis. Sci. 2022;63(7):2010 – A0451.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : To denoise visual fields (VFs) in glaucoma by developing a deep autoencoder model.

Methods : We selected reliable SITA Standard 24-2 VFs from a multi-center dataset excluding Massachusetts Eye and Ear (MEE) data. A 2D convolutional autoencoder was developed to denoise VFs using the multi-center dataset for training. The noise is defined as the difference between the original VFs and the reconstructed (denoised) VFs from our deep autoencoder model. Our autoencoder model was tested on the MEE dataset. To demonstrate the effectiveness of our denoising model, we compared the structure-function relationships between linear regression models using 12 clock-hour retinal nerve fiber layer thickness (RNFLT) from reliable optical coherence tomography (OCT, signal strength at least 6) to predict the 52 TDs of the paired (within 3 months) original VFs and the denoised VFs. Model selection based on Bayesian information criteria (BIC) was applied to remove redundant features from the structure-function linear models. Adjusted r-squared and BIC penalized for linear model complexity were used to measure the structure-function relationship strength.

Results : A total of 419,755 of VFs from 204,619 eyes of 116,288 patients (age: 64.17 ± 15.42 years; mean deviation: -4.93 ± 6.10 dB) in the multi-center dataset excluding MEE data were used to train our deep autoencoder. There were 9,456 OCT-VF pairs from 4,609 eyes of 2,962 patients from MEE (age: 61.76 ± 15.53 years; mean deviation: -5.04 ± 7.01 dB) available to test our denoising autoencoder. Two examples of the original VF and denoised VFs are shown in Figure. 1 (a-d), where we observe extreme values (noise) to be mitigated after being denoised by our autoencoder model. The absolute average VF differences between original and denoised VF were greater in the central sector (Figure. 1 [e]). Smaller absolute denoising amount was correlated with worse TD values and the correlations were greater in inferior paracentral region (Figure. 1 [f]). The denoised VFs (Figure. 2) can be better predicted by the 12 clock-hour RNFLTs than the original VF with R-squared and BIC improvements up to 0.02 and 48 (BIC improvement ≥ 6: strong improvement) in both 3,672 left and 5,784 right eyes, and the improvement is relatively more conspicuous in superior hemifield.

Conclusions : Denoising VFs with our deep autoencoder model can improve structure-function correlation in glaucoma.

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

 

 

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×