June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Improving Image Resolution of Ophthalmoscopy using Artificial Neural Networks
Author Affiliations & Notes
  • Mohssen Kassir
    Department of Bioengineering, University of California Riverside, Riverside, California, United States
  • Xiaolin Wang
    Doheny Eye Institute, Los Angeles, California, United States
    Department of Ophthalmology, University of California Los Angeles, Los Angeles, California, United States
  • Yuhua Zhang
    Doheny Eye Institute, Los Angeles, California, United States
    Department of Ophthalmology, University of California Los Angeles, Los Angeles, California, United States
  • Jia Guo
    Department of Bioengineering, University of California Riverside, Riverside, California, United States
  • Footnotes
    Commercial Relationships   Mohssen Kassir, None; Xiaolin Wang, None; Yuhua Zhang, None; Jia Guo, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 2130. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Mohssen Kassir, Xiaolin Wang, Yuhua Zhang, Jia Guo; Improving Image Resolution of Ophthalmoscopy using Artificial Neural Networks. Invest. Ophthalmol. Vis. Sci. 2021;62(8):2130.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Adaptive optics has enabled in vivo imaging of the living human retina with diffraction limited spatial resolution and thereby can image the retinal structure at the cellular level. However, adaptive optics may not readily be available for all imaging modalities, and in some cases its performance may be compromised by incomplete compensation of ocular wave aberrations. We investigate a deep learning based method to enhance the spatial resolution of retinal images without or with adaptive optics.

Methods : Twelve high resolution retinal images were obtained using an adaptive optics near-confocal ophthalmoscope (AONCO) as the ground truth. To model the image blur induced by ocular optical defects, we introduced various wave aberrations (with varying Zernike coefficients up to the 7th order). To expand the dataset, the AONCO images were split into small patches (2820 patches/image on average). With 8 different blurring kernels applied, there were 270,736 image patches in total for training and testing. In application of the trained networks, the corrected patches were combined to form images of their original sizes.

The artificial neural network was based on a U-net architecture. We performed a 4-fold cross validation study with a quarter of the images reserved for testing per cross validation.

The normalized mean squared error (NMSE) and structural similarity index measure (SSIM) were calculated for the images before and after correcting for the blurring effects, using the ground truth images as the reference.

Results : After correction with the neural networks, the NMSE was reduced by 36% on average, from 0.063 ± 0.026 to 0.040 ± 0.013. The SSIM was improved by 89% on average, from 0.22 ± 0.10 to 0.40 ± 0.14. The improvements were significant (by paired t-tests, p< 0.001 for both the NMSE and the SSIM). Image examples are shown in Figures 1 and 2.

Conclusions : Our preliminary results showed that deep learning may be useful in correcting the retinal image blur caused by ocular wave aberrations. Further optimization with larger datasets and more types of blurring effects are underway to improve its performance and the generalizability of the network.

This is a 2021 ARVO Annual Meeting abstract.

 

Fig 1: Examples of: (a) ground truth image; (b) blurry image; (c) corrected image. The NMSE were: (b) 0.048 (c) 0.026, and the SSIM: (b) 0.26 (c) 0.50.

Fig 1: Examples of: (a) ground truth image; (b) blurry image; (c) corrected image. The NMSE were: (b) 0.048 (c) 0.026, and the SSIM: (b) 0.26 (c) 0.50.

 

Fig 2: Another set of examples. The NMSE were: (b) 0.071 (c) 0.030, and the SSIM: (b) 0.18 (c) 0.60.

Fig 2: Another set of examples. The NMSE were: (b) 0.071 (c) 0.030, and the SSIM: (b) 0.18 (c) 0.60.

×
×

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.

×