Related Experiment Video
Updated: Aug 23, 2025
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
Deep Learning Estimation of 10-2 Visual Field Map Based on Circumpapillary Retinal Nerve Fiber Layer Thickness
Alireza Kamalipour1, Sasan Moghimi1, Pooya Khosravi1
1From the Hamilton Glaucoma Center (A.K., S.M., T.N., G.M., E.H.L., M.C., M.A.F., L.Z., R.N.W.),; Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California San Diego, La Jolla; School of Medicine (P.K.),; University of California Irvine, Irvine; Department of Civil, Construction, and Environmental Engineering (M.S.J.),; San Diego State University, San Diego, California; Bernard and Shirlee Brown Glaucoma Research Laboratory (J.M.L.),; Department of Ophthalmology, Edward S. Harkness Eye Institute, Columbia University Medical Center, New York, New York; and the Department of Ophthalmology and Vision Sciences (M.A.F., C.A.G.),; Heersink School of Medicine, The University of Alabama at Birmingham, Birmingham, Alabama, USA.
Purpose:
To estimate central 10-degree visual field (VF) map from spectral-domain optical coherence tomography (SD-OCT) retinal nerve fiber layer thickness (RNFL) measurements in glaucoma with artificial intelligence.
Design:
Artificial intelligence (convolutional neural networks) study.
Methods:
This study included 5352 SD-OCT scans and 10-2 VF pairs from 1365 eyes of 724 healthy patients, patients with suspected glaucoma, and patients with glaucoma. Convolutional neural networks (CNNs) were developed to estimate the 68 individual sensitivity thresholds of 10-2 VF map using all-sectors (CNNA) and temporal-sectors (CNNT) RNFL thickness information of the SD-OCT circle scan (768 thickness points). 10-2 indices including pointwise total deviation (TD) values, mean deviation (MD), and pattern standard deviation (PSD) were generated using the CNN-estimated sensitivity thresholds at individual test locations. Linear regression (LR) models with the same input were used for comparison.
Results:
The CNNA model achieved an average pointwise mean absolute error of 4.04 dB (95% confidence interval [CI] 3.76-4.35) and correlation coefficient (r) of 0.59 (95% CI 0.52-0.64) over 10-2 map and the mean absolute error and r of 2.88 dB (95% CI 2.63-3.15) and 0.74 (95% CI 0.67-0.80) for MD, and 2.31 dB (95% CI 2.03-2.61) and 0.59 (95% CI 0.51-0.65) for PSD estimations, respectively, significantly outperforming the LRA model.
Conclusions:
The proposed CNNA model improved the estimation of 10-2 VF map based on circumpapillary SD-OCT RNFL thickness measurements. These artificial intelligence methods using SD-OCT structural data show promise to individualize the frequency of central VF assessment in patients with glaucoma and would enable the reallocation of resources from patients at lowest risk to those at highest risk of central VF damage.
