Purchase this article with an account.
Mark Christopher, Akram Belghith, Christopher Bowd, Massimo Antonio Fazio, Michael Henry Goldbaum, Robert N Weinreb, Christopher A Girkin, Jeffrey M Liebmann, Linda M Zangwill; Deep Learning Models Predict Visual Function from Macula Thickness Map. Invest. Ophthalmol. Vis. Sci. 2019;60(9):5600. doi: https://doi.org/.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
To apply deep learning approaches to predict visual field (VF) mean deviation (MD) from multiple thickness maps derived from macular imaging.
Imaging and VF measurements were collected from a cohort of 394 healthy, suspect, and glaucoma participants and 703 eyes. The imaging consisted of 1448 Spectralis horizontal posterior pole (61 b-scans, 30°x25°) images. VF testing in the form of 10-2 (mean ± standard deviation MD = -3.9 ± 6.3 dB) and 24-2 (mean ± standard deviation MD = -4.1 ± 6.3 dB) tests was completed within 180 days of imaging. Participants were randomly divided into independent training (85%), validation (5%), and test (10%) sets. Using standard instrument segmentation, retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL), ganglion cell – inner plexiform layer combined (GCIPL), ganglion cell complex (GCC), and whole retina (RET) thickness maps were generated Individual deep learning models were trained to predict both 10-2 and 24-2 MD from each layer. Combined deep learning models that use all layers simultaneously were also constructed. The Resnet50 architecture was used and transfer learning was applied by pre-training on a general image dataset (ImageNet). Models were evaluated using R2 to compare to predicted and true MD. As a baseline comparison, linear regression models that predicted MD from mean layer thicknesses were also evaluated.
In predicting 10-2 MD, the individual deep learning models, the GCIPL (R2 = 0.84), GCL (R2 = 0.78), and IPL (R2 = 0.74) outperformed other layers. The combined deep learning model achieved an R2 = 0.87 (p < 0.001), outperforming mean layer thickness R2 = 0.60 (p < 0.001). In predicting 24-2 MD, the combined deep learning model achieved an R2 = 0.82 (p < 0.001) while the mean layer thickness prediction had an R2 = 0.62 (p < 0.001). Here, the RNFL (R2 = 0.73), GCIPL (R2 = 0.71), and IPL (R2 = 0.70) outperformed other layers. The full results are summarized in Table 1.
Applying deep learning models to macular structural measurements can predict both central and peripheral visual field loss in glaucoma with a high degree of accuracy. The results suggest that deep learning models can provide useful clinical information without relying on time-consuming and subjective visual field testing.
This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.
Table 1: Performance of macula layer thicknesses and deep learning models to predict MD of 10-2 and 24-2 visual fields.
This PDF is available to Subscribers Only