Visual Field Prognosis From Macula and Circumpapillary Spectral Domain Optical Coherence Tomography

TL;DR

This study uses deep learning on OCT images to predict visual field loss in glaucoma patients, aiming to improve diagnosis and care.

Contribution

A deep learning model combining macular and optic-nerve OCT data improves prediction of glaucoma-related visual field loss.

Findings

Combining macular and peri-papillary OCT scans achieves an R2 score of 0.48 for MD prediction.

Central cluster MD predictions reach an R2 of 0.56, showing strong performance in key visual areas.

RNFL, GCL + IPL, and RT layers individually show R2 scores of 0.37, 0.33, and 0.31 for MD prediction.

Abstract

To explore the structural-functional loss relationship from optic-nerve-head– and macula-centred spectral-domain (SD) Optical Coherence Tomography (OCT) images in the full spectrum of glaucoma patients using deep-learning methods.

A cohort comprising 5238 unique eyes classified as suspects or diagnosed with glaucoma was considered. All patients underwent ophthalmologic examination consisting of standard automated perimetry (SAP), macular OCT, and peri-papillary OCT on the same day. Deep learning models were trained to estimate G-pattern visual field (VF) mean deviation (MD) and cluster MD using retinal thickness maps from seven layers: retinal nerve fiber layer (RNFL), ganglion cell layer and inner plexiform layer (GCL + IPL), inner nuclear layer and outer plexiform layer (INL + OPL), outer nuclear layer (ONL), photoreceptors and retinal pigmented epithelium (PR + RPE), choriocapillaris and choroidal stroma (CC + CS), total retinal thickness (RT).

The best performance on MD prediction is achieved by RNFL, GCL + IPL and RT layers, with R2 scores of 0.37, 0.33, and 0.31, respectively. Combining macular and peri-papillary scans outperforms single modality prediction, achieving an R2 value of 0.48. Cluster MD predictions show promising results, notably in central clusters, reaching an R2 of 0.56.

The combination of multiple modalities, such as optic-nerve-head circular B-scans and retinal thickness maps from macular SD-OCT images, improves the performance of MD and cluster MD prediction. Our proposed model demonstrates the highest level of accuracy in predicting MD in the early-to-mid stages of glaucoma.

Objective measures recorded with SD-OCT can optimize the number of visual field tests and improve individualized glaucoma care by adjusting VF testing frequency based on deep-learning estimates of functional damage.

Figures