Pointwise Visual Field Estimation From Optical Coherence Tomography in Glaucoma Using Deep Learning

Abstract

Purpose Standard automated perimetry is the gold standard to monitor visual field (VF) loss in glaucoma management, but it is prone to intrasubject variability. We trained and validated a customized deep learning (DL) regression model with Xception backbone that estimates pointwise and overall VF sensitivity from unsegmented optical coherence tomography (OCT) scans. Methods DL regression models have been trained with four imaging modalities (circumpapillary OCT at 3.5 mm, 4.1 mm, and 4.7 mm diameter) and scanning laser ophthalmoscopy en face images to estimate mean deviation (MD) and 52 threshold values. This retrospective study used data from patients who underwent a complete glaucoma examination, including a reliable Humphrey Field Analyzer (HFA) 24-2 SITA Standard (SS) VF exam and a SPECTRALIS OCT. Results For MD estimation, weighted prediction averaging of all four individuals yielded a mean absolute error (MAE) of 2.89 dB (2.50–3.30) on 186 test images, reducing the baseline by 54% (MAEdecr%). For 52 VF threshold values’ estimation, the weighted ensemble model resulted in an MAE of 4.82 dB (4.45–5.22), representing an MAEdecr% of 38% from baseline when predicting the pointwise mean value. DL managed to explain 75% and 58% of the variance ( R 2 ) in MD and pointwise sensitivity estimation, respectively. Conclusions Deep learning can estimate global and pointwise VF sensitivities that fall almost entirely within the 90% test–retest confidence intervals of the 24-2 SS test. Translational Relevance Fast and consistent VF prediction from unsegmented OCT scans could become a solution for visual function estimation in patients unable to perform reliable VF exams.

Usability and Clinician Acceptance of a Deep Learning-Based Clinical Decision Support Tool for Predicting Glaucomatous Visual Field Progression

“…Other information (other data from VF testing such as pattern deviation, location of VF loss, and more medical history) may be helpful in glaucoma management and may be displayed in other ways, such as dynamic user interfaces. In addition, the incorporation of point-wise predictions of VF 55,56 may assist in increasing clinician trust in the predicted VF. However, these will require future iterations of GLANCE and may be implemented as part of future stakeholder interviews and data reviews.…”

Comparison of machine learning approaches for structure–function modeling in glaucoma

“…We also observed that estimation performance in the external test set was better compared with the internal test set, which could be attributed to differences in the spatial distribution of focal severities in the two test sets. Strengths of our study include the use of a standardized, stratified approach for dataset construction, the There has been continued interest in the development and evaluation of models for the estimation VF loss in glaucoma from structural measurements of the retina [9][10][11][12][13][14]27,28 with reported MAEs in the range of 2-5 dB [11][12][13][14] for VF MD estimation. In most previous studies, comparisons with other approaches were largely limited to linear regression 9,11,12,28 or SVMs.…”

“…95% confidence intervals were obtained using a clustered bootstrapping approach at the subject level to adjust for intrasubject correlations. Baseline MAEs were calculated with the differences between the actual values and the means of the datasets, and the extent by which the baseline MAEs were reduced with each of the models was also calculated 14 . For the global VF MD analysis, an additional linear regression (LR) model using global RNFL values was also developed.…”

“…Various modeling approaches have been reported for the estimation of VF loss from structural measurements using techniques based on linear and nonlinear regression, 9 support vector machines, 10 random forests, 11 and, more recently, neural networks 11–15 . Instead of relying on structure–function maps based on sectoral groupings 16 or focal nerve fiber trajectories, 17,18 these models were developed using data‐driven associations in which estimations of either VF mean deviation (VF MD) or focal VF function were developed directly from structural measurements.…”

Artificial intelligence for glaucoma: state of the art and future perspectives

“…Hemelings et al used the raw circumpapillary rings at three different diameters as input to a customized deep learning model [27]. As a baseline model, the corresponding enface scanning laser ophthalmoscopy image was used.…”