Prediction of Visual Field Progression from OCT Structural Measures in Moderate to Advanced Glaucoma

Detecting Visual Field Worsening From Optic Nerve Head and Macular Optical Coherence Tomography Thickness Measurements

Purpose

Compare the use of optic disc and macular optical coherence tomography measurements to predict glaucomatous visual field (VF) worsening.

Methods

Machine learning and statistical models were trained on 924 eyes (924 patients) with circumpapillary retinal nerve fiber layer (cp-RNFL) or ganglion cell inner plexiform layer (GC-IPL) thickness measurements. The probability of 24-2 VF worsening was predicted using both trend-based and event-based progression definitions of VF worsening. Additionally, the cp-RNFL and GC-IPL predictions were combined to produce a combined prediction. A held-out test set of 617 eyes was used to calculate the area under the curve (AUC) to compare cp-RNFL, GC-IPL, and combined predictions.

Results

The AUCs for cp-RNFL, GC-IPL, and combined predictions with the statistical and machine learning models were 0.72, 0.69, 0.73, and 0.78, 0.75, 0.81, respectively, when using trend-based analysis as ground truth. The differences in performance between the cp-RNFL, GC-IPL, and combined predictions were not statistically significant. AUCs were highest in glaucoma suspects using cp-RNFL predictions and highest in moderate/advanced glaucoma using GC-IPL predictions. The AUCs for the statistical and machine learning models were 0.63, 0.68, 0.69, and 0.72, 0.69, 0.73, respectively, when using event-based analysis. AUCs decreased with increasing disease severity for all predictions.

Conclusions

cp-RNFL and GC-IPL similarly predicted VF worsening overall, but cp-RNFL performed best in early glaucoma stages and GC-IPL in later stages. Combining both did not enhance detection significantly.

Translational Relevance

cp-RNFL best predicted trend-based 24-2 VF progression in early-stage disease, while GC-IPL best predicted progression in late-stage disease. Combining both features led to minimal improvement in predicting progression.

Prediction of Visual Field Progression with Baseline and Longitudinal Structural Measurements Using Deep Learning

PURPOSE

Identifying glaucoma patients at high risk of progression based on widely available structural data is an unmet task in clinical practice. We test the hypothesis that baseline or serial structural measures can predict visual field (VF) progression with deep learning (DL).

DESIGN

Development of a DL algorithm to predict VF progression.

METHODS

3,079 eyes (1,765 patients) with various types of glaucoma and ≥5 VFs, and ≥3 years of follow-up from a tertiary academic center were included. Serial VF mean deviation (MD) rates of change were estimated with linear-regression. VF progression was defined as negative MD slope with p<0.05. A Siamese Neural Network with ResNet-152 backbone pre-trained on ImageNet was designed to predict VF progression using serial optic-disc photographs (ODP), and baseline retinal nerve fiber layer (RNFL) thickness. We tested the model on a separate dataset (427 eyes) with RNFL data from different OCT. The Main Outcome Measure was Area under ROC curve (AUC).

RESULTS

Baseline average (SD) MD was 3.4 (4.9)dB. VF progression was detected in 900 eyes (29%). AUC (95% CI) for model incorporating baseline ODP and RNFL thickness was 0.813 (0.757-0.869). After adding the second and third ODPs, AUC increased to 0.860 and 0.894, respectively (p<0.027). This model also had highest AUC (0.911) for predicting fast progression (MD rate <1.0 dB/year). Model's performance was similar when applied to second dataset using RNFL data from another OCT device (AUC=0.893; 0.837-0.948).

CONCLUSIONS

DL model predicted VF progression with clinically relevant accuracy using baseline RNFL thickness and serial ODPs and can be implemented as a clinical tool after further validation.

Time to Glaucoma Progression Detection by Optical Coherence Tomography in Individuals of African and European Descents

PURPOSE

To examine the time to detectable retinal nerve fiber layer thickness (RNFLT) progression by optical coherence tomography (OCT) among glaucoma patients of African descent (AD) and European descent (ED).

DESIGN

Retrospective cohort study.

METHODS

AD and ED glaucoma eyes from the Diagnostic Innovations in Glaucoma Study (DIGS)/African Descent and Glaucoma Evaluation Study (ADAGES) with ≥2 years/4 visits of optic nerve head RNFLT measurements were included after homogenization on age, diagnosis, and baseline visual field (VF) measurement. RNFLT variability estimates based on linear mixed-effects models were used to simulate longitudinal RNFLT data for both races. Times to trend-based RNFLT progression detection were calculated under standardized scenarios (same RNFLT baseline/thinning rates for both races) and real-world scenarios (AD and ED cohort-specific RNFLT baseline/thinning rates).

RESULTS

We included 332 and 542 eyes (216 and 317 participants) of AD and ED, respectively. In standardized scenarios, the time to detect RNFLT progression appeared to be similar (difference, <0.2 years) for AD and ED across different assumed RNFLT thinning rates/baseline. In real-world scenarios, compared to ED, AD had a faster RNFLT thinning rate (-0.8 vs -0.6 µm/y) and thicker baseline RNFLT (84.6 vs 81.8 µm). With a faster thinning rate, the mean (SD) time to progression detection was shorter in AD (4.8 [2.0] vs ED: 5.4 [2.4] years), and the 5-year progression rate appeared to be higher (AD: 59% vs ED: 47%).

CONCLUSIONS

Time to progression detection was similar for both races when assuming identical RNFLT baseline/thinning rates, and shorter in AD eyes under real-world simulation when AD had faster RNFLT thinning. In contrast to prior results on VF, which detected progression later in AD eyes than in ED eyes, OCT may detect progression more consistently across these races.

Study of the ganglion cell complex of the macula by optical coherence tomography in the diagnosis of glaucoma progression

INTRODUCTION

The aim of this work is to evaluate the usefulness of the study of the ganglion cell complex of the macula using the OCT technique to estimate the progression of glaucoma according to its severity.

MATERIAL AND METHODS

This is a retrospective cross-sectional study. It includes 205 eyes of 131 patients with glaucoma or ocular hypertension followed for a mean of 5.7 years. The parameters and rates of three tests have been analyzed using the progression software of each instrument: visual field, optical coherence tomography (OCT) in the ganglion cell complex of the macula and in the nerve fiber layer of the optic nerve. The results of each test, the concordance between them and how they differ according to severity stage have been evaluated.

RESULTS

Visual field classifies more cases of progression in moderate-advanced glaucoma, while in mild glaucoma its capacity is limited. Optic nerve fiber layer OCT classifies more cases of progression in mild glaucoma than in moderate-advanced glaucoma, as it is artifacted by the floor effect. OCT of the macular ganglion cell complex is the test that classifies more cases of progression and has the highest agreement with visual field, regardless of severity.

CONCLUSION

In both mild and moderate-advanced glaucoma, OCT of the macula ganglion cell complex may be a better biomarker of progression than OCT of the macula ganglion cell complex.

An Artificial Intelligence Enabled System for Retinal Nerve Fiber Layer Thickness Damage Severity Staging

Purpose

To develop an objective glaucoma damage severity classification system based on OCT-derived retinal nerve fiber layer (RNFL) thickness measurements.

Design

Algorithm development for RNFL damage severity classification based on multicenter OCT data.

Subjects and Participants

A total of 6561 circumpapillary RNFL profiles from 2269 eyes of 1171 subjects to develop models, and 2505 RNFL profiles from 1099 eyes of 900 subjects to validate models.

Methods

We developed an unsupervised k-means model to identify clusters of eyes with similar RNFL thickness profiles. We annotated the clusters based on their respective global RNFL thickness. We computed the optimal global RNFL thickness thresholds that discriminated different severity levels based on Bayes' minimum error principle. We validated the proposed pipeline based on an independent validation dataset with 2505 RNFL profiles from 1099 eyes of 900 subjects.

Main Outcome Measures

Accuracy, area under the receiver operating characteristic curve, and confusion matrix.

Results

The k-means clustering discovered 4 clusters with 1382, 1613, 1727, and 1839 samples with mean (standard deviation) global RNFL thickness of 58.3 (8.9) μm, 78.9 (6.7) μm, 87.7 (8.2) μm, and 101.5 (7.9) μm. The Bayes' minimum error classifier identified optimal global RNFL values of > 95 μ m , 86 to 95 μ m , 70 to 85 μ m , and < 70 μ m for discriminating normal eyes and eyes at the early, moderate, and advanced stages of RNFL thickness loss, respectively. About 4% of normal eyes and 98% of eyes with advanced RNFL loss had either global, or ≥ 1 quadrant, RNFL thickness outside of normal limits provided by the OCT instrument.

Conclusions

Unsupervised machine learning discovered that the optimal RNFL thresholds for separating normal eyes and eyes with early, moderate, and advanced RNFL loss were 95 μ m , 85 μm, and 70 μ m , respectively. This RNFL loss classification system is unbiased as there was no preassumption or human expert intervention in the development process. Additionally, it is objective, easy to use, and consistent, which may augment glaucoma research and day-to-day clinical practice.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Predicting 60-4 visual field tests using 3D facial reconstruction

BACKGROUND

Despite, the potential clinical utility of 60-4 visual fields, they are not frequently used in clinical practice partly, due to the purported impact of facial contour on field defects. The purpose of this study was to design and test an artificial intelligence-driven platform to predict facial structure-dependent visual field defects on 60-4 visual field tests.

METHODS

Subjects with no ocular pathology were included. Participants were subject to optical coherence tomography, 60-4 Swedish interactive thresholding algorithm visual field tests and photography. The predicted visual field was compared with observed 60-4 visual field results in subjects. Average and point-specific sensitivity, specificity, precision, negative predictive value, accuracy, and F1-scores were primary outcome measures.

RESULTS

30 healthy were enrolled. Three-dimensional facial reconstruction using a convolution neural network (CNN) was able to predict facial contour-dependent 60-4 visual field defects in 30 subjects without ocular pathology. Overall model accuracy was 97%±3% and 96%±3% and the F1-score, dependent on precision and sensitivity, was 58%±19% and 55%±15% for the right eye and left eye, respectively. Spatial-dependent model performance was observed with increased sensitivity and precision within the far inferior nasal field reflected by an average F1-score of 76%±20% and 70%±29% for the right eye and left eye, respectively.

CONCLUSIONS

This pilot study reports the development of a CNN-enhanced platform capable of predicting 60-4 visual field defects in healthy controls based on facial contour. Further study with this platform may enhance understanding of the influence of facial contour on 60-4 visual field testing.

Predicting glaucoma progression using deep learning framework guided by generative algorithm

Glaucoma is a slowly progressing optic neuropathy that may eventually lead to blindness. To help patients receive customized treatment, predicting how quickly the disease will progress is important. Structural assessment using optical coherence tomography (OCT) can be used to visualize glaucomatous optic nerve and retinal damage, while functional visual field (VF) tests can be used to measure the extent of vision loss. However, VF testing is patient-dependent and highly inconsistent, making it difficult to track glaucoma progression. In this work, we developed a multimodal deep learning model comprising a convolutional neural network (CNN) and a long short-term memory (LSTM) network, for glaucoma progression prediction. We used OCT images, VF values, demographic and clinical data of 86 glaucoma patients with five visits over 12 months. The proposed method was used to predict VF changes 12 months after the first visit by combining past multimodal inputs with synthesized future images generated using generative adversarial network (GAN). The patients were classified into two classes based on their VF mean deviation (MD) decline: slow progressors (< 3 dB) and fast progressors (> 3 dB). We showed that our generative model-based novel approach can achieve the best AUC of 0.83 for predicting the progression 6 months earlier. Further, the use of synthetic future images enabled the model to accurately predict the vision loss even earlier (9 months earlier) with an AUC of 0.81, compared to using only structural (AUC = 0.68) or only functional measures (AUC = 0.72). This study provides valuable insights into the potential of using synthetic follow-up OCT images for early detection of glaucoma progression.

Optic Nerve Head Morphology is Associated with the Initial Location of Structural Progression in Early Open Angle Glaucoma

PRCIS

Glaucoma eyes with a small cup-to-disk ratio (CDR) tend to show retinal nerve fiber layer progression earlier than ganglion cell-inner plexiform layer progression.

PURPOSE

To investigate the effects of clinical variables on the temporal relationship between macular ganglion cell-inner plexiform layer (mGCIPL) loss and peripapillary retinal nerve fiber layer (pRNFL) loss in glaucoma.

METHODS

This retrospective observational study used medical records of patients diagnosed with open angle glaucoma. Structural change was determined using guided progression analysis software of Cirrus optical coherence tomography. Based on the time of detection of pRNFL and mGCIPL changes, eyes showing progressive layer loss were categorized into the pRNFL-first and mGCIPL-first groups. The association between sites of layer thinning and clinical variables such as major retinal arterial angles and several optic disk measurements, including disk area, average CDR, and vertical CDR, were analyzed.

RESULTS

A total of 282 eyes were included in the study, of which 104 showed structural progression either in the mGCIPL or pRNFL. Out of these, 49 eyes showed the first progression in pRNFL, while 37 eyes showed the first progression in mGCIPL. The minimum mGCIPL thickness, pRNFL thickness, average CDR, vertical CDR, and location of progression were significantly different between the 2 groups ( P =0.041, P =0.034, P =0.015, P <0.001, and P <0.001, respectively). In multivariate analysis, average CDR and vertical CDR were significantly associated with the progression site ( P =0.033 and P =0.006, respectively). The structural changes in the inferoinferior area and the superior vulnerability zone were significantly associated with RNFL-first progression ( P <0.001 for both).

CONCLUSION

The location of layer loss and CDR are related to the layer where loss is first detected (either pRNFL or mGCIPL) in open angle glaucoma.

Artifact Correction in Retinal Nerve Fiber Layer Thickness Maps Using Deep Learning and Its Clinical Utility in Glaucoma

Purpose

Correcting retinal nerve fiber layer thickness (RNFLT) artifacts in glaucoma with deep learning and evaluate its clinical usefulness.

Methods

We included 24,257 patients with optical coherence tomography and reliable visual field (VF) measurements within 30 days and 3,233 patients with reliable VF series of at least five measurements over ≥4 years. The artifacts are defined as RNFLT less than the known floor value of 50 µm. We selected 27,319 high-quality RNFLT maps with an artifact ratio (AR) of <2% as the ground truth. We created pseudo-artifacts from 21,722 low-quality RNFLT maps with AR of >5% and superimposed them on high-quality RNFLT maps to predict the artifact-free ground truth. We evaluated the impact of artifact correction on the structure-function relationship and progression forecasting.

Results

The mean absolute error and Pearson correlation of the artifact correction were 9.89 µm and 0.90 (P < 0.001), respectively. Artifact correction improved R2 for VF prediction in RNFLT maps with AR of >10% and AR of >20% up to 0.03 and 0.04 (P < 0.001), respectively. Artifact correction improved (P < 0.05) the AUC for progression prediction in RNFLT maps with AR of ≤10%, >10%, and >20%: (1) total deviation pointwise progression: 0.68 to 0.69, 0.62 to 0.63, and 0.62 to 0.64; and (2) mean deviation fast progression: 0.67 to 0.68, 0.54 to 0.60, and 0.45 to 0.56.

Conclusions

Artifact correction for RNFLTs improves VF and progression prediction in glaucoma.

Translational Relevance

Our model improves clinical usability of RNFLT maps with artifacts.

Clinical Factors Associated With Long-Term OCT Variability in Glaucoma

PURPOSE

To examine clinical factors associated with long-term optical coherence tomography (OCT)-measured retinal nerve fiber layer thickness (RNFLT) variability in glaucoma.

STUDY DESIGN

Retrospective cohort study.

METHODS

Glaucoma eyes from Diagnostic Innovations in Glaucoma Study (DIGS)/the African Descent and Glaucoma Evaluation Study (ADAGES) with ≥2-years and 4-visit follow-up were included. RNFLT variability was calculated per visit as the absolute error of optic nerve head RNFLT residuals across longitudinal follow-up. Clinical factors examined included general demographics, baseline ocular measurements, prior and intervening cataract extraction (CE) or glaucoma surgery, scan quality, baseline RNFLT and RNFLT thinning rate, follow-up duration, and visit/testing frequency. Three multivariable linear mixed models (full model, baseline model, and parsimonious model) were fit to evaluate the effects of clinical factors on RNFLT variability, with 10-fold cross-validation to estimate real-world model performance.

RESULTS

A total of 1140 eyes (634 patients) were included. The overall mean (95% CI) RNFLT variability was 1.51(1.45, 1.58) µm. Across different models, African American race (β [standard error {SE} = 0.18 [0.06]), intervening CE (β [SE] = 0.52 [0.07]), intervening glaucoma surgeries (β [SE] = 0.15 [0.03]), and more positive RNFLT thinning rate (β [SE] = 0.06 [0.02] per 1 µm/y more positive) showed consistent association with greater RNFLT variability, whereas more frequent visits/testing (β [SE] = -0.11[0.05] per 1 visit/y higher) was associated with smaller RNFLT variability (P < .05 for all).

CONCLUSIONS

Relevant clinical factors affecting long-term RNFLT variability in glaucoma were identified. These data enhance the evaluation of longitudinal structural change. Increasing the testing frequency, especially in eyes at risk for higher measurement variability, and resetting of baseline imaging after intervening procedures may help to more reliably detect OCT progression.

Predicting Visual Field Worsening with Longitudinal OCT Data Using a Gated Transformer Network

PURPOSE

To identify visual field (VF) worsening from longitudinal OCT data using a gated transformer network (GTN) and to examine how GTN performance varies for different definitions of VF worsening and different stages of glaucoma severity at baseline.

DESIGN

Retrospective longitudinal cohort study.

PARTICIPANTS

A total of 4211 eyes (2666 patients) followed up at the Johns Hopkins Wilmer Eye Institute with at least 5 reliable VF results and 1 reliable OCT scan within 1 year of each reliable VF test.

METHODS

For each eye, we used 3 trend-based methods (mean deviation [MD] slope, VF index slope, and pointwise linear regression) and 3 event-based methods (Guided Progression Analysis, Collaborative Initial Glaucoma Treatment Study scoring system, and Advanced Glaucoma Intervention Study [AGIS] scoring system) to define VF worsening. Additionally, we developed a "majority of 6" algorithm (M6) that classifies an eye as worsening if 4 or more of the 6 aforementioned methods classified the eye as worsening. Using these 7 reference standards for VF worsening, we trained 7 GTNs that accept a series of at least 5 as input OCT scans and provide as output a probability of VF worsening. Gated transformer network performance was compared with non-deep learning models with the same serial OCT input from previous studies-linear mixed-effects models (MEMs) and naive Bayes classifiers (NBCs)-using the same training sets and reference standards as for the GTN.

MAIN OUTCOME MEASURES

Area under the receiver operating characteristic curve (AUC).

RESULTS

The M6 labeled 63 eyes (1.50%) as worsening. The GTN achieved an AUC of 0.97 (95% confidence interval, 0.88-1.00) when trained with M6. Gated transformer networks trained and optimized with the other 6 reference standards showed an AUC ranging from 0.78 (MD slope) to 0.89 (AGIS). The 7 GTNs outperformed all 7 MEMs and all 7 NBCs accordingly. Gated transformer network performance was worse for eyes with more severe glaucoma at baseline.

CONCLUSIONS

Gated transformer network models trained with OCT data may be used to identify VF worsening. After further validation, implementing such models in clinical practice may allow us to track functional worsening of glaucoma with less onerous structural testing.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found after the references.

Optical Coherence Tomography and Optical Coherence Tomography Angiography: Essential Tools for Detecting Glaucoma and Disease Progression

Early diagnosis and detection of disease progression are critical to successful therapeutic intervention in glaucoma, the leading cause of irreversible blindness worldwide. Optical coherence tomography (OCT) is a non-invasive imaging technique that allows objective quantification in vivo of key glaucomatous structural changes in the retina and the optic nerve head (ONH). Advances in OCT technology have increased the scan speed and enhanced image quality, contributing to early glaucoma diagnosis and monitoring, as well as the visualization of critically important structures deep within the ONH, such as the lamina cribrosa. OCT angiography (OCTA) is a dye-free technique for noninvasively assessing ocular microvasculature, including capillaries within each plexus serving the macula, peripapillary retina and ONH regions, as well as the deeper vessels of the choroid. This layer-specific assessment of the microvasculature has provided evidence that retinal and choroidal vascular impairments can occur during early stages of glaucoma, suggesting that OCTA-derived measurements could be used as biomarkers for enhancing detection of glaucoma and its progression, as well as to reveal novel insights about pathophysiology. Moreover, these innovations have demonstrated that damage to the macula, a critical region for the vision-related quality of life, can be observed in the early stages of glaucomatous eyes, leading to a paradigm shift in glaucoma monitoring. Other advances in software and hardware, such as artificial intelligence-based algorithms, adaptive optics, and visible-light OCT, may further benefit clinical management of glaucoma in the future. This article reviews the utility of OCT and OCTA for glaucoma diagnosis and disease progression detection, emphasizes the importance of detecting macula damage in glaucoma, and highlights the future perspective of OCT and OCTA. We conclude that the OCT and OCTA are essential glaucoma detection and monitoring tools, leading to clinical and economic benefits for patients and society.

GABA decrease is associated with degraded neural specificity in the visual cortex of glaucoma patients

Glaucoma is an age-related neurodegenerative disease of the visual system, affecting both the eye and the brain. Yet its underlying metabolic mechanisms and neurobehavioral relevance remain largely unclear. Here, using proton magnetic resonance spectroscopy and functional magnetic resonance imaging, we investigated the GABAergic and glutamatergic systems in the visual cortex of glaucoma patients, as well as neural specificity, which is shaped by GABA and glutamate signals and underlies efficient sensory and cognitive functions. Our study shows that among the older adults, both GABA and glutamate levels decrease with increasing glaucoma severity regardless of age. Further, our study shows that the reduction of GABA but not glutamate predicts the neural specificity. This association is independent of the impairments on the retina structure, age, and the gray matter volume of the visual cortex. Our results suggest that glaucoma-specific decline of GABA undermines neural specificity in the visual cortex and that targeting GABA could improve the neural specificity in glaucoma.

Combined Model of OCT Angiography and Structural OCT Parameters to Predict Paracentral Visual Field Loss in Primary Open-Angle Glaucoma

PURPOSE

To assess a model combining OCT angiography (OCTA) and OCT parameters to predict the severity of paracentral visual field (VF) loss in primary open-angle glaucoma (POAG).

DESIGN

Cross-sectional study.

PARTICIPANTS

Forty-four patients with POAG and 42 control subjects underwent OCTA and OCT imaging with a swept-source OCT device.

METHODS

The circumpapillary microvasculature was quantified for vessel density (cpVD) and flow (cpFlow) after delineation of Bruch's membrane opening and removal of large vessels. Retinal nerve fiber layer thickness (RNFLT) and Bruch's membrane opening-minimum rim width (BMO-MRW) were measured from structural OCT. Paracentral total deviation (PaTD) was defined as the average of the total deviation values within the central 10 degrees on Humphrey VF testing (24-2) for upper and lower hemifields. The OCT and OCTA parameters were measured in the affected hemisphere corresponding to the hemifield with lower PaTD for POAG patients. Models were created to predict affected PaTD based on RNFLT alone; RNFLT and BMO-MRW; OCTA alone; or RNFLT, BMO-MRW and OCTA parameters. The models were compared using coefficient of determination (r2) and Bayesian information criterion (BIC) score. Bayesian information criterion decrease of ≥6 indicates strong evidence for model improvement.

MAIN OUTCOME MEASURES

Performance of models containing OCT and OCTA parameters in predicting PaTD.

RESULTS

Patients with POAG and controls were similar in age and sex (65.9 ± 9.5 years and 38.4% male overall, P ≥ 0.56 for both). Average RNFLT, minimum RNFLT, average BMO-MRW, minimum BMO-MRW, cpVD, and cpFlow were all significantly lower (all P < 0.001) in the affected hemisphere in patients with POAG than in controls. In patients with POAG, the average mean deviation was -4.33 ± 3.25 dB; the PaTD of the affected hemifield averaged -4.55 ± 5.26 dB and correlated significantly with both OCTA and structural OCT parameters (r ≥ 0.43, P ≤ 0.004 for all). The model containing RNFLT, BMO-MRW, and OCTA parameters was superior in predicting affected PaTD (r2 = 0.47, BIC = 290.7), with higher r2 and lower BIC compared with all 3 other models.

CONCLUSIONS

A combined model of OCTA and structural OCT parameters can predict the severity of paracentral VF loss of the affected hemifield, supporting clinical utility of OCTA in patients with POAG with paracentral VF loss.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found after the references.

Use of artificial intelligence in forecasting glaucoma progression

Artificial intelligence (AI) has been widely used in ophthalmology for disease detection and monitoring progression. For glaucoma research, AI has been used to understand progression patterns and forecast disease trajectory based on analysis of clinical and imaging data. Techniques such as machine learning, natural language processing, and deep learning have been employed for this purpose. The results from studies using AI for forecasting glaucoma progression however vary considerably due to dataset constraints, lack of a standard progression definition and differences in methodology and approach. While glaucoma detection and screening have been the focus of most research that has been published in the last few years, in this narrative review we focus on studies that specifically address glaucoma progression. We also summarize the current evidence, highlight studies that have translational potential, and provide suggestions on how future research that addresses glaucoma progression can be improved.

Detecting disease progression in mild, moderate and severe glaucoma

PURPOSE OF REVIEW

The purpose of this review is to examine contemporary techniques for detecting the progression of glaucoma. We provide a general overview of detection principles and review evidence-based diagnostic strategies and specific considerations for detecting glaucomatous progression in patients with mild, moderate and severe disease.

RECENT FINDINGS

Diagnostic techniques and technologies for glaucoma have dramatically evolved in recent years, affording clinicians an expansive toolkit with which to detect glaucoma progression. Each stage of glaucoma, however, presents unique diagnostic challenges. In mild disease, either structural or functional changes can develop first in disease progression. In moderate disease, structural or functional changes can occur either in tandem or in isolation. In severe disease, standard techniques may fail to detect further disease progression, but such detection can still be measured using other modalities.

SUMMARY

Detecting disease progression is central to the management of glaucoma. Glaucomatous progression has both structural and functional elements, both of which must be carefully monitored at all disease stages to determine when interventions are warranted.

Comparison of Retinal Structural and Neurovascular Changes between Patients with and without Amyloid Pathology

To evaluate whether an impaired anterior visual pathway (retinal structures with microvasculature) is associated with underlying beta-amyloid (Aβ) pathologies in patients with Alzheimer's disease dementia (ADD) and mild cognitive impairment (MCI), we compared retinal structural and vascular factors in each subgroup with positive or negative amyloid biomarkers. Twenty-seven patients with dementia, thirty-five with MCI, and nine with cognitively unimpaired (CU) controls were consecutively recruited. All participants were divided into positive Aβ (A+) or negative Aβ (A-) pathology based on amyloid positron emission tomography or cerebrospinal fluid Aβ. The retinal circumpapillary retinal nerve fiber layer thickness (cpRNFLT), macular ganglion cell/inner plexiform layer thickness (mGC/IPLT), and microcirculation of the macular superficial capillary plexus were measured using optical coherence tomography (OCT) and OCT angiography. One eye of each participant was included in the analysis. Retinal structural and vascular factors significantly decreased in the following order: dementia < MCI < CU controls. The A+ group had significantly lower microcirculation in the para- and peri-foveal temporal regions than did the A-. However, the structural and vascular parameters did not differ between the A+ and A- with dementia. The cpRNFLT was unexpectedly greater in the A+ than in the A- with MCI. mGC/IPLT was lower in the A+ CU than in the A- CU. Our findings suggest that retinal structural changes may occur in the preclinical and early stages of dementia but are not highly specific to AD pathophysiology. In contrast, decreased temporal macula microcirculation may be used as a biomarker for the underlying Aβ pathology.

Combining Optical Coherence Tomography and Optical Coherence Tomography Angiography Longitudinal Data for the Detection of Visual Field Progression in Glaucoma

PURPOSE

To use longitudinal optical coherence tomography (OCT) and OCT angiography (OCTA) data to detect glaucomatous visual field (VF) progression with a supervised machine learning approach.

DESIGN

Prospective cohort study.

METHODS

One hundred ten eyes of patients with suspected glaucoma (33.6%) and patients with glaucoma (66.4%) with a minimum of 5 24-2 VF tests and 3 optic nerve head and macula images over an average follow-up duration of 4.1 years were included. VF progression was defined using a composite measure including either a "likely progression event" on Guided Progression Analysis, a statistically significant negative slope of VF mean deviation or VF index, or a positive pointwise linear regression event. Feature-based gradient boosting classifiers were developed using different subsets of baseline and longitudinal OCT and OCTA summary parameters. The area under the receiver operating characteristic curve (AUROC) was used to compare the classification performance of different models.

RESULTS

VF progression was detected in 28 eyes (25.5%). The model with combined baseline and longitudinal OCT and OCTA parameters at the global and hemifield levels had the best classification accuracy to detect VF progression (AUROC = 0.89). Models including combined OCT and OCTA parameters had higher classification accuracy compared with those with individual subsets of OCT or OCTA features alone. Including hemifield measurements significantly improved the models' classification accuracy compared with using global measurements alone. Including longitudinal rates of change of OCT and OCTA parameters (AUROCs = 0.80-0.89) considerably increased the classification accuracy of the models with baseline measurements alone (AUROCs = 0.60-0.63).

CONCLUSIONS

Longitudinal OCTA measurements complement OCT-derived structural metrics for the evaluation of functional VF loss in patients with glaucoma.

Reverse translation of artificial intelligence in glaucoma: Connecting basic science with clinical applications

Artificial intelligence (AI) has been approved for biomedical research in diverse areas from bedside clinical studies to benchtop basic scientific research. For ophthalmic research, in particular glaucoma, AI applications are rapidly growing for potential clinical translation given the vast data available and the introduction of federated learning. Conversely, AI for basic science remains limited despite its useful power in providing mechanistic insight. In this perspective, we discuss recent progress, opportunities, and challenges in the application of AI in glaucoma for scientific discoveries. Specifically, we focus on the research paradigm of reverse translation, in which clinical data are first used for patient-centered hypothesis generation followed by transitioning into basic science studies for hypothesis validation. We elaborate on several distinctive areas of research opportunities for reverse translation of AI in glaucoma including disease risk and progression prediction, pathology characterization, and sub-phenotype identification. We conclude with current challenges and future opportunities for AI research in basic science for glaucoma such as inter-species diversity, AI model generalizability and explainability, as well as AI applications using advanced ocular imaging and genomic data.

Multivariate Longitudinal Modeling of Macular Ganglion Cell Complex: Spatiotemporal Correlations and Patterns of Longitudinal Change

Purpose

To investigate spatiotemporal correlations among ganglion cell complex (GCC) superpixel thickness measurements and explore underlying patterns of longitudinal change across the macular region.

Design

Longitudinal cohort study.

Subjects

One hundred eleven eyes from 111 subjects from the Advanced Glaucoma Progression Study with ≥ 4 visits and ≥ 2 years of follow-up.

Methods

We further developed our proposed Bayesian hierarchical model for studying longitudinal GCC thickness changes across macular superpixels in a cohort of glaucoma patients. Global priors were introduced for macular superpixel parameters to combine data across superpixels and better estimate population slopes and intercepts.

Main Outcome Measures

Bayesian residual analysis to inspect cross-superpixel correlations for subject random effects and residuals. Principal component analysis (PCA) to explore underlying patterns of longitudinal macular change.

Results

Average (standard deviation [SD]) follow-up and baseline 10-2 visual field mean deviation were 3.6 (0.4) years and -8.9 (5.9) dB, respectively. Superpixel-level random effects and residuals had the greatest correlations with nearest neighbors; correlations were higher in the superior than in the inferior region and strongest among random intercepts, followed by random slopes, residuals, and residual SDs. PCA of random intercepts showed a first large principal component (PC) across superpixels that approximated a global intercept, a second PC that contrasted the superior and inferior macula, and a third PC, contrasting inner and nasal superpixels with temporal and peripheral superpixels. PCs for slopes, residual SDs, and residuals were remarkably similar to those of random intercepts.

Conclusions

Introduction of cross-superpixel random intercepts and slopes is expected to improve estimation of population and subject parameters. Further model enhancement may be possible by including cross-superpixel random effects and correlations to address spatiotemporal relationships in longitudinal data sets.

Optical Microangiography and Progressive Ganglion Cell-Inner Plexiform Layer Loss in Primary Open-Angle Glaucoma

PURPOSE

To evaluate the association between optical microangiography (OMAG) measurements and progressive ganglion cell-inner plexiform layer (GCIPL) loss in patients with primary open-angle glaucoma (POAG).

DESIGN

Prospective case series.

METHODS

Sixty-three eyes of 38 patients with POAG were studied for ≥2 years and with ≥ 3 optical coherence tomography examinations. Only those hemifields with mild to moderate functional damage at baseline (106 hemifields) were included in the analysis. OMAG imaging was performed at the baseline visit. The effects of clinical parameters (age, gender, central corneal thickness, presence of disc hemorrhage, and mean and fluctuation of intraocular pressure), baseline mean deviation, retinal nerve fiber layer, and GCIPL thickness and baseline OMAG measurements (peripapillary and macular perfusion density [PD] and vessel density [VD]) on the rate of change of GCIPL thickness were evaluated using linear mixed models.

RESULTS

Average (± standard deviation) mean deviation, quadrant retinal nerve fiber layer, and sector GCIPL thickness of the analyzed hemifields respectively at baseline were -5.2 ± 2.8 dB, 94.5 ± 20.0 µm, and 72.4 ± 8.7 µm, respectively. Peripapillary PD and VD in the quadrant were 43.1% ± 7.0% and 17.0 ± 2.6 mm/mm², respectively. Macular PD and VD in the quadrant were 37.2% ± 6.9% and 15.1 ± 2.6 mm/mm², respectively. Rate of sector GCIPL change was -0.97 ± 0.15 µm per year. Multivariate mixed models showed that lower peripapillary PD (coefficient 0.04, P = .01) and VD (coefficient 0.09, P = .05) were significantly associated with a faster rate of GCIPL loss.

CONCLUSIONS

Lower baseline peripapillary OMAG measurements were significantly associated with a faster rate of GCIPL loss in patients with mild to moderate POAG.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology

PURPOSE OF REVIEW

The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each.

RECENT FINDINGS

Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks.

SUMMARY

AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.

[Artificial intelligence and glaucoma: A literature review]

In recent years, research in artificial intelligence (AI) has experienced an unprecedented surge in the field of ophthalmology, in particular glaucoma. The diagnosis and follow-up of glaucoma is complex and relies on a body of clinical evidence and ancillary tests. This large amount of information from structural and functional testing of the optic nerve and macula makes glaucoma a particularly appropriate field for the application of AI. In this paper, we will review work using AI in the field of glaucoma, whether for screening, diagnosis or detection of progression. Many AI strategies have shown promising results for glaucoma detection using fundus photography, optical coherence tomography, or automated perimetry. The combination of these imaging modalities increases the performance of AI algorithms, with results comparable to those of humans. We will discuss potential applications as well as obstacles and limitations to the deployment and validation of such models. While there is no doubt that AI has the potential to revolutionize glaucoma management and screening, research in the coming years will need to address unavoidable questions regarding the clinical significance of such results and the explicability of the predictions.

Combining Structural and Vascular Parameters to Discriminate Among Glaucoma Patients, Glaucoma Suspects, and Healthy Subjects

Purpose

Compare the ability of peripapillary and macular structural parameters, vascular parameters, and their integration to discriminate among glaucoma, suspected glaucoma (GS), and healthy controls (HCs).

Methods

In this study, 196 eyes of 119 patients with glaucoma (n = 81), patients with GS (n = 48), and HCs (n = 67) underwent optical coherence tomography (OCT) and OCT angiography to measure peripapillary retinal nerve fiber layer (pRNFL), macular ganglion cell-inner plexiform layer (mGCIPL) thicknesses, radial peripapillary capillary perfusion density (RPC-PD), and macular GCIPL perfusion density (GCIPL-PD). Parameters were integrated regionally with logistic regression and globally with machine learning algorithms. Diagnostic performances were evaluated with area under the receiver operating characteristic (AUROC) curves.

Results

Patients with glaucoma had mild to moderate damage (median, -3.3 dB; interquartile range, -6.5 to -1.4). In discriminating between patients with glaucoma and the HCs, pRNFL thickness had higher AUROC curve values than RPC-PD for average (0.87 vs. 0.62; P < 0.001), superior (0.86 vs. 0.54; P < 0.001), inferior (0.90 vs. 0.71; P < 0.001), and temporal (0.65 vs. 0.51; P = 0.02) quadrants. mGCIPL thickness had higher AUROC curve values than GCIPL-PD for average (0.84 vs. 0.68; P < 0.001), superotemporal (0.76 vs. 0.65; P = 0.016), superior (0.72 vs. 0.57; P = 0.004), superonasal (0.70 vs. 0.56; P = 0.01), inferotemporal (0.90 vs. 0.72; P < 0.001), inferior (0.87 vs. 0.69; P < 0.001), and inferonasal (0.78 vs. 0.65, P = 0.012) sectors. All structural multisector indices had higher diagnostic ability than vascular ones (P < 0.001). Combined structural-vascular indices did not outperform structural indices. Similar results were found to discriminate glaucoma from GS.

Conclusions

Combining structural and vascular parameters in a structural-vascular index does not improve diagnostic ability over structural parameters alone.

Translational Relevance

OCT angiography does not add additional benefit to structural OCT in early to moderate glaucoma diagnosis.

Slowed Saccadic Reaction Times in Seemingly Normal Parts of Glaucomatous Visual Fields

Purpose: In eye movement perimetry, peripheral stimuli are confirmed by goal-directed eye movements toward the stimulus. The saccadic reaction time (SRT) is regarded as an index of visual field responsiveness, whereas in standard automated perimetry (SAP), the visual field sensitivity is tested. We investigated the relation between visual field sensitivity and responsiveness in corresponding locations of the visual field in healthy controls and in patients with mild, moderate and advanced glaucoma.

Materials and Methods: Thirty-four healthy control subjects and 42 glaucoma patients underwent a 54-point protocol in eye movement perimetry (EMP) and a 24-2 SITA standard protocol in a Humphrey Field Analyzer. The visual field points were stratified by total deviation sensitivity loss in SAP into 6 strata. A generalized linear mixed model was applied to determine the influence of the various factors.

Results: The generalized linear mixed model showed that the mean SRT increased with increasing glaucoma severity, from 479 ms in the control eyes to 678 ms in the eyes of patients with advanced glaucoma (p < 0.001). Mean SRTs significantly increased with increasing SAP sensitivity loss. Even at the locations where no sensitivity loss was detected by SAP (total deviation values greater or equal than 0 dB), we found lengthened SRTs in mild, moderate and advanced glaucoma compared to healthy controls (p < 0.05) and in moderate and advanced glaucoma compared to mild glaucoma (p < 0.05). At locations with total deviation values between 0 and −3 dB, −3 and −6 dB and −6 and −12 dB, we found similar differences.

Conclusions: The lengthened SRT in areas with normal retinal sensitivities in glaucomatous eyes, i.e., planning and execution of saccades to specific locations, precede altered sensory perception as assessed with SAP. Better understanding of altered sensory processing in glaucoma might allow earlier diagnosis of emerging glaucoma.

Macular Optical Coherence Tomography Imaging in Glaucoma

The advent of spectral-domain optical coherence tomography has played a transformative role in posterior segment imaging of the eye. Traditionally, images of the optic nerve head and the peripapillary area have been used to evaluate the structural changes associated with glaucoma. Recently, there is growing evidence in the literature supporting the use of macular spectral-domain optical coherence tomography as a complementary tool for clinical evaluation and research purposes in glaucoma. Containing more than 50% of retinal ganglion cells in a multilayered pattern, macula is shown to be affected even at the earliest stages of glaucomatous structural damage. Risk assessment for glaucoma progression, earlier detection of glaucomatous structural damage, monitoring of glaucoma especially in advanced cases, and glaucoma evaluation in certain ocular conditions including eyes with high myopia, positive history of disc hemorrhage, and certain optic disc phenotypes are specific domains where macular imaging yields complementary information compared to optic nerve head and peripapillary evaluation using optical coherence tomography. Moreover, the development of artificial intelligence models in data analysis has enabled a tremendous opportunity to create an integrated representation of structural and functional alterations observed in glaucoma. In this study, we aimed at providing a brief review of the main clinical applications and future potential utility of macular spectral-domain optical coherence tomography in glaucoma.