Combining spectral domain optical coherence tomography structural parameters for the diagnosis of glaucoma with early visual field loss

A Hybrid Deep Learning Classification of Perimetric Glaucoma Using Peripapillary Nerve Fiber Layer Reflectance and Other OCT Parameters from Three Anatomy Regions

Précis

A hybrid deep-learning model combines NFL reflectance and other OCT parameters to improve glaucoma diagnosis.

Objective

To investigate if a deep learning model could be used combine nerve fiber layer (NFL) reflectance and other OCT parameters for glaucoma diagnosis.

Patients and Methods

This is a prospective observational study where of 106 normal subjects and 164 perimetric glaucoma (PG) patients. Peripapillary NFL reflectance map, NFL thickness map, optic head analysis of disc, and macular ganglion cell complex thickness were obtained using spectral domain OCT. A hybrid deep learning model combined a fully connected network (FCN) and a convolution neural network (CNN) to develop to combine those OCT maps and parameters to distinguish normal and PG eyes. Two deep learning models were compared based on whether the NFL reflectance map was used as part of the input or not.

Results

The hybrid deep learning model with reflectance achieved 0.909 sensitivity at 99% specificity and 0.926 at 95%. The overall accuracy was 0.948 with 0.893 sensitivity and 1.000 specificity, and the AROC was 0.979, which is significantly better than the logistic regression models (p < 0.001). The second best model is the hybrid deep learning model w/o reflectance, which also had significantly higher AROC than logistic regression models (p < 0.001). Logistic regression with reflectance model had slightly higher AROC or sensitivity than the other logistic regression model without reflectance (p = 0.024).

Conclusions

Hybrid deep learning model significantly improved the diagnostic accuracy, without or without NFL reflectance. Hybrid deep learning model, combining reflectance/NFL thickness/GCC thickness/ONH parameter, may be a practical model for glaucoma screen purposes.

Diagnosis of Glaucoma Based on Few-Shot Learning with Wide-Field Optical Coherence Tomography Angiography

This study evaluated the utility of incorporating deep learning into the relatively novel imaging technique of wide-field optical coherence tomography angiography (WF-OCTA) for glaucoma diagnosis. To overcome the challenge of limited data associated with this emerging imaging, the application of few-shot learning (FSL) was explored, and the advantages observed during its implementation were examined. A total of 195 eyes, comprising 82 normal controls and 113 patients with glaucoma, were examined in this study. The system was trained using FSL instead of traditional supervised learning. Model training can be presented in two distinct ways. Glaucoma feature detection was performed using ResNet18 as a feature extractor. To implement FSL, the ProtoNet algorithm was utilized to perform task-independent classification. Using this trained model, the performance of WF-OCTA through the FSL technique was evaluated. We trained the WF-OCTA validation method with 10 normal and 10 glaucoma images and subsequently examined the glaucoma detection effectiveness. FSL using the WF-OCTA image achieved an area under the receiver operating characteristic curve (AUC) of 0.93 (95% confidence interval (CI): 0.912-0.954) and an accuracy of 81%. In contrast, supervised learning using WF-OCTA images produced worse results than FSL, with an AUC of 0.80 (95% CI: 0.778-0.823) and an accuracy of 50% (p-values < 0.05). Furthermore, the FSL method using WF-OCTA images demonstrated improvement over the conventional OCT parameter-based results (all p-values < 0.05). This study demonstrated the effectiveness of applying deep learning to WF-OCTA for glaucoma diagnosis, highlighting the potential of WF-OCTA images in glaucoma diagnostics. Additionally, it showed that FSL could overcome the limitations associated with a small dataset and is expected to be applicable in various clinical settings.

Comparison of Optical Coherence Tomography Structural Parameters for Diagnosis of Glaucoma in High Myopia

Importance

Diagnosis of glaucoma in highly myopic eyes is challenging. This study compared the glaucoma detection utility of various optical coherence tomography (OCT) parameters for high myopia.

Objective

To compare the diagnostic accuracy of single OCT parameters, the University of North Carolina (UNC) OCT Index, and the temporal raphe sign for discrimination of glaucoma in patients with high myopia.

Design, Setting, and Participants

This was a retrospective cross-sectional study conducted from January 1, 2014, and January 1, 2022. Participants with high myopia (axial length ≥26.0 mm or spherical equivalent ≤-6 diopters) plus glaucoma and participants with high myopia without glaucoma were recruited from a single tertiary hospital in South Korea.

Exposures

Macular ganglion cell-inner plexiform layer (GCIPL) thickness, peripapillary retinal nerve fiber layer (RNFL) thickness, and optic nerve head (ONH) parameters were measured in each participant. The UNC OCT scores and the temporal raphe sign were checked to compare diagnostic utility. Decision tree analysis with single OCT parameters, the UNC OCT Index, and the temporal raphe sign were also applied.

Main outcome and Measures

Area under the receiver operating characteristic curve (AUROC).

Results

A total of 132 individuals with high myopia and glaucoma (mean [SD] age, 50.0 [11.7] years; 78 male [59.1%]) along with 142 individuals with high myopia without glaucoma (mean [SD] age, 50.0 [11.3] years; 79 female [55.6%]) were included in the study. The AUROC of the UNC OCT Index was 0.891 (95% CI, 0.848-0.925). The AUROC of temporal raphe sign positivity was 0.922 (95% CI, 0.883-0.950). The best single OCT parameter was inferotemporal GCIPL thickness (AUROC, 0.951; 95% CI, 0.918-0.973), and its AUROC difference from the UNC OCT Index, temporal raphe sign, mean RNFL thickness, and ONH rim area was 0.060 (95% CI, 0.016-0.103; P = .007); 0.029 (95% CI, -0.009 to 0.068; P = .13), 0.022 (95% CI, -0.012-0.055; P = .21), and 0.075 (95% CI, 0.031-0.118; P < .001), respectively.

Conclusions and Relevance

Results of this cross-sectional study suggest that in discriminating glaucomatous eyes in patients with high myopia, inferotemporal GCIPL thickness yielded the highest AUROC value. The RNFL thickness and GCIPL thickness parameters may play a greater role in glaucoma diagnosis than the ONH parameters in high myopia.

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.

Evaluation of University of North Carolina OCT Index for Diagnosis of Early Glaucoma

PURPOSE

To evaluate the diagnostic performance of the University of North Carolina (UNC) OCT Index based on Cirrus high-definition OCT to discriminate early glaucomatous eyes from normal eyes in clinical practice.

DESIGN

Evaluation of diagnostic test or technology.

PARTICIPANTS

Ninety-eight patients with early glaucoma and 98 age-matched normal subjects.

METHODS

Macular ganglion cell-inner plexiform layer (GCIPL) thickness, peripapillary retinal nerve fiber layer (RNFL) thickness, and optic nerve head parameters were measured in each subject. The measurements were run through the UNC OCT algorithm to compare their diagnostic abilities.

MAIN OUTCOME MEASURES

Area under the curve (AUC) of the receiver operating characteristic and sensitivity at 95% specificity.

RESULTS

The AUC of the UNC OCT Index was 0.974. The best AUCs of the single parameters were those of the minimum GCIPL (0.926) of the macular GCIPL, average RNFL (0.916) of the peripapillary RNFL, and rim area (0.964) of the optic nerve head. The AUC of the UNC OCT Index was significantly greater than those of the minimum GCIPL and average RNFL (all P values < 0.05), and also outperformed the rim area. The sensitivity value of the UNC OCT Index (90.8) was greater than that of single OCT parameters (minimum GCIPL, 42.9; average RNFL, 64.3; rim area, 84.7) at 95% specificity.

CONCLUSIONS

The diagnostic performance of the UNC OCT Index in discriminating early glaucomatous eyes from normal eyes is high and exceeds the best optic nerve head, peripapillary RNFL, and macular GCIPL parameters in clinical practice.

Predicting Glaucoma Progression Requiring Surgery Using Clinical Free-Text Notes and Transfer Learning With Transformers

Purpose

We evaluated the use of massive transformer-based language models to predict glaucoma progression requiring surgery using ophthalmology clinical notes from electronic health records (EHRs).

Methods

Ophthalmology clinical notes for 4512 glaucoma patients at a single center from 2008 to 2020 were identified from the EHRs. Four different pre-trained Bidirectional Encoder Representations from Transformers (BERT)-based models were fine-tuned on ophthalmology clinical notes from the patients' first 120 days of follow-up for the task of predicting which patients would require glaucoma surgery. Models were evaluated with standard metrics, including area under the receiver operating characteristic curve (AUROC) and F1 score.

Results

Of the patients, 748 progressed to require glaucoma surgery (16.6%). The original BERT model had the highest AUROC (73.4%; F1 = 45.0%) for identifying these patients, followed by RoBERTa, with an AUROC of 72.4% (F1 = 44.7%); DistilBERT, with an AUROC of 70.2% (F1 = 42.5%); and BioBERT, with an AUROC of 70.1% (F1 = 41.7%). All models had higher F1 scores than an ophthalmologist's review of clinical notes (F1 = 29.9%).

Conclusions

Using transfer learning with massively pre-trained BERT-based models is a natural language processing approach that can access the wealth of clinical information stored within ophthalmology clinical notes to predict the progression of glaucoma. Future work to improve model performance can focus on integrating structured or imaging data or further tailoring the BERT models to ophthalmology domain-specific text.

Translational Relevance

Predictive models can provide the basis for clinical decision support tools to aid clinicians in identifying high- or low-risk patients to maximally tailor glaucoma treatments.

Structural abnormalities associated with glaucoma using swept-source optical coherence tomography in patients with systemic sclerosis

PURPOSE

Vasospasm represents an early event in systemic sclerosis (SSc). Ocular vasospasm may induce optic nerve head (ONH) damage and has been involved in the pathogenesis of glaucoma, especially normal-tension glaucoma (NTG). We aimed to investigate the presence of structural abnormalities associated with NTG using swept-source optical coherence tomography (SS-OCT) and to correlate the OCT parameters with clinical, capillaroscopy and digital blood flow measures in patients with SSc.

METHODS

In this cross-sectional study, 40 patients with SSc and 23 age-matched controls were included. The following parameters were measured using SS-OCT: mean and sectoral retinal nerve fibre layer (RNFL) thickness, macular ganglion cell layer complex (GCC) thickness and ONH morphology. Nailfold capillaroscopy (NFC) and digital blood flow measurements using laser Doppler imaging (LDI) were performed in all subjects.

RESULTS

Patients with SSc showed a thinner temporal RNFL than the controls (69.23 ± 11.74 versus 83.35 ± 20.19 µm, p = 0.001). The other parameters were similar between the two groups. In SSc patients, there was an inverse correlation between the disease duration and the average, superior and inferior RNFL thickness and the GCC thickness and between Raynaud's phenomenon duration and the average RNFL and GCC thickness (p < 0.05). NFC and LDI measurements did not show correlations with OCT parameters.

CONCLUSION

A thinner temporal RNFL and the correlation between Raynaud's phenomenon and disease duration and structural abnormalities on OCT suggest the presence of early ganglion cell damage in patients with SSc. Although mild, these findings indicate the need to monitor ocular abnormalities in SSc.

Predicting 10-2 Visual Field From Optical Coherence Tomography in Glaucoma Using Deep Learning Corrected With 24-2/30-2 Visual Field

Purpose

To investigate whether a correction based on a Humphrey field analyzer (HFA) 24-2/30-2 visual field (VF) can improve the prediction performance of a deep learning model to predict the HFA 10-2 VF test from macular optical coherence tomography (OCT) measurements.

Methods

This is a multicenter, cross-sectional study. The training dataset comprised 493 eyes of 285 subjects (407, open-angle glaucoma [OAG]; 86, normative) who underwent HFA 10-2 testing and macular OCT. The independent testing dataset comprised 104 OAG eyes of 82 subjects who had undergone HFA 10-2 test, HFA 24-2/30-2 test, and macular OCT. A convolutional neural network (CNN) DL model was trained to predict threshold sensitivity (TH) values in HFA 10-2 from retinal thickness measured by macular OCT. The predicted TH values was modified by pattern-based regularization (PBR) and corrected with HFA 24-2/30-2. Absolute error (AE) of mean TH values and mean absolute error (MAE) of TH values were compared between the CNN-PBR alone model and the CNN-PBR corrected with HFA 24-2/30-2.

Results

AE of mean TH values was lower in the CNN-PBR with HFA 24-2/30-2 correction than in the CNN-PBR alone (1.9dB vs. 2.6dB; P = 0.006). MAE of TH values was lower in the CNN-PBR with correction compared to the CNN-PBR alone (4.2dB vs. 5.3 dB; P < 0.001). The inferior temporal quadrant showed lower prediction errors compared with other quadrants.

Conclusions

The performance of a DL model to predict 10-2 VF from macular OCT was improved by the correction with HFA 24-2/30-2.

Translational Relevance

This model can reduce the burden of additional HFA 10-2 by making the best use of routinely performed HFA 24-2/30-2 and macular OCT.

Deep Learning-based Diagnosis of Glaucoma Using Wide-field Optical Coherence Tomography Images

PURPOSE

(1) To evaluate the performance of deep learning (DL) classifier in detecting glaucoma, based on wide-field swept-source optical coherence tomography (SS-OCT) images. (2) To assess the performance of DL-based fusion methods in diagnosing glaucoma using a variety of wide-field SS-OCT images and compare their diagnostic abilities with that of conventional parameter-based methods.

METHODS

Overall, 675 eyes, including 258 healthy eyes and 417 eyes with glaucoma were enrolled in this retrospective observational study. Each single-page wide-field report (12×9 mm) of wide-field SS-OCT imaging provides different types of images that reflect the state of the eyes. A DL-based automated diagnosis system was proposed to detect glaucoma and identify its stage based on such images. We applied the convolutional neural network to each type of image to detect glaucoma. In addition, 2 fusion strategies, fusion by convolution network (FCN) and fusion by fully connected network (FFC) were developed; they differ in terms of the level of fusion of features derived from convolutional neural networks. The diagnostic models were trained using 382 and 293 images in the training and test data sets, respectively. The diagnostic ability of this method was compared with conventional parameters of the thickness of the retinal nerve fiber layer and ganglion cell complex.

RESULTS

FCN achieved an area under the receiver operating characteristic curve (AUC) of 0.987 (95% confidence interval, CI: 0.968-0.996) and an accuracy of 95.22%. In contrast, FFC achieved an AUC of 0.987 (95% CI, 0.971-0.998) and an accuracy of 95.90%. Both FCN and FFC outperformed the conventional method (P<0.001). In detecting early glaucoma, both FCN and FFC achieved significantly higher AUC and accuracy than the conventional approach (P<0.001). In addition, the classification performance of the DL-based fusion methods in identifying the 5 stages of glaucoma is presented via a confusion matrix.

CONCLUSION

DL protocol based on wide-field OCT images outperformed the conventional method in terms of both AUC and accuracy. Therefore, DL-based diagnostic methods using wide-field OCT images are promising in diagnosing glaucoma in clinical practice.

Focal Loss Analysis of Nerve Fiber Layer Reflectance for Glaucoma Diagnosis

Purpose

To evaluate nerve fiber layer (NFL) reflectance for glaucoma diagnosis.

Methods

Participants were imaged with 4.5 × 4.5 mm volumetric disc scans using spectral-domain optical coherence tomography. The normalized NFL reflectance map was processed by an azimuthal filter to reduce directional reflectance bias caused by variation of beam incidence angle. The peripapillary area of the map was divided into 160 superpixels. Average reflectance was the mean of superpixel reflectance. Low-reflectance superpixels were identified as those with NFL reflectance below the fifth percentile normative cutoff. Focal reflectance loss was measured by summing loss in low-reflectance superpixels.

Results

Thirty-five normal, 30 preperimetric, and 35 perimetric glaucoma participants were enrolled. Azimuthal filtering improved the repeatability of the normalized NFL reflectance, as measured by the pooled superpixel standard deviation (SD), from 0.73 to 0.57 dB (P < 0.001, paired t-test) and reduced the population SD from 2.14 to 1.78 dB (P < 0.001, t-test). Most glaucomatous reflectance maps showed characteristic patterns of contiguous wedge or diffuse defects. Focal NFL reflectance loss had significantly higher diagnostic sensitivity than the best NFL thickness parameter (from map or profile): 77% versus 55% (P < 0.001) in glaucoma eyes with the specificity fixed at 99%.

Conclusions

Azimuthal filtering reduces the variability of NFL reflectance measurements. Focal NFL reflectance loss has excellent glaucoma diagnostic accuracy compared to the standard NFL thickness parameters. The reflectance map may be useful for localizing NFL defects.

Translational Relevance

The high diagnostic accuracy of NFL reflectance may make population-based screening feasible.

High interpretable machine learning classifier for early glaucoma diagnosis

AIM

To develop a classifier for differentiating between healthy and early stage glaucoma eyes based on peripapillary retinal nerve fiber layer (RNFL) thicknesses measured with optical coherence tomography (OCT), using machine learning algorithms with a high interpretability.

METHODS

Ninety patients with early glaucoma and 85 healthy eyes were included. Early glaucoma eyes showed a visual field (VF) defect with mean deviation >-6.00 dB and characteristic glaucomatous morphology. RNFL thickness in every quadrant, clock-hour and average thickness were used to feed machine learning algorithms. Cluster analysis was conducted to detect and exclude outliers. Tree gradient boosting algorithms were used to calculate the importance of parameters on the classifier and to check the relation between their values and its impact on the classifier. Parameters with the lowest importance were excluded and a weighted decision tree analysis was applied to obtain an interpretable classifier. Area under the ROC curve (AUC), accuracy and generalization ability of the model were estimated using cross validation techniques.

RESULTS

Average and 7 clock-hour RNFL thicknesses were the parameters with the highest importance. Correlation between parameter values and impact on classification displayed a stepped pattern for average thickness. Decision tree model revealed that average thickness lower than 82 µm was a high predictor for early glaucoma. Model scores had AUC of 0.953 (95%CI: 0.903-0998), with an accuracy of 89%.

CONCLUSION

Gradient boosting methods provide accurate and highly interpretable classifiers to discriminate between early glaucoma and healthy eyes. Average and 7-hour RNFL thicknesses have the best discriminant power.

Predicting the central 10 degrees visual field in glaucoma by applying a deep learning algorithm to optical coherence tomography images

We aimed to develop a model to predict visual field (VF) in the central 10 degrees in patients with glaucoma, by training a convolutional neural network (CNN) with optical coherence tomography (OCT) images and adjusting the values with Humphrey Field Analyzer (HFA) 24–2 test. The training dataset included 558 eyes from 312 glaucoma patients and 90 eyes from 46 normal subjects. The testing dataset included 105 eyes from 72 glaucoma patients. All eyes were analyzed by the HFA 10-2 test and OCT; eyes in the testing dataset were additionally analyzed by the HFA 24-2 test. During CNN model training, the total deviation (TD) values of the HFA 10-2 test point were predicted from the combined OCT-measured macular retinal layers’ thicknesses. Then, the predicted TD values were corrected using the TD values of the innermost four points from the HFA 24-2 test. Mean absolute error derived from the CNN models ranged between 9.4 and 9.5 B. These values reduced to 5.5 dB on average, when the data were corrected using the HFA 24-2 test. In conclusion, HFA 10-2 test results can be predicted with a OCT images using a trained CNN model with adjustment using HFA 24-2 test.

Retinal Ganglion Cells-Diversity of Cell Types and Clinical Relevance

Retinal ganglion cells (RGCs) are the bridging neurons that connect the retinal input to the visual processing centres within the central nervous system. There is a remarkable diversity of RGCs and the various subtypes have unique morphological features, distinct functions, and characteristic pathways linking the inner retina to the relevant brain areas. A number of psychophysical and electrophysiological tests have been refined to investigate this large and varied population of RGCs. Technological advances, such as high-resolution optical coherence tomography imaging, have provided additional tools to define the pattern of RGC involvement and the chronological sequence of events in both inherited and acquired optic neuropathies. The mechanistic insights gained from these studies, in particular the selective vulnerability and relative resilience of particular RGC subtypes, are of fundamental importance as they are directly relevant to the development of targeted therapies for these invariably progressive blinding diseases. This review provides a comprehensive description of the various types of RGCs, the developments in proposed methods of classification, and the current gaps in our knowledge of how these RGCs are differentially affected depending on the underlying aetiology. The synthesis of the current body of knowledge on the diversity of RGCs and the pathways that are potentially amenable to therapeutic modulation will hopefully lead to much needed effective treatments for patients with optic neuropathies.

Predicting the Glaucomatous Central 10-Degree Visual Field From Optical Coherence Tomography Using Deep Learning and Tensor Regression

PURPOSE

To predict the visual field (VF) of glaucoma patients within the central 10° from optical coherence tomography (OCT) measurements using deep learning and tensor regression.

DESIGN

Cross-sectional study.

METHODS

Humphrey 10-2 VFs and OCT measurements were carried out in 505 eyes of 304 glaucoma patients and 86 eyes of 43 normal subjects. VF sensitivity at each test point was predicted from OCT-measured thicknesses of macular ganglion cell layer + inner plexiform layer, retinal nerve fiber layer, and outer segment + retinal pigment epithelium. Two convolutional neural network (CNN) models were generated: (1) CNN-PR, which simply connects the output of the CNN to each VF test point; and (2) CNN-TR, which connects the output of the CNN to each VF test point using tensor regression. Prediction performance was assessed using 5-fold cross-validation through the root mean squared error (RMSE). For comparison, RMSE values were also calculated using multiple linear regression (MLR) and support vector regression (SVR). In addition, the absolute prediction error for predicting mean sensitivity in the whole VF was analyzed.

RESULTS

RMSE with the CNN-TR model averaged 6.32 ± 3.76 (mean ± standard deviation) dB. Significantly (P < .05) larger RMSEs were obtained with other models: CNN-PR (6.76 ± 3.86 dB), SVR (7.18 ± 3.87 dB), and MLR (8.56 ± 3.69 dB). The absolute mean prediction error for the whole VF was 2.72 ± 2.60 dB with the CNN-TR model.

CONCLUSION

The Humphrey 10-2 VF can be predicted from OCT-measured retinal layer thicknesses using deep learning and tensor regression.

Improving Visual Field Trend Analysis with OCT and Deeply Regularized Latent-Space Linear Regression

PURPOSE

To investigate whether OCT measurements can improve visual field (VF) trend analyses in glaucoma patients using the deeply regularized latent-space linear regression (DLLR) model.

DESIGN

Retrospective cohort study.

PARTICIPANTS

Training and testing datasets included 7984 VF results from 998 eyes of 592 patients and 1184 VF results from 148 eyes of 84 patients with open-angle glaucoma, respectively. Each eye underwent a series of 8 VF tests with the Humphrey Field Analyzer OCT series obtained within the same observation period.

METHODS

Using pointwise linear regression (PLR), the threshold values of a patient's eighth VF results were predicted using values from shorter VF series (first to second VF tests [VF1-2], first to third VF tests, . . . , to first to seventh VF tests [VF1-7]), and the root mean square error (RMSE) was calculated. With DLLR, OCT measurements (macular retinal nerve fiber layer thickness, the thickness of macular ganglion cell layer and inner plexiform layer, and the thickness of the outer segment and retinal pigment epithelium) that were obtained within the period of shorter VF series were incorporated into the model to predict the eighth VF.

MAIN OUTCOME MEASURES

Prediction accuracy of VF trend analyses.

RESULTS

The mean ± standard deviation RMSE resulting from PLR averaged 27.48 ± 16.14 dB for VF1-2 and 3.98 ± 2.25 dB for VF1-7. Significantly (P < 0.001) smaller RMSEs were obtained from DLLR: 4.57 ± 2.71 dB (VF1-2) and 3.65 ± 2.27 dB (VF1-7).

CONCLUSIONS

It is useful to include OCT measurements when predicting future VF progression in glaucoma patients, especially with short VF series.

Deep learning model to predict visual field in central 10° from optical coherence tomography measurement in glaucoma

BACKGROUND/AIM

To train and validate the prediction performance of the deep learning (DL) model to predict visual field (VF) in central 10° from spectral domain optical coherence tomography (SD-OCT).

METHODS

This multicentre, cross-sectional study included paired Humphrey field analyser (HFA) 10-2 VF and SD-OCT measurements from 591 eyes of 347 patients with open-angle glaucoma (OAG) or normal subjects for the training data set. We trained a convolutional neural network (CNN) for predicting VF threshold (TH) sensitivity values from the thickness of the three macular layers: retinal nerve fibre layer, ganglion cell layer+inner plexiform layer and outer segment+retinal pigment epithelium. We implemented pattern-based regularisation on top of CNN to avoid overfitting. Using an external testing data set of 160 eyes of 131 patients with OAG, the prediction performance (absolute error (AE) and R² between predicted and actual TH values) was calculated for (1) mean TH in whole VF and (2) each TH of 68 points. For comparison, we trained support vector machine (SVM) and multiple linear regression (MLR).

RESULTS

AE of whole VF with CNN was 2.84±2.98 (mean±SD) dB, significantly smaller than those with SVM (5.65±5.12 dB) and MLR (6.96±5.38 dB) (all, p<0.001). Mean of point-wise mean AE with CNN was 5.47±3.05 dB, significantly smaller than those with SVM (7.96±4.63 dB) and MLR (11.71±4.15 dB) (all, p<0.001). R² with CNN was 0.74 for the mean TH of whole VF, and 0.44±0.24 for the overall 68 points.

CONCLUSION

DL model showed considerably accurate prediction of HFA 10-2 VF from SD-OCT.

Macular imaging with optical coherence tomography in glaucoma

With the advent of spectral-domain optical coherence tomography, imaging of the posterior segment of the eye can be carried out rapidly at multiple anatomical locations, including the optic nerve head, circumpapillary retinal nerve fiber layer, and macula. There is now ample evidence to support the role of spectral-domain optical coherence tomography imaging of the macula for detection of early glaucoma. Macular spectral-domain optical coherence tomography measurements demonstrate high reproducibility, and evidence on its utility for detection of glaucoma progression is accumulating. We present a comprehensive review of macular spectral-domain optical coherence tomography imaging emerging as an essential diagnostic tool in glaucoma.

Early Glaucoma Discrimination Index

PURPOSE

To develop a new structural algorithm derived from optical coherence tomography (OCT) retinal nerve fiber layer (RNFL) thickness and asymmetry and validate it as a discriminate among normal, suspect, and early primary open-angle glaucoma (POAG).

STUDY DESIGN

A case-controlled observational clinical study.

MATERIALS AND METHODS

In total, 150 subjects (299 eyes) were selected, 61 normal, 46 suspect, and 43 early glaucoma, from Al-Azhar University Hospitals. They were in fifth decade and free from any ocular or systemic diseases affecting the retinal nerve fiber layer. They were investigated by two consecutive perimetry (1 month apart), and three scans of circumpapillary retinal nerve fiber layer (cpRNFL) by using Nidek spectral domain (SD)-OCT 3000 Lite. The cpRNFL thickness (cpRNFLT) and inter-eye asymmetry parameters were analyzed among the three groups. Then some selected parameters were selected and analyzed using a binary logistic regression analysis for developing the new algorithm. The new algorithm was tested for the best fitting, accuracy, and diagnostic ability among the three groups and was validated in the suspect group.

RESULTS

The new algorithm model [early glaucoma discrimination index (EGDI)] works well with only four variables; whole cpRNFLT, inferior quadrant cpRNFLT, inferotemporal clock hour (CH) cpRNFLT, and absolute inter-eye inferior quadrants asymmetry. The highest area under the curve (AUC) obtained from the EGDI among the three groups was 0.854. The validation analysis in the suspect group revealed a higher diagnostic ability in discrimination of early glaucoma with AUC of 0.989 (0.976-1.003).

CONCLUSION

The EGDI showed better diagnostic ability for diagnosis of glaucoma in the pre-perimetric stage. The new OCT algorithm is simple and can be run in any SD-OCT device without dependence on normative data.

HOW TO CITE THIS ARTICLE

Safwat H, Nassar E, Rashwan A. Early Glaucoma Discrimination Index. J Curr Glaucoma Pract 2020;14(1):16-24.

Long segment 3D double inversion recovery (DIR) hypersignal on MRI in glaucomatous optic neuropathy

Background

In this retrospective study the relationship between intraocular pressure (IOP), retinal nerve fiber layer (RNFL) thickness and pathologic hypersignal in optic nerve segments on 3D double inversion recovery (DIR) MR sequence in 21 patients with proven glaucoma of different origin was evaluated.

Methods

All patients were examined on a 3 T MR Philips® scanner. Pathologic optic nerve DIR hypersignal was determined in four different nerve segments. IOP was measured in mmHg by applanation tonometry. RNFL thickness was measured in μm with optical coherence tomography (OCT Heidelberg Engineering Spectralis® apparatus). Wilcoxon rank sum tests, student’s t-tests and (multivariate) linear regression models were appied.

Results

3D DIR hypersignal was present in 17 (41.5%) optic nerves. 3D DIR hypersignal was not related to ischemic or demyelinating optic nerve pathology but was associated with increased IOP (19.8 [24–18]; versus 15.45; [18.85–13.75] mmHg; p = 0.008) and decreased RNFL thickness (61.06 ± 12.1 versus 82.5 ± 21.6 μm; p < 0.001) in comparison to optic nerves of glaucoma patients without DIR hypersignal. Specifically, presence of DIR hypersignal in optic nerves in at least one optic nerve segment lowered RNFL thickness on average by 17.54 μm (p = 0.005) in comparison to optic nerves without DIR hypersignal.

Conclusions

In patients with glaucomatous optic neuropathy (GON) and pathologic optic nerve DIR hypersignal, significantly increased IOP and significantly decreased RNFL thickness values are present. DIR hypersignal seems to be a marker for disease severity in GON related to decreased RNFL thickness and may thus represent long-segment severe axonal degeneration in optic nerves in patients with GON. Venous congestion and edema within the optic nerve related to high IOP may contribute to the DIR hypersignal as well.

Linear discriminant score for differentiating early primary open angle glaucoma from glaucoma suspects

Purpose:

To determine the diagnostic accuracy of a linear discriminant function (LDF) based on macular ganglion cell complex (GCC), optic nerve head (ONH) and retinal nerve fibre layer (RNFL) for differentiating early primary open-angle glaucoma (POAG) from glaucoma suspects.

Methods:

In this cross-sectional study, data from consecutive 127 glaucoma suspects and 74 early POAG eyes were analysed. Each patient underwent detailed ocular examination, standard automated perimetry, GCC and ONH and RNFL analysis. After adjusting for age, gender and signal strength using the analysis of covariance; Benjamin–Hochberg multiple testing correction was performed to detect truly significant parameters to calculate the LDF. Subsequently, diagnostic accuracy of GCC and ONH and RNFL were determined. The obtained LDF score was evaluated for diagnostic accuracy in another test set of 32 suspect and 19 glaucomatous eyes. Data were analysed with the R-3.2.1 (R Core Team 2015), analysis of variance, t-test, Chi-square test and receiver operating curve.

Results:

Among all GCC parameters, infero temporal had the best discriminating power and average RNFL thickness and vertical CDR among ONH and RNFL parameters. LDF scores for GCC had AUROC of 0.809 for a cut-off value 0.07, while scores for ONH and RNFL had AUROC of 0.903 for a cut-off value − 0.24. Analysis on combined parametric space resulted in avg RNFL thickness, vertical CDR, min GCC + IPL and superior GCC + IPL as key parameters. LDF scores obtained had AUROC of 0.924 for a cut-off value 0.1. The LDF was applied to a test set with an accuracy of 84.31%.

Conclusion:

The LDF had a better accuracy than individual GCC and ONH and RNFL parameters and can be used for diagnosis of glaucoma.

Using Deep Learning and Transfer Learning to Accurately Diagnose Early-Onset Glaucoma From Macular Optical Coherence Tomography Images

PURPOSE

We sought to construct and evaluate a deep learning (DL) model to diagnose early glaucoma from spectral-domain optical coherence tomography (OCT) images.

DESIGN

Artificial intelligence diagnostic tool development, evaluation, and comparison.

METHODS

This multi-institution study included pretraining data of 4316 OCT images (RS3000) from 1371 eyes with open angle glaucoma (OAG) regardless of the stage of glaucoma and 193 normal eyes. Training data included OCT-1000/2000 images from 94 eyes of 94 patients with early OAG (mean deviation > -5.0 dB) and 84 eyes of 84 normal subjects. Testing data included OCT-1000/2000 from 114 eyes of 114 patients with early OAG (mean deviation > -5.0 dB) and 82 eyes of 82 normal subjects. A DL (convolutional neural network) classifier was trained using a pretraining dataset, followed by a second round of training using an independent training dataset. The DL model input features were the 8 × 8 grid macular retinal nerve fiber layer thickness and ganglion cell complex layer thickness from spectral-domain OCT. Diagnostic accuracy was investigated in the testing dataset. For comparison, diagnostic accuracy was also evaluated using the random forests and support vector machine models. The primary outcome measure was the area under the receiver operating characteristic curve (AROC).

RESULTS

The AROC with the DL model was 93.7%. The AROC significantly decreased to between 76.6% and 78.8% without the pretraining process. Significantly smaller AROCs were obtained with random forests and support vector machine models (82.0% and 67.4%, respectively).

CONCLUSION

A DL model for glaucoma using spectral-domain OCT offers a substantive increase in diagnostic performance.

Evaluation of spectral domain optical coherence tomography parameters in discriminating preperimetric glaucoma from high myopia

AIM

To evaluate the diagnostic ability of macular ganglion cell-inner plexiform layer (GCIPL) thickness obtained by spectral-domain optical coherence tomography (SD-OCT) in discriminating non-highly myopic eyes with preperimetric glaucoma (PPG) from highly myopic healthy eyes.

METHODS

A total of 254 eyes, including 76 normal controls (NC), 116 eyes with high myopia (HM) and 62 non-highly myopic eyes with PPG were enrolled. The diagnostic ability of OCT parameters was accessed by the areas under the receiver operating characteristic (AUROC) curve in two distinguishing groups: PPG eyes with non-glaucomatous eyes including NC and HM (Group 1), and PPG eyes with HM eyes (Group 2). Differences in diagnostic performance between GCIPL and RNFL parameters were evaluated.

RESULTS

The minimum (AUROC curve of 0.782), inferotemporal (0.758) and inferior (0.705) GCIPL thickness were the top three GCIPL parameters in discriminating PPG from non-glaucomatous eyes, all of which had statistically significant lower diagnostic ability than average RNFL thickness (0.847). In discriminating PPG from HM, the best GCIPL parameter was minimum (0.689), statistically significant lower in diagnostic ability than average RNFL thickness (0.789) and three other RNFL thickness parameters of temporal and inferotemporal clock-hour sectors.

CONCLUSION

The minimum GCIPL thickness is the best GCIPL parameter to detect non-highly myopic PPG from highly myopic eyes, whose diagnostic ability is inferior to that of average RNFL thickness and RNFL thickness of several temporal and inferotemporal clock-hour sectors. The average RNFL thickness is recommended for discriminating PPG from highly myopic healthy eyes in current clinical practice in a Chinese population.

A new diagnostic model of primary open angle glaucoma based on FD-OCT parameters

AIM

To build a clinical diagnostic model of primary open angle glaucoma (POAG) using the normal probability chart of frequency-domain optical coherence tomography (FD-OCT).

METHODS

This is a cross-sectional study. Total 133 eyes from 133 healthy subjects and 99 eyes from 99 early POAG patients were included in the study. The retinal nerve fibre layer (RNFL) thickness parameters of optic nerve head (ONH) and RNFL3.45 scan were measured in one randomly selected eye of each subject using RTVue-100 FD-OCT. Then, we used these parameters to establish the diagnostic models. Four different diagnostic models based on two different area partition strategies on ONH and RNFL3.45 parameters, including ONH traditional area partition model (ONH-T), ONH new area partition model (ONH-N), RNFL3.45 traditional area partition model (RNFL3.45-T) and RNFL3.45 new area partition model (RNFL3.45-N), were built and tested by cross-validation.

RESULTS

The new area partition models had higher area under the receiver operating characteristic (AROC; ONH-N: 0.990; RNFL3.45-N: 0.939) than corresponding traditional area partition models (ONH-T: 0.979; RNFL3.45-T: 0.881). There was no statistical difference among AROC of ONH-T, ONH-N, and RNFL3.45-N. Nevertheless, ONH-N was the simplest model.

CONCLUSION

The new area partition models had higher diagnostic accuracy than corresponding traditional area partition models, which can improve the diagnostic ability of early POAG. In particular, the simplest ONH-N diagnostic model may be convenient for clinical application.

Utility of combining spectral domain optical coherence tomography structural parameters for the diagnosis of early Glaucoma: a mini-review

Optical coherence tomography (OCT) has moved to the forefront of imaging modalities in the management of glaucoma and retinal diseases. It is modifying how glaucoma and glaucoma progression are diagnosed clinically and augmenting our understanding of the disease. OCT provides multiple parameters from various anatomic areas for glaucoma diagnosis, evaluation of treatment efficacy, and progression monitoring. While the use of multiple parameters has increased the likelihood of detecting early structural changes, diagnosing glaucoma in early stages is often challenging when the damages are subtle and not apparent on OCT scans, in addition to the fact that assessment of OCT parameters often yields conflicting findings. One promising approach is to combine multiple individual parameters into a composite parameter from the same test to improve diagnostic accuracy, sensitivity, and specificity. This review presents current evidence regarding the value of spectral domain OCT composite parameters in diagnosing early glaucoma.

Validation of the UNC OCT Index for the Diagnosis of Early Glaucoma

Purpose

To independently validate the performance of the University of North Carolina Optical Coherence Tomography (UNC OCT) Index in diagnosing and predicting early glaucoma.

Methods

Data of 118 normal subjects (118 eyes) and 96 subjects (96 eyes) with early glaucoma defined as visual field mean deviation (MD) greater than -4 decibels (dB), aged 40 to 80 years, and who were enrolled in the Full-Threshold Testing Size III, V, VI comparison study were used in this study. CIRRUS OCT average and quadrants' retinal nerve fiber layer (RNFL); optic disc vertical cup-to-disc ratio (VCDR), cup-to-disc area ratio, and rim area; and average, minimum, and six sectoral ganglion cell-inner plexiform layer (GCIPL) measurements were run through the UNC OCT Index algorithm. Area under the receiver operating characteristic curve (AUC) and sensitivities at 95% and 99% specificity were calculated and compared between single parameters and the UNC OCT Index.

Results

Mean age was 60.1 ± 11.0 years for normal subjects and 66.5 ± 8.1 years for glaucoma patients (P < 0.001). MD was 0.29 ± 1.04 dB and -1.30 ± 1.35 dB in normal and glaucomatous eyes (P < 0.001), respectively. The AUC of the UNC OCT Index was 0.96. The best single metrics when compared to the UNC OCT Index were VCDR (0.93, P = 0.054), average RNFL (0.92, P = 0.014), and minimum GCIPL (0.91, P = 0.009). The sensitivities at 95% and 99% specificity were 85.4% and 76.0% (UNC OCT Index), 71.9% and 62.5% (VCDR, all P < 0.001), 64.6% and 53.1% (average RNFL, all P < 0.001), and 66.7% and 58.3% (minimum GCIPL, all P < 0.001), respectively.

Conclusions

The findings confirm that the UNC OCT Index may provide improved diagnostic perforce over that of single OCT parameters and may be a good tool for detection of early glaucoma.

Translational Relevance

The UNC OCT Index algorithm may be incorporated easily into routine clinical practice and be useful for detecting early glaucoma.

Factors affecting signal strength in spectral-domain optical coherence tomography

PURPOSE

To identify ocular factors that affect signal strength in spectral-domain optical coherence tomography (SD-OCT).

METHODS

Data from 1312 participants of the population-based Singapore Malay Eye Study-2 (SiMES-2) were included in the analysis. All participants underwent standardized ophthalmic examination, including measurements of best-corrected visual acuity (BCVA), refractive error, axial length, corneal curvature and presence of cataracts. Optic disc and macular cube scans were acquired using the Cirrus HD-OCT (software version 6.0, Carl Zeiss Meditec, Dublin, CA, USA). Signal strength of the optical coherence tomography (OCT) scan was recorded for each study eye. Multivariable linear regression analyses were performed to evaluate the associations between ocular factors and signal strength of the OCT scans.

RESULTS

The mean (±SD) age of our study participants was 61 ± 9 years, and 44.6% were male. Mean optic disc scan signal strength was 7.90 ± 1.25, range = 0-10, while mean macular scan signal strength was 8.80 ± 1.27, range = 0-10. In multivariable regression analyses, poorer signal strength in optic disc and macular cube scans was each associated with older age (per decade, β = -0.373, p < 0.001; β = -0.373, p < 0.001, respectively), poorer BCVA (per logMAR line; β = -0.123, p < 0.001; β = -0.156, p < 0.001, respectively), greater degree of myopia (per negative dioptre of spherical equivalent; β = -0.112, p < 0.001; β = -0.117, p < 0.001, respectively), presence of cortical cataracts (β = -0.331, p < 0.001; β = -0.314, p < 0.001, respectively) and presence of posterior subcapsular cataracts (β = -0.910, p < 0.001; β = -0.797, p < 0.001, respectively).

CONCLUSION

We found that older age, poorer BCVA, greater degree of myopia and presence of cortical and posterior subcapsular cataracts were associated with reduced signal strength in Cirrus SD-OCT. Our findings provide information on the barriers to obtaining good image quality when using SD-OCT, and allow clinicians to potentially identify individuals who are more likely to have unreliable OCT measurements.

Detecting Structural Progression in Glaucoma with Optical Coherence Tomography

Optical coherence tomography (OCT) is increasingly used to obtain objective measurements of the retinal nerve fiber layer (RNFL), optic nerve head, and macula for assessing glaucoma progression. Although OCT has been adopted widely in clinical practice, uncertainty remains concerning its optimal role. Questions include: What is the best structure to measure? What quantity of change is significant? Are structural changes relevant to the patient? How are longitudinal measurements affected by aging? How can changes resulting from aging be differentiated from true progression? How best should OCT be used alongside visual fields, and how often should OCT be performed? Recent studies have addressed some of these questions. Important developments include appreciation of the need to use a consistent point of reference for structural measurements, leading to the introduction of Bruch's membrane opening (BMO)-based measurements, including BMO-minimum rim width and BMO-minimum rim area. Commercially available OCT devices also permit analysis of macular changes over time, for example, changes in the ganglion cell and inner plexiform layers, the sites of the retinal ganglion cell bodies and dendrites, respectively. Several longitudinal studies have compared rates of change in RNFL and macular measurements, with some suggesting that the relative value of each parameter may differ at different stages of disease. In early disease, looking for change over time also may be useful for glaucoma diagnosis, with advantages over classifying eyes using cross-sectional normative databases. Optimal glaucoma management requires information from imaging and visual fields, and efforts have been made to combine information, reducing the noise inherent in both tests to benefit from their different performances according to the stage of disease. Combining information from different structural measurements may also be useful. There is now substantial evidence that progressive structural changes are of direct clinical relevance, with progressive changes on OCT often preceding functional loss and patients with faster change on OCT at increased risk of worsening visual losses. Identification of such patients offers the possibility of commencing or escalating treatment at an earlier stage. This review appraises recent developments in the use of OCT for assessing glaucoma progression.

Patterns of Retinal Nerve Fiber Layer Loss in Different Subtypes of Open Angle Glaucoma Using Spectral Domain Optical Coherence Tomography

PURPOSE OF THE STUDY

The purpose of the study was to determine whether there are different patterns of retinal nerve fiber layer (RNFL) thinning as measured by spectral domain optical coherence tomography (SD-OCT) for 4 subtypes of open angle glaucoma (OAG): primary OAG (POAG), normal tension glaucoma (NTG), pseudoexfoliation glaucoma (PXG), and pigmentary glaucoma (PDG) and to compare them with normal controls.

MATERIALS AND METHODS

SD-OCT RNFL thickness values were measured for 4 quadrants and for 4 sectors (ie, superior-nasal, superior-temporal, inferior-nasal, and inferior-temporal). Differences in RNFL thickness values between groups were analyzed using analysis of variance. Paired t tests were used for quadrant comparisons.

RESULTS

Two hundred eighty-five participants (102 POAG patients, 33 with NTG, 48 with PXG, 13 with PDG, and 89 normal patients) were included in this study. All 4 subtypes of OAG showed significant RNFL thinning in the superior, inferior, and nasal quadrants as well as the superior-temporal and inferior-temporal sectors (all P-values <0.0001) compared with normals. POAG and NTG patients had greater RNFL thinning inferiorly and inferior-temporally than superiorly (P-values: 0.002 to 0.018 and 0.006, respectively) compared with PXG patients. In contrast, PDG patients had greater RNFL thinning superiorly and superior-nasally than inferiorly compared with other OAG subtypes (ie, POAG, NTG, PXG groups, with P-values: 0.009, 0.003, 0.009, respectively). Of the 4 OAG subtypes, PXG patients exhibited the greatest degree of inter-eye RNFL asymmetry.

CONCLUSIONS

This study suggests that SD-OCT may be able to detect significant differences in patterns of RNFL thinning for different subtypes of OAG.

The Pattern of Retinal Nerve Fiber Layer and Macular Ganglion Cell-Inner Plexiform Layer Thickness Changes in Glaucoma

Background/Aims

To investigate the patterns of retinal ganglion cell damage at different stages of glaucoma, using the circumpapillary retinal nerve fiber layer (RNFL) and macula ganglion cell-inner plexiform layer (GCIPL) thicknesses.

Methods

In 296 eyes of 296 glaucoma patients and 55 eyes of 55 healthy controls, the correlations of mean deviation (MD) with the superior and inferior quadrant RNFL/GCIPL thickness (defined as the average of three superior and inferior sectors, resp.) were analyzed.

Results

In early to moderate glaucoma, most of the RNFL/GCIPL thicknesses had significant positive correlations with the MD. In advanced glaucoma, the superior GCIPL thickness showed the highest correlation with MD (r = 0.495), followed by the superior RNFL (r = 0.452) (all; P < 0.05). The correlation coefficient of the inferior RNFL thickness with MD (r < 0.471) was significantly stronger in early to moderate glaucoma compared to that in advanced glaucoma (r = 0.192; P < 0.001). In contrast, the correlations of the superior GCIPL thickness with MD (r = 0.452) in advanced glaucoma was significantly stronger compared to that in early to moderate glaucoma (r = 0.159; P < 0.001).

Conclusions

The most preserved region in advanced glaucoma appears to be the superior macular GCIPL, whereas the most vulnerable region for initial glaucoma is the inferior RNFL around the optic disc.

Validating the Usefulness of the "Random Forests" Classifier to Diagnose Early Glaucoma With Optical Coherence Tomography

PURPOSE

To validate the usefulness of the "Random Forests" classifier to diagnose early glaucoma with spectral-domain optical coherence tomography (SDOCT).

METHODS

design: Comparison of diagnostic algorithms.

SETTING

Multiple institutional practices.

STUDY PARTICIPANTS

Training dataset included 94 eyes of 94 open-angle glaucoma (OAG) patients and 84 eyes of 84 normal subjects and testing dataset included 114 eyes of 114 OAG patients and 82 eyes of 82 normal subjects. In both groups, OAG eyes with mean deviation (MD) values better than -5.0 dB were included.

OBSERVATION PROCEDURE

Using the training dataset, classifiers were built to discriminate between glaucoma and normal eyes using 84 OCT measurements using the Random Forests method, multiple logistic regression models based on backward or bidirectional stepwise model selection, a least absolute shrinkage and selection operator regression (LASSO) model, and a Ridge regression model.

MAIN OUTCOME MEASURES

Diagnostic accuracy.

RESULTS

With the testing data, the area under the receiver operating characteristic curve (AROC) with the Random Forests method (93.0%) was significantly (P < .05) larger than those with other models of the stepwise model selections (71.9%), LASSO model (89.6%), and Ridge model (89.2%).

CONCLUSION

It is useful to analyze multiple SDOCT parameters concurrently using the Random Forests method to diagnose glaucoma in early stages.

Discrimination of Glaucoma Patients From Healthy Individuals Using Combined Parameters From Spectral-domain Optical Coherence Tomography in an African American Population

PURPOSE

To create a multivariable predictive model for glaucoma in an exclusively African American population and to compare the performance of the model with individual structural parameters derived from SD-OCT.

PATIENTS AND METHODS

A total of 103 healthy eyes and 118 glaucomatous eyes of African American patients underwent SD-OCT optic disc and macular scanning. Twenty-seven optic nerve head, retinal nerve fiber layer (RNFL), and ganglion cell parameters were collected. A multivariable model was derived using a backward elimination variable selection procedure. Areas under the curve were used to measure the diagnostic performance of the individual parameters and the multivariable model.

RESULTS

The best performing parameters for glaucoma patients included inferior quadrant thickness (AUC=0.9239), average RNFL thickness (AUC=0.9209), sup2 RNFL thickness (AUC=0.9157), superior quadrant thickness (AUC=0.8906), and vertical CDR (AUC=0.8640). The best performing parameters for early glaucoma patients were sup2 RNFL thickness (AUC=0.8680), inferior quadrant thickness (AUC=0.8571), average RNFL thickness (AUC=0.8550), superior quadrant thickness (AUC=0.8420), and inf2 RNFL thickness (AUC=0.8420). The AUC of the multivariable model was 0.8918 for early glaucoma and 0.9744 for moderate/advanced glaucoma. There was some variability in the performance of the model based on disc size.

CONCLUSIONS

These findings confirm that several individual RNFL, ONH, and GCA parameters have excellent diagnostic performance in differentiating glaucomatous patients from healthy patients in African American population. A multivariable model was developed and validated with high diagnostic accuracy.

Optical coherence tomography platforms and parameters for glaucoma diagnosis and progression

PURPOSE OF REVIEW

Optical coherence tomography (OCT) aids in the diagnosis and long-term monitoring of various ocular diseases, including glaucoma. Initially, the retinal nerve fiber layer was the only OCT structural parameter used in glaucoma. Subsequent research has resulted in more retinal and optic nerve head parameters. In addition, OCT is being investigated for its ability to assess ocular hemodynamics. This review summarizes these spectral domain-optical coherence tomography (SDOCT) parameters in the context of glaucoma.

RECENT FINDINGS

Several new SDOCT retinal nerve fiber layer, optic nerve head, and macular parameters with good glaucoma diagnostic ability have been added to existing ones recently. The combination of SDOCT and Doppler or angiography has also resulted in hemodynamic parameters that may prove to be useful in the functional assessment in glaucoma.

SUMMARY

OCT technology is advancing not only as a tool for structural assessment, but also as a multimodality tool to assess both structure and function to enhance our understanding of glaucoma, and ultimately clinical decisions.

Macular versus Retinal Nerve Fiber Layer Parameters for Diagnosing Manifest Glaucoma: A Systematic Review of Diagnostic Accuracy Studies

TOPIC

Macular parameters have been proposed as an alternative to retinal nerve fiber layer (RNFL) parameters to diagnose glaucoma. Comparing the diagnostic accuracy of macular parameters, specifically the ganglion cell complex (GCC) and ganglion cell inner plexiform layer (GCIPL), with the accuracy of RNFL parameters for detecting manifest glaucoma is important to guide clinical practice and future research.

METHODS

Studies using spectral domain optical coherence tomography (SD OCT) and reporting macular parameters were included if they allowed the extraction of accuracy data for diagnosing manifest glaucoma, as confirmed with automated perimetry or a clinician's optic nerve head (ONH) assessment. Cross-sectional cohort studies and case-control studies were included. The QUADAS 2 tool was used to assess methodological quality. Only direct comparisons of macular versus RNFL parameters (i.e., in the same study) were conducted. Summary sensitivity and specificity of each macular or RNFL parameter were reported, and the relative diagnostic odds ratio (DOR) was calculated in hierarchical summary receiver operating characteristic (HSROC) models to compare them.

RESULTS

Thirty-four studies investigated macular parameters using RTVue OCT (Optovue Inc., Fremont, CA) (19 studies, 3094 subjects), Cirrus OCT (Carl Zeiss Meditec Inc., Dublin, CA) (14 studies, 2164 subjects), or 3D Topcon OCT (Topcon, Inc., Tokyo, Japan) (4 studies, 522 subjects). Thirty-two of these studies allowed comparisons between macular and RNFL parameters. Studies generally reported sensitivities at fixed specificities, more commonly 0.90 or 0.95, with sensitivities of most best-performing parameters between 0.65 and 0.75. For all OCT devices, compared with RNFL parameters, macular parameters were similarly or slightly less accurate for detecting glaucoma at the highest reported specificity, which was confirmed in analyses at the lowest specificity. Included studies suffered from limitations, especially the case-control study design, which is known to overestimate accuracy. However, this flaw is less relevant as a source of bias in direct comparisons conducted within studies.

CONCLUSIONS

With the use of OCT, RNFL parameters are still preferable to macular parameters for diagnosing manifest glaucoma, but the differences are small. Because of high heterogeneity, direct comparative or randomized studies of OCT devices or OCT parameters and diagnostic strategies are essential.

Optic nerve head and fibre layer imaging for diagnosing glaucoma

BACKGROUND

The diagnosis of glaucoma is traditionally based on the finding of optic nerve head (ONH) damage assessed subjectively by ophthalmoscopy or photography or by corresponding damage to the visual field assessed by automated perimetry, or both. Diagnostic assessments are usually required when ophthalmologists or primary eye care professionals find elevated intraocular pressure (IOP) or a suspect appearance of the ONH. Imaging tests such as confocal scanning laser ophthalmoscopy (HRT), optical coherence tomography (OCT) and scanning laser polarimetry (SLP, as used by the GDx instrument), provide an objective measure of the structural changes of retinal nerve fibre layer (RNFL) thickness and ONH parameters occurring in glaucoma.

OBJECTIVES

To determine the diagnostic accuracy of HRT, OCT and GDx for diagnosing manifest glaucoma by detecting ONH and RNFL damage.

SEARCH METHODS

We searched several databases for this review. The most recent searches were on 19 February 2015.

SELECTION CRITERIA

We included prospective and retrospective cohort studies and case-control studies that evaluated the accuracy of OCT, HRT or the GDx for diagnosing glaucoma. We excluded population-based screening studies, since we planned to consider studies on self-referred people or participants in whom a risk factor for glaucoma had already been identified in primary care, such as elevated IOP or a family history of glaucoma. We only considered recent commercial versions of the tests: spectral domain OCT, HRT III and GDx VCC or ECC.

DATA COLLECTION AND ANALYSIS

We adopted standard Cochrane methods. We fitted a hierarchical summary ROC (HSROC) model using the METADAS macro in SAS software. After studies were selected, we decided to use 2 x 2 data at 0.95 specificity or closer in meta-analyses, since this was the most commonly-reported level.

MAIN RESULTS

We included 106 studies in this review, which analysed 16,260 eyes (8353 cases, 7907 controls) in total. Forty studies (5574 participants) assessed GDx, 18 studies (3550 participants) HRT, and 63 (9390 participants) OCT, with 12 of these studies comparing two or three tests. Regarding study quality, a case-control design in 103 studies raised concerns as it can overestimate accuracy and reduce the applicability of the results to daily practice. Twenty-four studies were sponsored by the manufacturer, and in 15 the potential conflict of interest was unclear.Comparisons made within each test were more reliable than those between tests, as they were mostly based on direct comparisons within each study.The Nerve Fibre Indicator yielded the highest accuracy (estimate, 95% confidence interval (CI)) among GDx parameters (sensitivity: 0.67, 0.55 to 0.77; specificity: 0.94, 0.92 to 0.95). For HRT measures, the Vertical Cup/Disc (C/D) ratio (sensitivity: 0.72, 0.60 to 0.68; specificity: 0.94, 0.92 to 0.95) was no different from other parameters. With OCT, the accuracy of average RNFL retinal thickness was similar to the inferior sector (0.72, 0.65 to 0.77; specificity: 0.93, 0.92 to 0.95) and, in different studies, to the vertical C/D ratio.Comparing the parameters with the highest diagnostic odds ratio (DOR) for each device in a single HSROC model, the performance of GDx, HRT and OCT was remarkably similar. At a sensitivity of 0.70 and a high specificity close to 0.95 as in most of these studies, in 1000 people referred by primary eye care, of whom 200 have manifest glaucoma, such as in those who have already undergone some functional or anatomic testing by optometrists, the best measures of GDx, HRT and OCT would miss about 60 cases out of the 200 patients with glaucoma, and would incorrectly refer 50 out of 800 patients without glaucoma. If prevalence were 5%, e.g. such as in people referred only because of family history of glaucoma, the corresponding figures would be 15 patients missed out of 50 with manifest glaucoma, avoiding referral of about 890 out of 950 non-glaucomatous people.Heterogeneity investigations found that sensitivity estimate was higher for studies with more severe glaucoma, expressed as worse average mean deviation (MD): 0.79 (0.74 to 0.83) for MD < -6 db versus 0.64 (0.60 to 0.69) for MD ≥ -6 db, at a similar summary specificity (0.93, 95% CI 0.92 to 0.94 and, respectively, 0.94; 95% CI 0.93 to 0.95; P < 0.0001 for the difference in relative DOR).

AUTHORS' CONCLUSIONS

The accuracy of imaging tests for detecting manifest glaucoma was variable across studies, but overall similar for different devices. Accuracy may have been overestimated due to the case-control design, which is a serious limitation of the current evidence base.We recommend that further diagnostic accuracy studies are carried out on patients selected consecutively at a defined step of the clinical pathway, providing a description of risk factors leading to referral and bearing in mind the consequences of false positives and false negatives in the setting in which the diagnostic question is made. Future research should report accuracy for each threshold of these continuous measures, or publish raw data.

Reproducibility of circumpapillary retinal nerve fiber layer measurements using handheld optical coherence tomography in sedated children

PURPOSE

To determine the intra- and intervisit reproducibility of circumpapillary retinal nerve fiber layer (RNFL) measures using handheld optical coherence tomography (OCT) in sedated children.

DESIGN

Prospective cross-sectional and longitudinal study.

METHODS

Children undergoing sedation for a clinically indicated magnetic resonance imaging for an optic pathway glioma and/or neurofibromatosis type 1 (NF1) had multiple 6 × 6 mm volumes (isotropic 300 × 300 or nonisotropic 1000 × 100 samplings) acquired over the optic nerve. Children with 2 handheld OCT sessions within 6 months were included in the intervisit cohort. The intra- and intervisit coefficient of variation (CV) and intraclass correlation coefficient (ICC) were calculated for the average and anatomic quadrant circumpapillary RNFL thickness.

RESULTS

Fifty-nine subjects (mean age 5.1 years, range 0.8-13.0 years) comprised the intravisit cohort and 29 subjects (mean age 5.7 years, range 1.8-12.7 years) contributed to the intervisit cohort. Forty-nine subjects had an optic pathway glioma and 10 subjects had NF1 without an optic pathway glioma. The CV was comparable regardless of imaging with an isotropic and nonisotropic volume in both the intra- and intervisit cohorts. The average circumpapillary RNFL demonstrated the lowest CV and highest ICC compared to the quadrants. For the intervisit cohort, the average ICC was typically higher while the CV was typically lower, but not statistically different compared to the other quadrants.

DISCUSSION

Circumpapillary RNFL measures acquired with handheld OCT during sedation demonstrate good intra- and intervisit reproducibility. Handheld OCT has the potential to monitor progressive optic neuropathies in young children who have difficulty cooperating with traditional OCT devices.

Discriminating between glaucoma and normal eyes using optical coherence tomography and the 'Random Forests' classifier

PURPOSE

To diagnose glaucoma based on spectral domain optical coherence tomography (SD-OCT) measurements using the 'Random Forests' method.

METHODS

SD-OCT was conducted in 126 eyes of 126 open angle glaucoma (OAG) patients and 84 eyes of 84 normal subjects. The Random Forests method was then applied to discriminate between glaucoma and normal eyes using 151 OCT parameters including thickness measurements of circumpapillary retinal nerve fiber layer (cpRNFL), the macular RNFL (mRNFL) and the ganglion cell layer-inner plexiform layer combined (GCIPL). The area under the receiver operating characteristic curve (AROC) was calculated using the Random Forests method adopting leave-one-out cross validation. For comparison, AROCs were calculated based on each one of the 151 OCT parameters.

RESULTS

The AROC obtained with the Random Forests method was 98.5% [95% Confidence interval (CI): 97.1-99.9%], which was significantly larger than the AROCs derived from any single OCT parameter (maxima were: 92.8 [CI: 89.4-96.2] %, 94.3 [CI: 91.1-97.6] % and 91.8 [CI: 88.2-95.4] % for cpRNFL-, mRNFL- and GCIPL-related parameters, respectively; P<0.05, DeLong's method with Holm's correction for multiple comparisons). The partial AROC above specificity of 80%, for the Random Forests method was equal to 18.5 [CI: 16.8-19.6] %, which was also significantly larger than the AROCs of any single OCT parameter (P<0.05, Bootstrap method with Holm's correction for multiple comparisons).

CONCLUSIONS

The Random Forests method, analyzing multiple SD-OCT parameters concurrently, significantly improves the diagnosis of glaucoma compared with using any single SD-OCT measurement.