Combining functional and structural tests improves the diagnostic accuracy of relevance vector machine classifiers

Wide-Field Optical Coherence Tomography Imaging Improves Rate of Change Detection in Progressing Glaucomatous Eyes Compared With Standard-Field Imaging

Purpose

To compare rates of retinal nerve fiber layer change over time in healthy, eyes with nonprogressing glaucoma and eyes with progressing glaucoma using single wide-field (SWF) and optic nerve head (ONH) cube scan optical coherence tomography (OCT) images.

Methods

Forty-five eyes of 25 healthy individuals and 263 eyes of 161 glaucoma patients from the Diagnostic Innovations in Glaucoma Study were included. All eyes underwent 24-2 visual field testing and OCT (Spectralis SD-OCT) ONH and macular imaging. SWF images (up to 43° × 28°) were created by stitching together ONH cube scans centered on the optic disc and macular cube scans centered on the fovea. Visual field progression was defined as guided progression analysis likely progression and/or a significant (P < 0.01) mean deviation slope of less than -1.0 dB/year. Mixed effects models were used to compare rates of change. Highly myopic eyes were included.

Results

Thirty glaucomatous eyes were classified as progressing. In eyes with glaucoma, mean global rate of change was -1.22 µm/year (P < 0.001) using SWF images and -0.83 µm/year (P = 0.003) using ONH cube scans. Rate of change was significantly greater in eyes with progressing glaucoma compared with eyes with nonprogressing glaucoma (-1.51 µm/year vs. -1.24 µm/year; P = 0.002) using SWF images and was similar using ONH cube scans (P = 0.27).

Conclusions

In this cohort that includes eyes with and without high axial myopia, the mean rate of retinal nerve fiber layer thinning measured using SWF images was faster in eyes with progressing glaucoma than in eyes with nonprogressing glaucoma. Wide-field OCT images including the ONH and macula can be effective for monitoring glaucomatous progression in patients with and without high myopia.

Multimodal Deep Learning Classifier for Primary Open Angle Glaucoma Diagnosis Using Wide-Field Optic Nerve Head Cube Scans in Eyes With and Without High Myopia

PRCIS

An optical coherence tomography (OCT)-based multimodal deep learning (DL) classification model, including texture information, is introduced that outperforms single-modal models and multimodal models without texture information for glaucoma diagnosis in eyes with and without high myopia.

BACKGROUND/AIMS

To evaluate the diagnostic accuracy of a multimodal DL classifier using wide OCT optic nerve head cube scans in eyes with and without axial high myopia.

MATERIALS AND METHODS

Three hundred seventy-one primary open angle glaucoma (POAG) eyes and 86 healthy eyes, all without axial high myopia [axial length (AL) ≤ 26 mm] and 92 POAG eyes and 44 healthy eyes, all with axial high myopia (AL > 26 mm) were included. The multimodal DL classifier combined features of 3 individual VGG-16 models: (1) texture-based en face image, (2) retinal nerve fiber layer (RNFL) thickness map image, and (3) confocal scanning laser ophthalmoscope (cSLO) image. Age, AL, and disc area adjusted area under the receiver operating curves were used to compare model accuracy.

RESULTS

Adjusted area under the receiver operating curve for the multimodal DL model was 0.91 (95% CI = 0.87, 0.95). This value was significantly higher than the values of individual models [0.83 (0.79, 0.86) for texture-based en face image; 0.84 (0.81, 0.87) for RNFL thickness map; and 0.68 (0.61, 0.74) for cSLO image; all P ≤ 0.05]. Using only highly myopic eyes, the multimodal DL model showed significantly higher diagnostic accuracy [0.89 (0.86, 0.92)] compared with texture en face image [0.83 (0.78, 0.85)], RNFL [0.85 (0.81, 0.86)] and cSLO image models [0.69 (0.63, 0.76)] (all P ≤ 0.05).

CONCLUSIONS

Combining OCT-based RNFL thickness maps with texture-based en face images showed a better ability to discriminate between healthy and POAG than thickness maps alone, particularly in high axial myopic eyes.

[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.

Deep Relation Transformer for Diagnosing Glaucoma With Optical Coherence Tomography and Visual Field Function

Glaucoma is the leading reason for irreversible blindness. Early detection and timely treatment of glaucoma are essential for preventing visual field loss or even blindness. In clinical practice, Optical Coherence Tomography (OCT) and Visual Field (VF) exams are two widely-used and complementary techniques for diagnosing glaucoma. OCT provides quantitative measurements of the optic nerve head (ONH) structure, while VF test is the functional assessment of peripheral vision. In this paper, we propose a Deep Relation Transformer (DRT) to perform glaucoma diagnosis with OCT and VF information combined. A novel deep reasoning mechanism is proposed to explore implicit pairwise relations between OCT and VF information in global and regional manners. With the pairwise relations, a carefully-designed deep transformer mechanism is developed to enhance the representation with complementary information for each modal. Based on reasoning and transformer mechanisms, three successive modules are designed to extract and collect valuable information for glaucoma diagnosis, the global relation module, the guided regional relation module, and the interaction transformer module, namely. Moreover, we build a large dataset, namely ZOC-OCT&VF dataset, which includes 1395 OCT-VF pairs for developing and evaluating our DRT. We conduct extensive experiments to validate the effectiveness of the proposed method. Experimental results show that our method achieves 88.3% accuracy and outperforms the existing single-modal approaches with a large margin. The codes and dataset will be publicly available in the future.

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

PURPOSE

To test the hypothesis that visual field (VF) progression can be predicted from baseline and longitudinal optical coherence tomography (OCT) structural measurements.

DESIGN

Prospective cohort study.

METHODS

A total of 104 eyes (104 patients) with ≥3 years of follow-up and ≥5 VF examinations were enrolled. We defined VF progression based on pointwise linear regression on 24-2 VF (≥3 locations with slope less than or equal to -1.0 dB/year and P < .01). We used elastic net logistic regression (ENR) and machine learning to predict VF progression with demographics, baseline circumpapillary retinal nerve fiber layer (RNFL), macular ganglion cell/inner plexiform layer (GCIPL) thickness, and RNFL and GCIPL change rates at central 24 superpixels and 3 eccentricities, 3.4°, 5.5°, and 6.8°, from fovea and hemimaculas. Areas-under-ROC curves (AUC) were used to compare models.

RESULTS

Average ± SD follow-up and VF examinations were 4.5 ± 0.9 years and 8.7 ± 1.6, respectively. VF progression was detected in 23 eyes (22%). ENR selected rates of change of superotemporal RNFL sector and GCIPL change rates in 5 central superpixels and at 3.4° and 5.6° eccentricities as the best predictor subset (AUC = 0.79 ± 0.12). Best machine learning predictors consisted of baseline superior hemimacular GCIPL thickness and GCIPL change rates at 3.4° eccentricity and 3 central superpixels (AUC = 0.81 ± 0.10). Models using GCIPL-only structural variables performed better than RNFL-only models.

CONCLUSIONS

VF progression can be predicted with clinically relevant accuracy from baseline and longitudinal structural data. Further refinement of proposed models would assist clinicians with timely prediction of functional glaucoma progression and clinical decision making.

Gradient-Boosting Classifiers Combining Vessel Density and Tissue Thickness Measurements for Classifying Early to Moderate Glaucoma

PURPOSE

To compare gradient-boosting classifier (GBC) analysis of optical coherence tomography angiography (OCTA)-measured vessel density (VD) and OCT-measured tissue thickness to standard OCTA VD and OCT thickness parameters for classifying healthy eyes and eyes with early to moderate glaucoma.

DESIGN

Comparison of diagnostic tools.

METHODS

A total of 180 healthy eyes and 193 glaucomatous eyes with OCTA and OCT imaging of the macula and optic nerve head (ONH) were studied. Four GBCs were evaluated that combined 1) all macula VD and thickness measurements (Macula GBC), 2) all ONH VD and thickness measurements (ONH GBC), 3) all VD measurements from the macula and ONH (vessel density GBC), and 4) all thickness measurements from the macula and ONH (thickness GBC). ROC curve (AUROC) analyses compared the diagnostic accuracy of GBCs to that of standard instrument-provided parameters. A fifth GBC that combined all parameters (full GBC) also was investigated.

RESULTS

GBCs had better diagnostic accuracy than standard OCTA and OCT parameters with AUROCs ranging from 0.90 to 0.93 and 0.64 to 0.91, respectively. The full GBC (AUROC = 0.93) performed significantly better than the ONH GBC (AUROC = 0.91; P = .036) and the vessel density GBC (AUROC = 0.90; P = .010). All other GBCs performed similarly. The mean relative influence of each parameter included in the full GBC identified a combination of macular thickness and ONH VD measurements as the greatest contributors.

CONCLUSIONS

GBCs that combine OCTA and OCT macula and ONH measurements can improve diagnostic accuracy for glaucoma detection compared to most but not all instrument provided parameters.

A Review of Deep Learning for Screening, Diagnosis, and Detection of Glaucoma Progression

Because of recent advances in computing technology and the availability of large datasets, deep learning has risen to the forefront of artificial intelligence, with performances that often equal, or sometimes even exceed, those of human subjects on a variety of tasks, especially those related to image classification and pattern recognition. As one of the medical fields that is highly dependent on ancillary imaging tests, ophthalmology has been in a prime position to witness the application of deep learning algorithms that can help analyze the vast amount of data coming from those tests. In particular, glaucoma stands as one of the conditions where application of deep learning algorithms could potentially lead to better use of the vast amount of information coming from structural and functional tests evaluating the optic nerve and macula. The purpose of this article is to critically review recent applications of deep learning models in glaucoma, discussing their advantages but also focusing on the challenges inherent to the development of such models for screening, diagnosis and detection of progression. After a brief general overview of deep learning and how it compares to traditional machine learning classifiers, we discuss issues related to the training and validation of deep learning models and how they specifically apply to glaucoma. We then discuss specific scenarios where deep learning has been proposed for use in glaucoma, such as screening with fundus photography, and diagnosis and detection of glaucoma progression with optical coherence tomography and standard automated perimetry.

Translational Relevance

Deep learning algorithms have the potential to significantly improve diagnostic capabilities in glaucoma, but their application in clinical practice requires careful validation, with consideration of the target population, the reference standards used to build the models, and potential sources of bias.

Glaucoma management in the era of artificial intelligence

Glaucoma is a result of irreversible damage to the retinal ganglion cells. While an early intervention could minimise the risk of vision loss in glaucoma, its asymptomatic nature makes it difficult to diagnose until a late stage. The diagnosis of glaucoma is a complicated and expensive effort that is heavily dependent on the experience and expertise of a clinician. The application of artificial intelligence (AI) algorithms in ophthalmology has improved our understanding of many retinal, macular, choroidal and corneal pathologies. With the advent of deep learning, a number of tools for the classification, segmentation and enhancement of ocular images have been developed. Over the years, several AI techniques have been proposed to help detect glaucoma by analysis of functional and/or structural evaluations of the eye. Moreover, the use of AI has also been explored to improve the reliability of ascribing disease prognosis. This review summarises the role of AI in the diagnosis and prognosis of glaucoma, discusses the advantages and challenges of using AI systems in clinics and predicts likely areas of future progress.

Machine learning models based on the dimensionality reduction of standard automated perimetry data for glaucoma diagnosis

INTRODUCTION

Visual field testing via standard automated perimetry (SAP) is a commonly used glaucoma diagnosis method. Applying machine learning techniques to the visual field test results, a valid clinical diagnosis of glaucoma solely based on the SAP data is provided. In order to reflect structural-functional patterns of glaucoma on the automated diagnostic models, we propose composite variables derived from anatomically grouped visual field clusters to improve the prediction performance. A set of machine learning-based diagnostic models are designed that implement different input data manipulation, dimensionality reduction, and classification methods.

METHODS

Visual field testing data of 375 healthy and 257 glaucomatous eyes were used to build the diagnostic models. Three kinds of composite variables derived from the Garway-Heath map and the glaucoma hemifield test (GHT) sector map were included in the input variables in addition to the 52 SAP visual filed locations. Dimensionality reduction was conducted to select important variables so as to alleviate high-dimensionality problems. To validate the proposed methods, we applied four classifiers-linear discriminant analysis, naïve Bayes classifier, support vector machines, and artificial neural networks-and four dimensionality reduction methods-Pearson correlation coefficient-based variable selection, Markov blanket variable selection, the minimum redundancy maximum relevance algorithm, and principal component analysis- and compared their classification performances.

RESULTS

For all tested combinations, the classification performance improved when the proposed composite variables and dimensionality reduction techniques were implemented. The combination of total deviation values, the GHT sector map, support vector machines, and Markov blanket variable selection obtains the best performance: an area under the receiver operating characteristic curve (AUC) of 0.912.

CONCLUSION

A glaucoma diagnosis model giving an AUC of 0.912 was constructed by applying machine learning techniques to SAP data. The results show that dimensionality reduction not only reduces dimensions of the input space but also enhances the classification performance. The variable selection results show that the proposed composite variables from visual field clustering play a key role in the diagnosis model.

Automated algorithms combining structure and function outperform general ophthalmologists in diagnosing glaucoma

PURPOSE

To test the ability of machine learning classifiers (MLCs) using optical coherence tomography (OCT) and standard automated perimetry (SAP) parameters to discriminate between healthy and glaucomatous individuals, and to compare it to the diagnostic ability of the combined structure-function index (CSFI), general ophthalmologists and glaucoma specialists.

DESIGN

Cross-sectional prospective study.

METHODS

Fifty eight eyes of 58 patients with early to moderate glaucoma (median value of the mean deviation = -3.44 dB; interquartile range, -6.0 to -2.4 dB) and 66 eyes of 66 healthy individuals underwent OCT and SAP tests. The diagnostic accuracy (area under the ROC curve-AUC) of 10 MLCs was compared to those obtained with the CSFI, 3 general ophthalmologists and 3 glaucoma specialists exposed to the same OCT and SAP data.

RESULTS

The AUCs obtained with MLCs ranged from 0.805 (Classification Tree) to 0.931 (Radial Basis Function Network, RBF). The sensitivity at 90% specificity ranged from 51.6% (Classification Tree) to 82.8% (Bagging, Multilayer Perceptron and Support Vector Machine Gaussian). The CSFI had a sensitivity of 79.3% at 90% specificity, and the highest AUC (0.948). General ophthalmologists and glaucoma specialists' grading had sensitivities of 66.2% and 83.8% at 90% specificity, and AUCs of 0.879 and 0.921, respectively. RBF (the best MLC), the CSFI, and glaucoma specialists showed significantly higher AUCs than that obtained by general ophthalmologists (P<0.05). However, there were no significant differences between the AUCs obtained by RBF, the CSFI, and glaucoma specialists (P>0.25).

CONCLUSION

Our findings suggest that both MLCs and the CSFI can be helpful in clinical practice and effectively improve glaucoma diagnosis in the primary eye care setting, when there is no glaucoma specialist available.

Diagnostic ability of Humphrey perimetry, Octopus perimetry, and optical coherence tomography for glaucomatous optic neuropathy

PurposeTo evaluate and compare the diagnostic accuracy of the Humphrey Field Analyzer (HFA), Octopus perimetry, and Cirrus OCT for glaucomatous optic neuropathy.MethodsEighty-eight healthy individuals and 150 open-angle glaucoma patients were consecutive and prospectively selected. Eligibility criteria for the glaucoma group were intraocular pressure ≥21 mm Hg and glaucomatous optic nerve head morphology. All subjects underwent a reliable standard automated perimetry with the HFA and Octopus perimeter, and were imaged with the Cirrus OCT. Receiver-operating characteristic (ROC) curves were plotted for the threshold values and main indices of the HFA and Octopus, the peripapillary retinal nerve fiber layer thicknesses, and the optic nerve head parameters. Sensitivities at 85 and 95% fixed-specificities were also calculated. The best areas under the ROC curves (AUCs) were compared using the DeLong method.ResultsIn the glaucoma group, mean deviation (MD) was -5.42±4.6 dB for HFA and 3.90±3.6 dB for Octopus. The MD of the HFA (0.966; P<0.001), mean sensitivity of the Octopus (0.941; P<0.001), and average cup-to-disc (C/D) ratio measured by the Cirrus OCT (0.958; P<0.001) had the largest AUCs for each test studied. There were no significant differences among them. Sensitivities at 95% fixed-specificity were 82% for pattern standard deviation of the HFA, 81.3% for average C/D ratio of OCT, and 80% for the MD of the Octopus.ConclusionsHFA, Octopus, and Cirrus OCT demonstrated similar diagnostic accuracies for glaucomatous optic neuropathy. Visual field and OCT provide supplementary information and thus these tests are not interchangeable.

Machine Learning Techniques in Clinical Vision Sciences

This review presents and discusses the contribution of machine learning techniques for diagnosis and disease monitoring in the context of clinical vision science. Many ocular diseases leading to blindness can be halted or delayed when detected and treated at its earliest stages. With the recent developments in diagnostic devices, imaging and genomics, new sources of data for early disease detection and patients' management are now available. Machine learning techniques emerged in the biomedical sciences as clinical decision-support techniques to improve sensitivity and specificity of disease detection and monitoring, increasing objectively the clinical decision-making process. This manuscript presents a review in multimodal ocular disease diagnosis and monitoring based on machine learning approaches. In the first section, the technical issues related to the different machine learning approaches will be present. Machine learning techniques are used to automatically recognize complex patterns in a given dataset. These techniques allows creating homogeneous groups (unsupervised learning), or creating a classifier predicting group membership of new cases (supervised learning), when a group label is available for each case. To ensure a good performance of the machine learning techniques in a given dataset, all possible sources of bias should be removed or minimized. For that, the representativeness of the input dataset for the true population should be confirmed, the noise should be removed, the missing data should be treated and the data dimensionally (i.e., the number of parameters/features and the number of cases in the dataset) should be adjusted. The application of machine learning techniques in ocular disease diagnosis and monitoring will be presented and discussed in the second section of this manuscript. To show the clinical benefits of machine learning in clinical vision sciences, several examples will be presented in glaucoma, age-related macular degeneration, and diabetic retinopathy, these ocular pathologies being the major causes of irreversible visual impairment.

Methodology and reporting of diagnostic accuracy studies of automated perimetry in glaucoma: evaluation using a standardised approach

PURPOSE

To evaluate methodological and reporting quality of diagnostic accuracy studies of perimetry in glaucoma and to determine whether there had been any improvement since the publication of the Standards for Reporting of Diagnostic Accuracy (STARD) guidelines.

METHODS

A systematic review of English language articles published between 1993 and 2013 reporting the diagnostic accuracy of perimetry in glaucoma. Articles were appraised for methodological quality using the 14-item Quality assessment tool for diagnostic accuracy studies (QUADAS) and evaluated for quality of reporting by applying the STARD checklist.

RESULTS

Fifty-eight articles were appraised. Overall methodological quality of these studies was moderate with a median number of QUADAS items rated as 'yes' equal to nine (out of a maximum of 14) (IQR 7-10). The studies were often poorly reported; median score of STARD items fully reported was 11 out of 25 (IQR 10-14). A comparison of the studies published in 10-year periods before and after the publication of the STARD checklist in 2003 found quality of reporting had not substantially improved.

CONCLUSIONS

Methodological and reporting quality of diagnostic accuracy studies of perimetry is sub-optimal and appears not to have improved substantially following the development of the STARD reporting guidance. This observation is consistent with previous studies in ophthalmology and in other medical specialities.

Diagnostic ability of macular ganglion cell inner plexiform layer measurements in glaucoma using swept source and spectral domain optical coherence tomography

Purpose

To evaluate the diagnostic ability of macular ganglion cell and inner plexiform layer measurements in glaucoma, obtained using swept source (SS) and spectral domain (SD) optical coherence tomography (OCT) and to compare to circumpapillary retinal nerve fiber layer (cpRNFL) thickness measurements.

Methods

The study included 106 glaucomatous eyes of 80 subjects and 41 eyes of 22 healthy subjects from the Diagnostic Innovations in Glaucoma Study. Macular ganglion cell and inner plexiform layer (mGCIPL), macular ganglion cell complex (mGCC) and cpRNFL thickness were assessed using SS-OCT and SD-OCT, and area under the receiver operating characteristic curves (AUCs) were calculated to determine ability to differentiate glaucomatous and healthy eyes and between early glaucomatous and healthy eyes.

Results

Mean (± standard deviation) mGCIPL and mGCC thickness were thinner in both healthy and glaucomatous eyes using SS-OCT compared to using SD-OCT. Fixed and proportional biases were detected between SS-OCT and SD-OCT measures. Diagnostic accuracy (AUCs) for differentiating between healthy and glaucomatous eyes for average and sectoral mGCIPL was similar in SS-OCT (0.65 to 0.81) and SD-OCT (0.63 to 0.83). AUCs for average cpRNFL acquired using SS-OCT and SD-OCT tended to be higher (0.83 and 0.85, respectively) than for average mGCC (0.82 and 0.78, respectively), and mGCIPL (0.73 and 0.75, respectively) but these differences did not consistently reach statistical significance. Minimum SD-OCT mGCIPL and mGCC thickness (unavailable in SS-OCT) had the highest AUC (0.86) among macular measurements.

Conclusion

Assessment of mGCIPL thickness using SS-OCT or SD-OCT is useful for detecting glaucomatous damage, but measurements are not interchangeable for patient management decisions. Diagnostic accuracies of mGCIPL and mGCC from both SS-OCT and SD-OCT were similar to that of cpRNFL for glaucoma detection.

Diagnostic ability of retinal nerve fiber layer imaging by swept-source optical coherence tomography in glaucoma

PURPOSE

To evaluate the diagnostic accuracies of swept-source optical coherence tomography (OCT) wide-angle and peripapillary retinal nerve fiber layer (RNFL) thickness measurements for glaucoma detection.

DESIGN

Cross-sectional case-control study.

METHODS

In this study we enrolled 144 glaucomatous eyes of 106 subjects and 66 eyes of 42 healthy subjects from the Diagnostic Innovations in Glaucoma Study. Glaucoma was defined by the presence of repeatable abnormal standard automated perimetry results and/or progressive glaucomatous optic disc change on masked grading of stereophotographs. Wide-angle and peripapillary RNFL thicknesses were assessed using swept-source OCT. Peripapillary RNFL thickness was also evaluated using spectral-domain OCT. Areas under the receiver operating characteristic (ROC) curves were calculated to evaluate the ability of the different swept-source OCT and spectral-domain OCT parameters to discriminate between glaucomatous and healthy eyes.

RESULTS

Mean (± standard deviation) average spectral-domain OCT wide-angle RNFL thicknesses were 50.5 ± 5.8 μm and 35.0 ± 9.6 μm in healthy and glaucomatous eyes, respectively (P < 0.001). Corresponding values for swept-source OCT peripapillary RNFL thicknesses were 103.5 ± 12.3 μm and 72.9 ± 16.5 μm, respectively (P < 0.001). Areas under the ROC curves of swept-source OCT wide-angle and peripapillary RNFL thickness were 0.88 and 0.89, respectively. Swept-source OCT performed similar to average peripapillary RNFL thickness obtained by spectral-domain OCT (area under the ROC curve of 0.90).

CONCLUSION

Swept-source OCT wide-angle and peripapillary RNFL thickness measurements performed well for detecting glaucomatous damage. The diagnostic accuracies of the swept-source OCT and spectral-domain OCT RNFL imaging protocols evaluated in this study were similar.

Glaucoma progression detection using structural retinal nerve fiber layer measurements and functional visual field points

Machine learning classifiers were employed to detect glaucomatous progression using longitudinal series of structural data extracted from retinal nerve fiber layer thickness measurements and visual functional data recorded from standard automated perimetry tests. Using the collected data, a longitudinal feature vector was created for each patient's eye by computing the norm 1 difference vector of the data at the baseline and at each follow-up visit. The longitudinal features from each patient's eye were then fed to the machine learning classifier to classify each eye as stable or progressed over time. This study was performed using several machine learning classifiers including Bayesian, Lazy, Meta, and Tree, composing different families. Combinations of structural and functional features were selected and ranked to determine the relative effectiveness of each feature. Finally, the outcomes of the classifiers were assessed by several performance metrics and the effectiveness of structural and functional features were analyzed.

On improving the use of OCT imaging for detecting glaucomatous damage

AIMS

To describe two approaches for improving the detection of glaucomatous damage seen with optical coherence tomography (OCT).

METHODS

The two approaches described were: one, a visual analysis of the high-quality OCT circle scans and two, a comparison of local visual field sensitivity loss to local OCT retinal ganglion cell plus inner plexiform (RGC+) and retinal nerve fibre layer (RNFL) thinning. OCT images were obtained from glaucoma patients and suspects using a spectral domain OCT machine and commercially available scanning protocols. A high-quality peripapillary circle scan (average of 50), a three-dimensional (3D) scan of the optic disc, and a 3D scan of the macula were obtained. RGC+ and RNFL thickness and probability plots were generated from the 3D scans.

RESULTS

A close visual analysis of a high-quality circle scan can help avoid both false positive and false negative errors. Similarly, to avoid these errors, the location of abnormal visual field points should be compared to regions of abnormal RGC+ and RNFL thickness.

CONCLUSIONS

To improve the sensitivity and specificity of OCT imaging, high-quality images should be visually scrutinised and topographical information from visual fields and OCT scans combined.

Glaucomatous patterns in Frequency Doubling Technology (FDT) perimetry data identified by unsupervised machine learning classifiers

Purpose

The variational Bayesian independent component analysis-mixture model (VIM), an unsupervised machine-learning classifier, was used to automatically separate Matrix Frequency Doubling Technology (FDT) perimetry data into clusters of healthy and glaucomatous eyes, and to identify axes representing statistically independent patterns of defect in the glaucoma clusters.

Methods

FDT measurements were obtained from 1,190 eyes with normal FDT results and 786 eyes with abnormal FDT results from the UCSD-based Diagnostic Innovations in Glaucoma Study (DIGS) and African Descent and Glaucoma Evaluation Study (ADAGES). For all eyes, VIM input was 52 threshold test points from the 24-2 test pattern, plus age.

Results

FDT mean deviation was −1.00 dB (S.D. = 2.80 dB) and −5.57 dB (S.D. = 5.09 dB) in FDT-normal eyes and FDT-abnormal eyes, respectively (p<0.001). VIM identified meaningful clusters of FDT data and positioned a set of statistically independent axes through the mean of each cluster. The optimal VIM model separated the FDT fields into 3 clusters. Cluster N contained primarily normal fields (1109/1190, specificity 93.1%) and clusters G₁ and G₂ combined, contained primarily abnormal fields (651/786, sensitivity 82.8%). For clusters G₁ and G₂ the optimal number of axes were 2 and 5, respectively. Patterns automatically generated along axes within the glaucoma clusters were similar to those known to be indicative of glaucoma. Fields located farther from the normal mean on each glaucoma axis showed increasing field defect severity.

Conclusions

VIM successfully separated FDT fields from healthy and glaucoma eyes without a priori information about class membership, and identified familiar glaucomatous patterns of loss.

Improving glaucoma detection using spatially correspondent clusters of damage and by combining standard automated perimetry and optical coherence tomography

PURPOSE

To improve the detection of glaucoma, techniques for assessing local patterns of damage and for combining structure and function were developed.

METHODS

Standard automated perimetry (SAP) and frequency-domain optical coherence tomography (fdOCT) data, consisting of macular retinal ganglion cell plus inner plexiform layer (mRGCPL) as well as macular and optic disc retinal nerve fiber layer (mRNFL and dRNFL) thicknesses, were collected from 52 eyes of 52 healthy controls and 156 eyes of 96 glaucoma suspects and patients. In addition to generating simple global metrics, SAP and fdOCT data were searched for contiguous clusters of abnormal points and converted to a continuous metric (pcc). The pcc metric, along with simpler methods, was used to combine the information from the SAP and fdOCT. The performance of different methods was assessed using the area under receiver operator characteristic curves (AROC scores).

RESULTS

The pcc metric performed better than simple global measures for both the fdOCT and SAP. The best combined structure-function metric (mRGCPL&SAP pcc, AROC = 0.868 ± 0.032) was better (statistically significant) than the best metrics for independent measures of structure and function. When SAP was used as part of the inclusion and exclusion criteria, AROC scores increased for all metrics, including the best combined structure-function metric (AROC = 0.975 ± 0.014).

CONCLUSIONS

A combined structure-function metric improved the detection of glaucomatous eyes. Overall, the primary sources of value-added for glaucoma detection stem from the continuous cluster search (the pcc), the mRGCPL data, and the combination of structure and function.

Predicting glaucomatous progression in glaucoma suspect eyes using relevance vector machine classifiers for combined structural and functional measurements

PURPOSE

The goal of this study was to determine if glaucomatous progression in suspect eyes can be predicted from baseline confocal scanning laser ophthalmoscope (CSLO) and standard automated perimetry (SAP) measurements analyzed with relevance vector machine (RVM) classifiers.

METHODS

Two hundred sixty-four eyes of 193 participants were included. All eyes had normal SAP results at baseline with five or more SAP tests over time. Eyes were labeled progressed (n = 47) or stable (n = 217) during follow-up based on SAP Guided Progression Analysis or serial stereophotograph assessment. Baseline CSLO-measured topographic parameters (n = 117) and baseline total deviation values from the 24-2 SAP test-grid (n = 52) were selected from each eye. Ten-fold cross-validation was used to train and test RVMs using the CSLO and SAP features. Receiver operating characteristic (ROC) curve areas were calculated using full and optimized feature sets. ROC curve results from RVM analyses of CSLO, SAP, and CSLO and SAP combined were compared to CSLO and SAP global indices (Glaucoma Probability Score, mean deviation and pattern standard deviation).

RESULTS

The areas under the ROC curves (AUROCs) for RVMs trained on optimized feature sets of CSLO parameters, SAP parameters, and CSLO and SAP parameters combined were 0.640, 0.762, and 0.805, respectively. AUROCs for CSLO Glaucoma Probability Score, SAP mean deviation (MD), and SAP pattern standard deviation (PSD) were 0.517, 0.513, and 0.620, respectively. No CSLO or SAP global indices discriminated between baseline measurements from progressed and stable eyes better than chance.

CONCLUSIONS

In our sample, RVM analyses of baseline CSLO and SAP measurements could identify eyes that showed future glaucomatous progression with a higher accuracy than the CSLO and SAP global indices. (ClinicalTrials.gov numbers, NCT00221897, NCT00221923.).

Integration and fusion of standard automated perimetry and optical coherence tomography data for improved automated glaucoma diagnostics

Background

The performance of glaucoma diagnostic systems could be conceivably improved by the integration of functional and structural test measurements that provide relevant and complementary information for reaching a diagnosis. The purpose of this study was to investigate the performance of data fusion methods and techniques for simple combination of Standard Automated Perimetry (SAP) and Optical Coherence Tomography (OCT) data for the diagnosis of glaucoma using Artificial Neural Networks (ANNs).

Methods

Humphrey 24-2 SITA standard SAP and StratusOCT tests were prospectively collected from a randomly selected population of 125 healthy persons and 135 patients with glaucomatous optic nerve heads and used as input for the ANNs. We tested commercially available standard parameters as well as novel ones (fused OCT and SAP data) that exploit the spatial relationship between visual field areas and sectors of the OCT peripapillary scan circle. We evaluated the performance of these SAP and OCT derived parameters both separately and in combination.

Results

The diagnostic accuracy from a combination of fused SAP and OCT data (95.39%) was higher than that of the best conventional parameters of either instrument, i.e. SAP Glaucoma Hemifield Test (p < 0.001) and OCT Retinal Nerve Fiber Layer Thickness ≥ 1 quadrant (p = 0.031). Fused OCT and combined fused OCT and SAP data provided similar Area under the Receiver Operating Characteristic Curve (AROC) values of 0.978 that were significantly larger (p = 0.047) compared to ANNs using SAP parameters alone (AROC = 0.945). On the other hand, ANNs based on the OCT parameters (AROC = 0.970) did not perform significantly worse than the ANNs based on the fused or combined forms of input data. The use of fused input increased the number of tests that were correctly classified by both SAP and OCT based ANNs.

Conclusions

Compared to the use of SAP parameters, input from the combination of fused OCT and SAP parameters, and from fused OCT data, significantly increased the performance of ANNs. Integrating parameters by including a priori relevant information through data fusion may improve ANN classification accuracy compared to currently available methods.