Deep Neural Network for Scleral Spur Detection in Anterior Segment OCT Images: The Chinese American Eye Study

Diagnostic criteria of anterior segment swept-source optical coherence tomography to detect gonioscopic angle closure

AIMS

To compare the diagnostic performance of 360° anterior segment optical coherence tomography assessment by applying normative percentile cut-offs versus iris trabecular contact (ITC) for detecting gonioscopic angle closure.

METHODS

In this multicentre study, 394 healthy individuals were included in the normative dataset to derive the age-specific and angle location-specific normative percentiles of angle open distance (AOD500) and trabecular iris space area (TISA500) which were measured every 10° for 360°. 119 healthy participants and 170 patients with angle closure by gonioscopy were included in the test dataset to investigate the diagnostic performance of three sets of criteria for detection of gonioscopic angle closure: (1) the 10th and (2) the 5th percentiles of AOD500/TISA500, and (3) ITC (ie, AOD500/TISA500=0 mm/mm2). The number of angle locations with angle closure defined by each set of the criteria for each eye was used to generate the receiver operating characteristic (ROC) curve for the discrimination between gonioscopic angle closure and open angle.

RESULTS

Of the three sets of diagnostic criteria examined, the area under the ROC curve was greatest for the 10th percentile of AOD500 (0.933), whereas the ITC criterion AOD500=0 mm showed the smallest area under the ROC (0.852) and the difference was statistically significant with or without adjusting for age and axial length (p<0.001). The criterion ≥90° of AOD500 below the 10th percentile attained the best sensitivity 87.6% and specificity 84.9% combination for detecting gonioscopic angle closure.

CONCLUSIONS

Applying the normative percentiles of angle measurements yielded a higher diagnostic performance than ITC for detecting angle closure on gonioscopy.

Automated expert-level scleral spur detection and quantitative biometric analysis on the ANTERION anterior segment OCT system

AIM

To perform an independent validation of deep learning (DL) algorithms for automated scleral spur detection and measurement of scleral spur-based biometric parameters in anterior segment optical coherence tomography (AS-OCT) images.

METHODS

Patients receiving routine eye care underwent AS-OCT imaging using the ANTERION OCT system (Heidelberg Engineering, Heidelberg, Germany). Scleral spur locations were marked by three human graders (reference, expert and novice) and predicted using DL algorithms developed by Heidelberg Engineering that prioritise a false positive rate <4% (FPR4) or true positive rate >95% (TPR95). Performance of human graders and DL algorithms were evaluated based on agreement of scleral spur locations and biometric measurements with the reference grader.

RESULTS

1308 AS-OCT images were obtained from 117 participants. Median differences in scleral spur locations from reference locations were significantly smaller (p<0.001) for the FPR4 (52.6±48.6 µm) and TPR95 (55.5±50.6 µm) algorithms compared with the expert (61.1±65.7 µm) and novice (79.4±74.9 µm) graders. Intergrader reproducibility of biometric measurements was excellent overall for all four (intraclass correlation coefficient range 0.918-0.997). Intergrader reproducibility of the expert grader (0.567-0.965) and DL algorithms (0.746-0.979) exceeded that of the novice grader (0.146-0.929) for images with narrow angles defined by OCT measurement of angle opening distance 500 µm anterior to the scleral spur (AOD500)<150 µm.

CONCLUSIONS

DL algorithms on the ANTERION approximate expert-level measurement of scleral spur-based biometric parameters in an independent patient population. These algorithms could enhance clinical utility of AS-OCT imaging, especially for evaluating patients with angle closure and performing intraocular lens calculations.

Assessment of angle closure disease in the age of artificial intelligence: A review

Primary angle closure glaucoma is a visually debilitating disease that is under-detected worldwide. Many of the challenges in managing primary angle closure disease (PACD) are related to the lack of convenient and precise tools for clinic-based disease assessment and monitoring. Artificial intelligence (AI)- assisted tools to detect and assess PACD have proliferated in recent years with encouraging results. Machine learning (ML) algorithms that utilize clinical data have been developed to categorize angle closure eyes by disease mechanism. Other ML algorithms that utilize image data have demonstrated good performance in detecting angle closure. Nonetheless, deep learning (DL) algorithms trained directly on image data generally outperformed traditional ML algorithms in detecting PACD, were able to accurately differentiate between angle status (open, narrow, closed), and automated the measurement of quantitative parameters. However, more work is required to expand the capabilities of these AI algorithms and for deployment into real-world practice settings. This includes the need for real-world evaluation, establishing the use case for different algorithms, and evaluating the feasibility of deployment while considering other clinical, economic, social, and policy-related factors.

Deep Learning-based Quantification of Anterior Segment OCT Parameters

Objective

To develop and validate a deep learning algorithm that could automate the annotation of scleral spur (SS) and segmentation of anterior chamber (AC) structures for measurements of AC, iris, and angle width parameters in anterior segment OCT (ASOCT) scans.

Design

Cross-sectional study.

Subjects

Data from 2 population-based studies (i.e., the Singapore Chinese Eye Study and Singapore Malay Eye Study) and 1 clinical study on angle-closure disease were included in algorithm development. A separate clinical study on angle-closure disease was used for external validation.

Method

Image contrast of ASOCT scans were first enhanced with CycleGAN. We utilized a heat map regression approach with coarse-to-fine framework for SS annotation. Then, an ensemble network of U-Net, full resolution residual network, and full resolution U-Net was used for structure segmentation. Measurements obtained from predicted SSs and structure segmentation were measured and compared with measurements obtained from manual SS annotation and structure segmentation (i.e., ground truth).

Main Outcome Measures

We measured Euclidean distance and intraclass correlation coefficients (ICC) to evaluate SS annotation and Dice similarity coefficient for structure segmentation. The ICC, Bland-Altman plot, and repeatability coefficient were used to evaluate agreement and precision of measurements.

Results

For SS annotation, our algorithm achieved a Euclidean distance of 124.7 μm, ICC ≥ 0.95, and a 3.3% error rate. For structure segmentation, we obtained Dice similarity coefficient ≥ 0.91 for cornea, iris, and AC segmentation. For angle width measurements, ≥ 95% of data points were within the 95% limits-of-agreement in Bland-Altman plot with insignificant systematic bias (all P > 0.12). The ICC ranged from 0.71-0.87 for angle width measurements, 0.54 for IT750, 0.83-0.85 for other iris measurements, and 0.89-0.99 for AC measurements. Using the same SS coordinates from a human expert, measurements obtained from our algorithm were generally less variable than measurements obtained from a semiautomated angle assessment program.

Conclusion

We developed a deep learning algorithm that could automate SS annotation and structure segmentation in ASOCT scans like human experts, in both open-angle and angle-closure eyes. This algorithm reduces the time needed and subjectivity in obtaining ASOCT measurements.

Financial Disclosures

The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Deep Learning-Based Model for Automatic Assessment of Anterior Angle Chamber in Ultrasound Biomicroscopy

OBJECTIVE

The goal of the work described here was to develop and assess a deep learning-based model that could automatically segment anterior chamber angle (ACA) tissues; classify iris curvature (I-Curv), iris root insertion (IRI), and angle closure (AC); automatically locate scleral spur; and measure ACA parameters in ultrasound biomicroscopy (UBM) images.

METHODS

A total of 11,006 UBM images were obtained from 1538 patients with primary angle-closure glaucoma who were admitted to the Eye Center of Renmin Hospital of Wuhan University (Wuhan, China) to develop an imaging database. The UNet++ network was used to segment ACA tissues automatically. In addition, two support vector machine (SVM) algorithms were developed to classify I-Curv and AC, and a logistic regression (LR) algorithm was developed to classify IRI. Meanwhile, an algorithm was developed to automatically locate the scleral spur and measure ACA parameters. An external data set of 1,658 images from Huangshi Aier Eye Hospital was used to evaluate the performance of the model under different conditions. An additional 439 images were collected to compare the performance of the model with experts.

RESULTS

The model achieved accuracies of 95.2%, 88.9% and 85.6% in classification of AC, I-Curv and IRI, respectively. Compared with ophthalmologists, the model achieved an accuracy of 0.765 in classifying AC, I-Curv and IRI, indicating that its high accuracy was as high as that of the ophthalmologists (p > 0.05). The average relative errors (AREs) of ACA parameters were smaller than 15% in the internal data sets. Intraclass correlation coefficients (ICCs) of all the angle-related parameters were greater than 0.911. ICC values of all iris thickness parameters were greater than 0.884. The accurate measurement of ACA parameters partly depended on accurate localization of the scleral spur (p < 0.001).

CONCLUSION

The model could effectively and accurately evaluate the ACA automatically based on fully automated analysis of UBM images, and it can potentially be a promising tool to assist ophthalmologists. The present study suggested that the deep learning model can be extensively applied to the evaluation of ACA and AC-related biometric risk factors, and it may broaden the application of UBM imaging in the clinical research of primary angle-closure glaucoma.

Agreement and Reproducibility of Anterior Chamber Angle Measurements between CASIA2 Built-In Software and Human Graders

PURPOSE

This study evaluated the agreement and reproducibility of ACA measurements obtained using the built-in software of the CASIA2 (Version 3G.1) and the measurements derived from expert clinicians.

METHODS

Healthy volunteers underwent ophthalmological evaluation and AS-OCT examination. ACA measurements derived from automated and manual SS location were obtained using the CASIA2 automated software and clinician identification, respectively. The intraobserver, interobserver reproducibility, CASIA2-human grader reproducibility and CASIA2 repeatability were assessed using intraclass correlation coefficients (ICCs).

RESULTS

The study examined 58 eyes of 30 participants. The CASIA2 software showed excellent repeatability for all ACA parameters (ICC > 0.84). Intraobserver, interobserver, and CASIA2-human grader reproducibility were also excellent (ICC > 0.87). Interobserver agreement was high, except for nasal TISA500, differing between observers 1 and 2 (p < 0.05). The agreement between CASIA2 measurements and human graders was high, except for nasal TISA500, where observer 1 values were smaller (p < 0.05).

CONCLUSION

The CASIA2 built-in software reliably measures ACA parameters in healthy individuals, demonstrating high consistency. Although a small difference was observed in nasal TISA500 measurements, interobserver and CASIA2-human grader reproducibility remained excellent. Automated SS detection has the potential to facilitate evaluation and monitoring of primary angle closure disease.

Classification of Angle Closure Severity by Hierarchical Cluster Analysis of Ocular Biometrics in the Dark and Light

Purpose

The purpose of this study was to investigate the classification of angle closure eyes based on hierarchical cluster analysis of ocular biometrics measured in the dark and light using anterior segment optical coherence tomography (AS-OCT).

Methods

Participants of the Chinese American Eye Study received complete eye examinations to identify primary angle closure suspects (PACS) and primary angle closure without/with glaucoma (PAC/G). AS-OCT was performed in the dark and light. Biometric parameters describing the angle, iris, lens, and anterior chamber were analyzed. Hierarchical clustering was performed using Ward's method. Post hoc logistic regression models were developed to identify biometric predictors of angle closure staging.

Results

Analysis of 159 eyes with PACS (N = 120) or PAC/G (N = 39) produced 2 clusters in the dark and light. In both analyses, cluster 1 (N = 132 in the dark and N = 126 in the light) was characterized by smaller angle opening distance (AOD)750 and trabecular iris space area (TISA)750, greater iris curvature (IC), and greater lens vault (LV; P < 0.001) than cluster 2. The proportion of PAC/PACG to PACS eyes was significantly higher in cluster 1 than 2 in the light (36:90 and 3:30, respectively; P = 0.02), but not the dark (36:96 and 3:24, respectively; P = 0.08). On multivariable regression analyses, smaller TISA750 (odds ratio [OR] = 0.84 per 0.01 mm2) and AOD750 (OR = 0.93 per 0.01 mm) in the light and smaller TISA750 (OR = 0.86 per 0.01 mm2) in the dark conferred higher risk of PAC/G (P ≤ 0.02).

Conclusions

Unsupervised cluster analysis of ocular biometrics can classify angle closure eyes by severity. Static biometrics measured in the light and dark are both predictive of PAC/G.

Translational Relevance

Clustering of biometrics measured in the light could provide an alternative source of information to risk-stratify angle closure eyes for more severe disease.

Comprehensive assessment of the anterior segment in refraction corrected OCT based on multitask learning

Anterior segment diseases are among the leading causes of irreversible blindness. However, a method capable of recognizing all important anterior segment structures for clinical diagnosis is lacking. By sharing the knowledge learned from each task, we proposed a fully automated multitask deep learning method that allows for simultaneous segmentation and quantification of all major anterior segment structures, including the iris, lens, cornea, as well as implantable collamer lens (ICL) and intraocular lens (IOL), and meanwhile for landmark detection of scleral spur and iris root in anterior segment OCT (AS-OCT) images. In addition, we proposed a refraction correction method to correct for the true geometry of the anterior segment distorted by light refraction during OCT imaging. 1251 AS-OCT images from 180 patients were collected and were used to train and test the model. Experiments demonstrated that our proposed network was superior to state-of-the-art segmentation and landmark detection methods, and close agreement was achieved between manually and automatically computed clinical parameters associated with anterior chamber, pupil, iris, ICL, and IOL. Finally, as an example, we demonstrated how our proposed method can be applied to facilitate the clinical evaluation of cataract surgery.

Deep Learning-Based Classification of Subtypes of Primary Angle-Closure Disease With Anterior Segment Optical Coherence Tomography

PRCIS

We developed a deep learning-based classifier that can discriminate primary angle closure suspects (PACS), primary angle closure (PAC)/primary angle closure glaucoma (PACG), and also control eyes with open angle with acceptable accuracy.

PURPOSE

To develop a deep learning-based classifier for differentiating subtypes of primary angle closure disease, including PACS and PAC/PACG, and also normal control eyes.

MATERIALS AND METHODS

Anterior segment optical coherence tomography images were used for analysis with 5 different networks including MnasNet, MobileNet, ResNet18, ResNet50, and EfficientNet. The data set was split with randomization performed at the patient level into a training plus validation set (85%), and a test data set (15%). Then 4-fold cross-validation was used to train the model. In each mentioned architecture, the networks were trained with original and cropped images. Also, the analyses were carried out for single images and images grouped on the patient level (case-based). Then majority voting was applied to the determination of the final prediction.

RESULTS

A total of 1616 images of normal eyes (87 eyes), 1055 images of PACS (66 eyes), and 1076 images of PAC/PACG (66 eyes) eyes were included in the analysis. The mean ± SD age was 51.76 ± 15.15 years and 48.3% were males. MobileNet had the best performance in the model, in which both original and cropped images were used. The accuracy of MobileNet for detecting normal, PACS, and PAC/PACG eyes was 0.99 ± 0.00, 0.77 ± 0.02, and 0.77 ± 0.03, respectively. By running MobileNet in a case-based classification approach, the accuracy improved and reached 0.95 ± 0.03, 0.83 ± 0.06, and 0.81 ± 0.05, respectively. For detecting the open angle, PACS, and PAC/PACG, the MobileNet classifier achieved an area under the curve of 1, 0.906, and 0.872, respectively, on the test data set.

CONCLUSION

The MobileNet-based classifier can detect normal, PACS, and PAC/PACG eyes with acceptable accuracy based on anterior segment optical coherence tomography images.

Optimal number and orientation of anterior segment OCT images to measure ocular biometric parameters in angle closure eyes: the Chinese American Eye Study

PURPOSE

To assess the optimal number and orientation of anterior segment optical coherence tomography (AS-OCT) images for accurately measuring ocular biometric parameters in angle closure eyes.

METHODS

Subjects with angle closure, defined as >3 quadrants of non-visible pigmented trabecular meshwork on static gonioscopy, were selected from the Chinese American Eye Study. Mean angle opening distance (AOD500) was calculated using four images (0°-180°, 45°-225°, 90°-270° and 135°-315° meridians) from one eye per subject. Ten eyes from each quartile of AOD500 measurements were randomly selected for detailed 32-image analysis of 10 biometric parameters, including AOD500, iris curvature (IC), anterior chamber depth (ACD), lens vault (LV), and anterior chamber area (ACA). Mean and range of measurements from 1, 2, 4, 8 or 16 images were compared with 32-image values for all parameters.

RESULTS

40 out of 335 eyes with angle closure were selected for 32-image analysis. Deviation from the 32-image mean was between 0.44% and 19.31% with one image, decreasing to 0.08% to 4.21% with two images for all parameters. Deviation from the 32-image range of measurements was between 54.67% to 88.94% with one image, decreasing to <7.00% with eight images for all parameters except ACD and ACA. Orienting the first image analysed along the 25°-205° meridian better approximated the range of measurements when four or fewer images were analysed.

CONCLUSIONS

Sectoral anatomical variations in angle closure eyes are easily misrepresented based on current AS-OCT imaging conventions. A revised multi-image approach can better capture the mean and range of biometric measurements.

Automatic measurement of anterior chamber angle parameters in AS-OCT images using deep learning

The early assessment of angle closure is of great significance for the timely diagnosis and treatment of primary angle-closure glaucoma (PACG). Anterior segment optical coherence tomography (AS-OCT) provides a fast and non-contact way to evaluate the angle close using the iris root (IR) and scleral spur (SS) information. The objective of this study was to develop a deep learning method to automatically detect IR and SS in AS-OCT for measuring anterior chamber (AC) angle parameters including angle opening distance (AOD), trabecular iris space area (TISA), trabecular iris angle (TIA), and anterior chamber angle (ACA). 3305 AS-OCT images from 362 eyes and 203 patients were collected and analyzed. Based on the recently proposed transformer-based architecture that learns to capture long-range dependencies by leveraging the self-attention mechanism, a hybrid convolutional neural network (CNN) and transformer model to encode both local and global features was developed to automatically detect IR and SS in AS-OCT images. Experiments demonstrated that our algorithm achieved a significantly better performance than state-of-the-art methods for AS-OCT and medical image analysis with a precision of 0.941, a sensitivity of 0.914, an F1 score of 0.927, and a mean absolute error (MAE) of 37.1±25.3 µm for IR, and a precision of 0.805, a sensitivity of 0.847, an F1 score of 0.826, and an MAE of 41.4±29.4 µm for SS, and a high agreement with expert human analysts for AC angle parameter measurement. We further demonstrated the application of the proposed method to evaluate the effect of cataract surgery with IOL implantation in a PACG patient and to assess the outcome of ICL implantation in a patient with high myopia with a potential risk of developing PACG. The proposed method can accurately detect IR and SS in AS-OCT images and effectively facilitate the AC angle parameter measurement for pre- and post-operative management of PACG.

Refractive Error and Anterior Chamber Depth as Risk Factors in Primary Angle Closure Disease: The Chinese American Eye Study

PRCIS

The risk of primary angle closure disease (PACD) rises rapidly with greater hyperopia while remaining relatively low for all degrees of myopia. Refractive error (RE) is useful for angle closure risk stratification in the absence of biometric data.

PURPOSE

To assess the role of RE and anterior chamber depth (ACD) as risk factors in PACD.

METHODS

Chinese American Eye Study participants received complete eye examinations including refraction, gonioscopy, amplitude-scan biometry, and anterior segment ocular coherence tomography imaging. PACD included primary angle closure suspect (≥3 quadrants of angle closure on gonioscopy) and primary angle closure/primary angle closure glaucoma (peripheral anterior synechiae or intraocular pressure >21 mm Hg). Logistic regression models were developed to assess associations between PACD and RE and/or ACD adjusted for sex and age. Locally weighted scatterplot smoothing curves were plotted to assess continuous relationships between variables.

RESULTS

Three thousand nine hundred seventy eyes (3403 open angle and 567 PACD) were included. The risk of PACD increased with greater hyperopia [odds ratio (OR) = 1.41 per diopter (D); P < 0.001] and shallower ACD (OR = 1.75 per 0.1 mm; P < 0.001). Hyperopia (≥ + 0.5 D; OR = 5.03) and emmetropia (-0.5 D to +0.5 D; OR = 2.78) conferred a significantly higher risk of PACD compared with myopia (≤0.5 D). ACD (standardized regression coefficient = -0.54) was a 2.5-fold stronger predictor of PACD risk compared with RE (standardized regression coefficient = 0.22) when both variables were included in one multivariable model. The sensitivity and specificity of a 2.6 mm ACD cutoff for PACD were 77.5% and 83.2% and of a +2.0 D RE cutoff were 22.3% and 89.1%.

CONCLUSION

The risk of PACD rises rapidly with greater hyperopia while remaining relatively low for all degrees of myopia. Although RE is a weaker predictor of PACD than ACD, it remains a useful metric to identify patients who would benefit from gonioscopy in the absence of biometric data.

Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives

Artificial intelligence (AI) is an emerging technology in healthcare and holds the potential to disrupt many arms in medical care. In particular, disciplines using medical imaging modalities, including e.g. radiology but ophthalmology as well, are already confronted with a wide variety of AI implications. In ophthalmologic research, AI has demonstrated promising results limited to specific diseases and imaging tools, respectively. Yet, implementation of AI in clinical routine is not widely spread due to availability, heterogeneity in imaging techniques and AI methods. In order to describe the status quo, this narrational review provides a brief introduction to AI ("what the ophthalmologist needs to know"), followed by an overview of different AI-based applications in ophthalmology and a discussion on future challenges.Abbreviations: Age-related macular degeneration, AMD; Artificial intelligence, AI; Anterior segment OCT, AS-OCT; Coronary artery calcium score, CACS; Convolutional neural network, CNN; Deep convolutional neural network, DCNN; Diabetic retinopathy, DR; Machine learning, ML; Optical coherence tomography, OCT; Retinopathy of prematurity, ROP; Support vector machine, SVM; Thyroid-associated ophthalmopathy, TAO.

Anterior segment biometric measurements explain misclassifications by a deep learning classifier for detecting gonioscopic angle closure

BACKGROUND/AIMS

To identify biometric parameters that explain misclassifications by a deep learning classifier for detecting gonioscopic angle closure in anterior segment optical coherence tomography (AS-OCT) images.

METHODS

Chinese American Eye Study (CHES) participants underwent gonioscopy and AS-OCT of each angle quadrant. A subset of CHES AS-OCT images were analysed using a deep learning classifier to detect positive angle closure based on manual gonioscopy by a reference human examiner. Parameter measurements were compared between four prediction classes: true positives (TPs), true negatives (TNs), false positives (FPs) and false negatives (FN). Logistic regression models were developed to differentiate between true and false predictions. Performance was assessed using area under the receiver operating curve (AUC) and classifier accuracy metrics.

RESULTS

584 images from 127 participants were analysed, yielding 271 TPs, 224 TNs, 77 FPs and 12 FNs. Parameter measurements differed (p<0.001) between prediction classes among anterior segment parameters, including iris curvature (IC) and lens vault (LV), and angle parameters, including angle opening distance (AOD). FP resembled TP more than FN and TN in terms of anterior segment parameters (steeper IC and higher LV), but resembled TN more than TP and FN in terms of angle parameters (wider AOD). Models for detecting FP (AUC=0.752) and FN (AUC=0.838) improved classifier accuracy from 84.8% to 89.0%.

CONCLUSIONS

Misclassifications by an OCT-based deep learning classifier for detecting gonioscopic angle closure are explained by disagreement between anterior segment and angle parameters. This finding could be used to improve classifier performance and highlights differences between gonioscopic and AS-OCT definitions of angle closure.

A Mechanistic Model of Aqueous Humor Flow to Study Effects of Angle Closure on Intraocular Pressure

Purpose

To study the relationship between the circumferential extent of angle closure and elevation in intraocular pressure (IOP) using a novel mechanistic model of aqueous humor (AH) flow.

Methods

AH flow through conventional and unconventional outflow pathways was modeled using the unified Stokes and Darcy equations, which were solved using the finite element method. The severity and circumferential extent of angle closure were modeled by lowering the permeability of the outflow pathways. The IOP predicted by the model was compared with biometric and IOP data from the Chinese American Eye Study, wherein the circumferential extent of angle closure was determined using anterior segment OCT measurements of angle opening distance.

Results

The mechanistic model predicted an initial linear rise in IOP with increasing extent of angle closure which became nonlinear when the extent of closure exceeded around one-half of the circumference. The nonlinear rise in IOP was associated with a nonlinear increase in AH outflow velocity in the open regions of the angle. These predictions were consistent with the nonlinear relationship between angle closure and IOP observed in the clinical data.

Conclusions

IOP increases rapidly when the circumferential extent of angle closure exceeds 180°. Residual AH outflow may explain why not all angle closure eyes develop elevated IOP when angle closure is extensive.

Translational Relevance

This study provides insight into the extent of angle closure that is clinically relevant and confers increased risk of elevated IOP. The proposed model can be utilized to study other mechanisms of impaired aqueous outflow.

Assessment of Iris Trabecular Contact in Eyes with Gonioscopic Angle-Closure

PURPOSE

To investigate the extent of iris trabecular contact (ITC) measured by anterior segment OCT (AS-OCT) and its association with primary angle-closure (PAC) and PAC glaucoma (PACG) in eyes with gonioscopic angle-closure and to determine the diagnostic performance of ITC for detection of gonioscopic angle-closure.

DESIGN

Multicenter, prospective study.

PARTICIPANTS

A total of 119 healthy participants with gonioscopic open-angle and 170 patients with gonioscopic angle-closure (94 with PAC suspect and 76 with PAC/PACG) were included.

METHODS

One eye of each subject was randomly selected for AS-OCT imaging. Angle-opening distance (AOD500) and trabecular iris space area (TISA500) were measured every 10° for 360°. Two criteria of ITC500 were examined: (1) AOD500 = 0 mm and (2) TISA500 = 0 mm². The association between the extent of ITC500 and PAC/PACG in eyes with gonioscopic angle-closure was analyzed with logistic regression analysis.

MAIN OUTCOME MEASURES

Sensitivity and specificity of ITC500 for detection of gonioscopic angle-closure; odds ratio (OR) of PAC/PACG.

RESULTS

The sensitivity of ITC500 ≥ 10° for detection of gonioscopic angle-closure ranged from 82.4% (AOD500 = 0 mm) to 84.7% (TISA500 = 0 mm²), and the specificity was 85.7% (for both AOD500 = 0 mm and TISA500 = 0 mm²). The extent of ITC500 determined by AS-OCT, not cumulative gonioscopy score (i.e., the sum of the modified Shaffer grades over 4 quadrants), was associated with the odds of PAC/PACG in eyes with gonioscopic angle-closure; the odds of PAC/PACG increased by 5% for every 10° increase in ITC500 (OR, 1.051, 95% confidence interval [CI], 1.022-1.080 for AOD500 = 0 mm; OR, 1.049, 95% CI, 1.022-1.078 for TISA500 = 0 mm²). Axial length and anterior chamber depth were not associated with PAC/PACG in eyes with gonioscopic angle-closure (P ≥ 0.574).

CONCLUSIONS

A greater extent of ITC measured by AS-OCT, not angle-closure determined by gonioscopy, was associated with a greater odds of PAC/PACG in eyes with gonioscopic angle-closure.

Performance of the Deep Neural Network Ciloctunet, Integrated with Open-Source Software for Ciliary Muscle Segmentation in Anterior Segment OCT Images, Is on Par with Experienced Examiners

Anterior segment optical coherence tomography (AS-OCT), being non-invasive and well-tolerated, is the method of choice for an in vivo investigation of ciliary muscle morphology and function. The analysis requires the segmentation of the ciliary muscle, which is, when performed manually, both time-consuming and prone to examiner bias. Here, we present a convolutional neural network trained for the automatic segmentation of the ciliary muscle in AS-OCT images. Ciloctunet is based on the Freiburg U-net and was trained and validated using 1244 manually segmented OCT images from two previous studies. An accuracy of 97.5% for the validation dataset was achieved. Ciloctunet's performance was evaluated by replicating the findings of a third study with 180 images as the test data. The replication demonstrated that Ciloctunet performed on par with two experienced examiners. The intersection-over-union index (0.84) of the ciliary muscle thickness profiles between Ciloctunet and an experienced examiner was the same as between the two examiners. The mean absolute error between the ciliary muscle thickness profiles of Ciloctunet and the two examiners (35.16 µm and 45.86 µm) was comparable to the one between the examiners (34.99 µm). A statistically significant effect of the segmentation type on the derived biometric parameters was found for the ciliary muscle area but not for the selective thickness reading ("perpendicular axis"). Both the inter-rater and the intra-rater reliability of Ciloctunet were good to excellent. Ciloctunet avoids time-consuming manual segmentation, thus enabling the analysis of large numbers of images of ample study cohorts while avoiding possible examiner biases. Ciloctunet is available as open-source.

Deep learning and optical coherence tomography in glaucoma: Bridging the diagnostic gap on structural imaging

Glaucoma is a leading cause of progressive blindness and visual impairment worldwide. Microstructural evidence of glaucomatous damage to the optic nerve head and associated tissues can be visualized using optical coherence tomography (OCT). In recent years, development of novel deep learning (DL) algorithms has led to innovative advances and improvements in automated detection of glaucomatous damage and progression on OCT imaging. DL algorithms have also been trained utilizing OCT data to improve detection of glaucomatous damage on fundus photography, thus improving the potential utility of color photos which can be more easily collected in a wider range of clinical and screening settings. This review highlights ten years of contributions to glaucoma detection through advances in deep learning models trained utilizing OCT structural data and posits future directions for translation of these discoveries into the field of aging and the basic sciences.

Development of Cumulative Order-Preserving Image Transformation Based Variational Autoencoder for Anterior Segment Optical Coherence Tomography Images

Purpose

To develop a variational autoencoder (VAE) suitable for analysis of the latent structure of anterior segment optical coherence tomography (AS-OCT) images and to investigate possibilities of latent structure analysis of the AS-OCT images.

Methods

We retrospectively collected clinical data and AS-OCT images from 2111 eyes of 1261 participants from the ongoing Asan Glaucoma Progression Study. A specifically modified VAE was used to extract six symmetrical and one asymmetrical latent variable. A total of 1692 eyes of 1007 patients were used for training the model. Conventional measurements and latent variables were compared between 74 primary angle closure (PAC) and 51 primary angle closure glaucoma (PACG) eyes from validation set (419 eyes of 254 patients) that were not used for training.

Results

Among the symmetrical latent variables, the first three and the last demonstrated easily recognized features, anterior chamber area in η₁, curvature of the cornea in η₂, the pupil size in η₃ and corneal thickness in η₆, whereas η₄ and η₅ were more complex aggregating complex interactions of multiple structures. Compared with PAC eyes, there was no difference in any of the conventional measurements in PACG eyes. However, values of η₄ were significantly different between the two groups, being smaller in the PACG group (P = 0.015).

Conclusions

VAE is a useful framework for analysis of the latent structure of AS-OCT. Latent structure analysis could be useful in capturing features not readily evident with conventional measures.

Translational Relevance

This study suggested that a deep learning-based latent space model can be applied for the analysis of AS-OCT images to find latent characteristics of the anterior segment of the eye.

Development of a β-Variational Autoencoder for Disentangled Latent Space Representation of Anterior Segment Optical Coherence Tomography Images

Purpose

To investigate the feasibility of extracting a low-dimensional latent structure of anterior segment optical coherence tomography (AS-OCT) images by use of a β-variational autoencoder (β-VAE).

Methods

We retrospectively collected 2111 AS-OCT images from 2111 eyes of 1261 participants from the ongoing Asan Glaucoma Progression Study. After hyperparameter optimization, the images were analyzed with β-VAE.

Results

The mean participant age was 64.4 years, with mean values of visual field index and mean deviation of 86.4% and −5.33 dB, respectively. After experiments, a latent space size of 6 and β value of 5³ were selected for latent space analysis with β-VAE. Latent variables were successfully disentangled, showing readily interpretable distinct characteristics, such as the overall depth and area of the anterior chamber (η1), pupil diameter (η2), iris profile (η3 and η4), and corneal curvature (η5).

Conclusions

β-VAE can successfully be applied for disentangled latent space representation of AS-OCT images, revealing the high possibility of applying unsupervised learning in the medical image analysis.

Translational Relevance

This study demonstrates that a deep learning–based latent space model can be applied for the analysis of AS-OCT images.

Reproducibility of deep learning based scleral spur localisation and anterior chamber angle measurements from anterior segment optical coherence tomography images

Aims

To apply a deep learning model for automatic localisation of the scleral spur (SS) in anterior segment optical coherence tomography (AS-OCT) images and compare the reproducibility of anterior chamber angle (ACA) width between deep learning located SS (DLLSS) and manually plotted SS (MPSS).

Methods

In this multicentre, cross-sectional study, a test dataset comprising 5166 AS-OCT images from 287 eyes (116 healthy eyes with open angles and 171 eyes with primary angle-closure disease (PACD)) of 287 subjects were recruited from four ophthalmology clinics. Each eye was imaged twice by a swept-source AS-OCT (CASIA2, Tomey, Nagoya, Japan) in the same visit and one eye of each patient was randomly selected for measurements of ACA. The agreement between DLLSS and MPSS was assessed using the Euclidean distance (ED). The angle opening distance (AOD) of 750 µm (AOD750) and trabecular-iris space area (TISA) of 750 µm (TISA750) were calculated using the CASIA2 embedded software. The repeatability of ACA width was measured.

Results

The mean age was 60.8±12.3 years (range: 30–85 years) for the normal group and 63.4±10.6 years (range: 40–91 years) for the PACD group. The mean difference in ED for SS localisation between DLLSS and MPSS was 66.50±20.54 µm and 84.78±28.33 µm for the normal group and the PACD group, respectively. The span of 95% limits of agreement between DLLSS and MPSS was 0.064 mm for AOD750 and 0.034 mm2 for TISA750. The respective repeatability coefficients of AOD750 and TISA750 were 0.049 mm and 0.026 mm2 for DLLSS, and 0.058 mm and 0.030 mm2 for MPSS.

Conclusion

DLLSS achieved comparable repeatability compared with MPSS for measurement of ACA.

Automatic Localization of the Scleral Spur Using Deep Learning and Ultrasound Biomicroscopy

Purpose

The purpose of this study was to develop a convolutional neural network (CNN) for automated localization of the scleral spur in ultrasound biomicroscopy (UBM) images of open-angle eyes.

Methods

UBM images were acquired, and one glaucoma specialist provided reference coordinates of scleral spur locations in all images. A CNN model based on the EfficientNetB3 architecture was developed to detect the scleral spur in each image. The prediction errors and Euclidean distance were used to evaluate localization performance of the CNN model. Trabecular-iris angle 500 (TIA500) and angle-opening distance 500 (AOD500) were measured and analyzed using the scleral spur locations provided by the specialist and predicted by the CNN model.

Results

The CNN was developed using a training dataset of 2328 images and tested using an independent dataset of 258 images. The mean absolute prediction errors of CNN model were 48.06 ± 45.40 µm for X-coordinates and 30.84 ± 27.03 µm for Y-coordinates. The mean absolute intraobserver variability was 47.80 ± 44.45 µm for X-coordinates and 29.50 ± 25.77 µm for Y-coordinates. The mean Euclidean distance of the CNN was 60.41 ± 49.02 µm and the intraobserver mean Euclidean distance was 59.78 ± 47.12 µm. The mean absolute error in TIA500 was 1.26 ± 1.38 degrees for all test images and in AOD500 was 0.039 ± 0.051 mm.

Conclusions

A CNN can detect the scleral spur on UBM images of open-angle eyes with performance similar to that of a glaucoma specialist.

Translational Relevance

Deep learning algorithms for automating scleral spur localization would facilitate the quantitative assessment of the opening of the angle and the risk in angle closure.

Corneal pachymetry by AS-OCT after Descemet's membrane endothelial keratoplasty

Corneal thickness (pachymetry) maps can be used to monitor restoration of corneal endothelial function, for example after Descemet’s membrane endothelial keratoplasty (DMEK). Automated delineation of the corneal interfaces in anterior segment optical coherence tomography (AS-OCT) can be challenging for corneas that are irregularly shaped due to pathology, or as a consequence of surgery, leading to incorrect thickness measurements. In this research, deep learning is used to automatically delineate the corneal interfaces and measure corneal thickness with high accuracy in post-DMEK AS-OCT B-scans. Three different deep learning strategies were developed based on 960 B-scans from 50 patients. On an independent test set of 320 B-scans, corneal thickness could be measured with an error of 13.98 to 15.50 μm for the central 9 mm range, which is less than 3% of the average corneal thickness. The accurate thickness measurements were used to construct detailed pachymetry maps. Moreover, follow-up scans could be registered based on anatomical landmarks to obtain differential pachymetry maps. These maps may enable a more comprehensive understanding of the restoration of the endothelial function after DMEK, where thickness often varies throughout different regions of the cornea, and subsequently contribute to a standardized postoperative regime.

Semi-supervised generative adversarial networks for closed-angle detection on anterior segment optical coherence tomography images: an empirical study with a small training dataset

BACKGROUND

Semi-supervised learning algorithms can leverage an unlabeled dataset when labeling is limited or expensive to obtain. In the current study, we developed and evaluated a semi-supervised generative adversarial networks (GANs) model that detects closed-angle on anterior segment optical coherence tomography (AS-OCT) images using a small labeled dataset.

METHODS

In this cross-sectional study, a semi-supervised GANs model was developed for automatic closed-angle detection training on a small labeled and large unsupervised training dataset collected from the Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong (JSIEC). The closed-angle was defined as iris-trabecular contact beyond the scleral spur in AS-OCT images. We further developed two supervised deep learning (DL) models training on the same supervised dataset and the whole dataset separately. The semi-supervised GANs model and supervised DL models' performance were compared on two independent testing datasets from JSIEC (515 images) and the Department of Ophthalmology (84 images), National University Health System, respectively. The diagnostic performance was assessed by evaluation matrices, including the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).

RESULTS

For closed-angle detection using clinician grading of AS-OCT imaging as the reference standard, the semi-supervised GANs model showed comparable performance, with AUCs of 0.97 (95% CI, 0.96-0.99) and 0.98 (95% CI, 0.94-1.00), compared with the supervised DL model (using the whole dataset) [AUCs of 0.97 (95% CI, 0.96-0.99), and 0.97 (95% CI, 0.94-1.00)]. When training on the same small supervised dataset, the semi-supervised GANs achieved performance at least as well as, if not better than, the supervised DL model [AUCs of 0.90 (95% CI: 0.84-0.96), and 0.92 (95% CI, 0.86-0.97)].

CONCLUSIONS

The semi-supervised GANs method achieves diagnostic performance at least as good as a supervised DL model when trained on small labeled datasets. Further development of semi-supervised learning methods could be useful within clinical and research settings.

TRIAL REGISTRATION NUMBER

ChiCTR2000037892.

Ocular Biometric Determinants of Anterior Chamber Angle Width in Chinese Americans: The Chinese American Eye Study

PURPOSE

We sought to investigate anatomic mechanisms of angle narrowing by assessing ocular biometric determinants of anterior chamber angle width.

DESIGN

Population-based cross-sectional study.

METHODS

Subjects ≥50 years of age from the Chinese American Eye Study underwent a comprehensive ocular examination, including anterior segment optical coherence tomography imaging and ultrasound A-scan. Independent variables, including anterior chamber depth (ACD), lens vault (LV), iris curvature (IC), anterior chamber width, lens thickness, vitreous cavity depth, and axial length, and dependent variables, including angle opening distance, were measured in 1 randomly selected eye per subject. Univariable and multivariable regression models with standardized regression coefficients (SRCs) and semipartial correlation coefficients squares (SPCC²) were used to assess relative and unique contributions by independent variables to angle width.

RESULTS

Two thousand two hundred twenty-five subjects (1433 women and 834 men) were included in the analysis. All biometric parameters except lens thickness differed between men and women (age-adjusted P < .001). In model 1A (R² = 0.66), which included ACD, lens thickness, and vitreous cavity depth, ACD (SRC = 0.64, SPCC² = 0.19) and IC (SRC = -0.26, SPCC² = 0.041) were the strongest determinants of angle opening distance. In model 1B (R² = 0.58), which included LV and axial length, LV (SRC = -0.46, SPCC² = 0.1) and IC (SRC = -0.3, SPCC² = 0.047) were the strongest determinants of angle opening distance. Determinants of angle width were similar in separate multivariable models for men and women.

CONCLUSIONS

ACD, LV, and IC are the strongest determinants of angle width in Chinese Americans. Sex-related differences in angle width are explained by differences among biometric measurements. These results provide insights into anatomic mechanisms of angle narrowing and have important implications for quantitative assessments of angle closure eyes.

Anterior Chamber Angle Assessment Techniques: A Review

Assessment of the anterior chamber angle (ACA) is an essential part of the ophthalmological examination. It is intrinsically related to the diagnosis and treatment of glaucoma and has a role in its prevention. Although slit-lamp gonioscopy is considered the gold-standard technique for ACA evaluation, its poor reproducibility and the long learning curve are well-known shortcomings. Several new imaging techniques for angle evaluation have been developed in the recent years. However, whether these instruments may replace or not gonioscopy in everyday clinical practice remains unclear. This review summarizes the last findings in ACA evaluation, focusing on new instruments and their application to the clinical practice. Special attention will be given to the comparison between these new techniques and traditional slit-lamp gonioscopy. Whereas ultrasound biomicroscopy and anterior segment optical coherence tomography provide quantitative measurements of the anterior segment’s structures, new gonio-photographic systems allow for a qualitative assessment of angle findings, similarly to gonioscopy. Recently developed deep learning algorithms provide an automated classification of angle images, aiding physicians in taking faster and more efficient decisions. Despite new imaging techniques made analysis of the ACA more objective and practical, the ideal method for ACA evaluation has still to be determined.