The Future of Imaging in Detecting Glaucoma Progression

Cardiac Surgery Patients Have Reduced Vascularity and Structural Defects of the Retina Similar to Persons with Open-Angle Glaucoma

(1) Background: Growing evidence suggests impairment of ocular blood flow in open-angle glaucoma (OAG) pathology, but little is known about the effect of an impaired cardiovascular supply on the structural and vascular parameters of the retina. This study aims to investigate the variations of these parameters in OAG patients compared to patients undergoing cardiac surgery (CS) with cardiopulmonary bypass. (2) Methods: Prospective observational study with 82 subjects (30 controls, 33 OAG patients, and 19 CS patients) who underwent ophthalmological assessment by swept-source OCT and CDI in one randomly selected eye. (3) Results: In the CS group, OA and SPCA PSV and EDV were significantly lower, OA and SPCA RI were significantly higher compared to the OAG and healthy subjects (p = 0.000-0.013), and SPCA EDV correlated with linear CDR (r = -0.508, p = 0.027). Temporal ONH sectors of GCL++ and GCL+ layers in the CS group did not differ significantly compared to the OAG patients (p = 0.085 and p = 0.220). The CS patients had significantly thinner GCL++ and GCL+ layers in the inner sectors (p = 0.000-0.038) compared to healthy subjects, and these layers correlated with the CRA PSV, EDV, and RI and SPCA PSV (p = 0.005-0.047). (4) Conclusions: CS patients had lower vascular and structural parameters in the ONH, and macula compared to the healthy controls that were similar to persons with OAG.

Three-Dimensional Structural Phenotype of the Optic Nerve Head as a Function of Glaucoma Severity

Importance

The 3-dimensional (3-D) structural phenotype of glaucoma as a function of severity was thoroughly described and analyzed, enhancing understanding of its intricate pathology beyond current clinical knowledge.

Objective

To describe the 3-D structural differences in both connective and neural tissues of the optic nerve head (ONH) between different glaucoma stages using traditional and artificial intelligence-driven approaches.

Design, Setting, and Participants

This cross-sectional, clinic-based study recruited 541 Chinese individuals receiving standard clinical care at Singapore National Eye Centre, Singapore, and 112 White participants of a prospective observational study at Vilnius University Hospital Santaros Klinikos, Vilnius, Lithuania. The study was conducted from May 2022 to January 2023. All participants had their ONH imaged using spectral-domain optical coherence tomography and had their visual field assessed by standard automated perimetry.

Main Outcomes and Measures

(1) Clinician-defined 3-D structural parameters of the ONH and (2) 3-D structural landmarks identified by geometric deep learning that differentiated ONHs among 4 groups: no glaucoma, mild glaucoma (mean deviation [MD], ≥-6.00 dB), moderate glaucoma (MD, -6.01 to -12.00 dB), and advanced glaucoma (MD, <-12.00 dB).

Results

Study participants included 213 individuals without glaucoma (mean age, 63.4 years; 95% CI, 62.5-64.3 years; 126 females [59.2%]; 213 Chinese [100%] and 0 White individuals), 204 with mild glaucoma (mean age, 66.9 years; 95% CI, 66.0-67.8 years; 91 females [44.6%]; 178 Chinese [87.3%] and 26 White [12.7%] individuals), 118 with moderate glaucoma (mean age, 68.1 years; 95% CI, 66.8-69.4 years; 49 females [41.5%]; 97 Chinese [82.2%] and 21 White [17.8%] individuals), and 118 with advanced glaucoma (mean age, 68.5 years; 95% CI, 67.1-69.9 years; 43 females [36.4%]; 53 Chinese [44.9%] and 65 White [55.1%] individuals). The majority of ONH structural differences occurred in the early glaucoma stage, followed by a plateau effect in the later stages. Using a deep neural network, 3-D ONH structural differences were found to be present in both neural and connective tissues. Specifically, a mean of 57.4% (95% CI, 54.9%-59.9%, for no to mild glaucoma), 38.7% (95% CI, 36.9%-40.5%, for mild to moderate glaucoma), and 53.1 (95% CI, 50.8%-55.4%, for moderate to advanced glaucoma) of ONH landmarks that showed major structural differences were located in neural tissues with the remaining located in connective tissues.

Conclusions and Relevance

This study uncovered complex 3-D structural differences of the ONH in both neural and connective tissues as a function of glaucoma severity. Future longitudinal studies should seek to establish a connection between specific 3-D ONH structural changes and fast visual field deterioration and aim to improve the early detection of patients with rapid visual field loss in routine clinical care.

A novel biosensing platform for detection of glaucoma biomarker GDF15 via an integrated BLI-ELASA strategy

Glaucoma is a leading cause of irreversible blindness worldwide. Early discovery and prioritized intervention significantly impact its prognosis. Precise monitoring of the biomarker GDF15 contributes towards effective diagnosis and assessment of glaucoma. In this study, we demonstrate that GDF15 monitoring can also aid screening for glaucoma risk and early diagnosis. We obtained an aptamer (APT2TM) with high affinity, high specificity, and high stability for binding to both human-derived and rat-derived GDF15. Simulation results showed that the binding capabilities of APT2TM are mainly affected by the interplay between van der Waals forces and polar solvation energy, and that salt bridges and hydrogen bonds play critical roles. We then integrated an enzyme-linked aptamer sandwich assay (ELASA) into a biolayer interferometry (BLI) system to develop an automated, high-throughput, real-time monitoring BLI-ELASA biosensing platform. This platform exhibited a wide linear detection window (10-810 pg/mL range) and high sensitivity for GDF15 (detection limit of 5-6 pg/mL). Moreover, we confirmed its excellent performance when applied to GDF15 quantification in real samples from glaucomatous rats and clinical patients. We believe that this technology represents a robust, convenient, and cost-effective approach for risk screening, early diagnosis, and animal modeling evaluation of glaucoma in the near future.

Geometric Deep Learning to Identify the Critical 3D Structural Features of the Optic Nerve Head for Glaucoma Diagnosis

PURPOSE

To compare the performance of 2 relatively recent geometric deep learning techniques in diagnosing glaucoma from a single optical coherence tomographic (OCT) scan of the optic nerve head (ONH); and to identify the 3-dimensional (3D) structural features of the ONH that are critical for the diagnosis of glaucoma.

DESIGN

Comparison and evaluation of deep learning diagnostic algorithms.

METHODS

In this study, we included a total of 2247 nonglaucoma and 2259 glaucoma scans from 1725 participants. All participants had their ONHs imaged in 3D with Spectralis OCT. All OCT scans were automatically segmented using deep learning to identify major neural and connective tissues. Each ONH was then represented as a 3D point cloud. We used PointNet and dynamic graph convolutional neural network (DGCNN) to diagnose glaucoma from such 3D ONH point clouds and to identify the critical 3D structural features of the ONH for glaucoma diagnosis.

RESULTS

Both the DGCNN (area under the curve [AUC]: 0.97±0.01) and PointNet (AUC: 0.95±0.02) were able to accurately detect glaucoma from 3D ONH point clouds. The critical points (ie, critical structural features of the ONH) formed an hourglass pattern, with most of them located within the neuroretinal rim in the inferior and superior quadrant of the ONH.

CONCLUSIONS

The diagnostic accuracy of both geometric deep learning approaches was excellent. Moreover, we were able to identify the critical 3D structural features of the ONH for glaucoma diagnosis that tremendously improved the transparency and interpretability of our method. Consequently, our approach may have strong potential to be used in clinical applications for the diagnosis and prognosis of a wide range of ophthalmic disorders.

One-step high-throughput detection of low-abundance biomarker BDNF using a biolayer interferometry-based 3D aptasensor

Although biosensors for signal monitoring have been extensively developed, their application in one-step high-throughput detection of low-abundance disease biomarkers remains challenging. This study presents a 3D aptasensor based on a biolayer interferometry (BLI) technique, followed by the sensitive and rapid detection of the specific biomarker brain-derived neurotrophic factor (BDNF) for early screening of glaucoma, an irreversible disease that causes blindness. The developed 3D aptasensor enabled one-step batch conversion of the low-abundance biomarker BDNF binding into optical interference signal, which was mainly attributed to the following factors: (1) A dimeric aptamer with extremely high targeting affinity was constructed as a biorecognition molecule, (2) highly sensitive 3D matrix sensors were integrated as signal transduction elements, and (3) the BLI Octet system with automated, high-throughput, and real-time online monitoring capabilities was used for reporting. The 3D aptasensor exhibited a broad detection window from 0.41 to 250 ng/mL BDNF, with a limit of detection of 0.2 ng/mL. Furthermore, detection of BDNF in glaucoma patient serum using the aptasensor showed good agreement with ELISA findings as well as the clinical diagnosis of the patient, demonstrating the feasibility of the system as a screening tool for glaucoma. This one-step high-throughput screening approach provides a valuable solution for the early diagnosis of glaucoma and may reduce the risk of blindness in visually impaired people.

Study of Optimal Perimetric Testing In Children (OPTIC): developing consensus and setting research priorities for perimetry in the management of children with glaucoma

BACKGROUND

Perimetry is important in the management of children with glaucoma, but there is limited evidence-based guidance on its use. We report an expert consensus-based study to update guidance and identify areas requiring further research.

METHODS

Experts were invited to participate in a modified Delphi consensus process. Panel selection was based on clinical experience of managing children with glaucoma and UK-based training to minimise diversity of view due to healthcare setting. Questionnaires were delivered electronically, and analysed to establish 'agreement'. Divergence of opinions was investigated and resolved where possible through further iterations.

RESULTS

7/9 experts invited agreed to participate. Consensus (≥5/7 (71%) in agreement) was achieved for 21/26 (80.8%) items in 2 rounds, generating recommendations to start perimetry from approximately 7 years of age (IQR: 6.75-7.25), and use qualitative methods in conjunction with automated reliability indices to assess test quality. There was a lack of agreement about defining progressive visual field (VF) loss and methods for implementing perimetry longitudinally. Panel members highlighted the importance of informing decisions based upon individual circumstances-from gauging maturity/capability when selecting tests and interpreting outcomes, to accounting for specific clinical features (e.g. poor IOP control and/or suspected progressive VF loss) when making decisions about frequency of testing.

CONCLUSIONS

There is commonality of expert views in relation to implementing perimetry and interpreting test quality in the management of children with glaucoma. However, there remains a lack of agreement about defining progressive VF loss, and utilising perimetry over an individuals' lifetime, highlighting the need for further research.

Describing the Structural Phenotype of the Glaucomatous Optic Nerve Head Using Artificial Intelligence

PURPOSE

To develop a novel deep-learning approach that can describe the structural phenotype of the glaucomatous optic nerve head (ONH) and can be used as a robust glaucoma diagnosis tool.

DESIGN

Retrospective, deep-learning approach diagnosis study.

METHOD

We trained a deep-learning network to segment 3 neural-tissue and 4 connective-tissue layers of the ONH. The segmented optical coherence tomography images were then processed by a customized autoencoder network with an additional parallel branch for binary classification. The encoder part of the autoencoder reduced the segmented optical coherence tomography images into a low-dimensional latent space (LS), whereas the decoder and the classification branches reconstructed the images and classified them as glaucoma or nonglaucoma, respectively. We performed principal component analysis on the latent parameters and identified the principal components (PCs). Subsequently, the magnitude of each PC was altered in steps and reported how it impacted the morphology of the ONH.

RESULTS

The image reconstruction quality and diagnostic accuracy increased with the size of the LS. With 54 parameters in the LS, the diagnostic accuracy was 92.0 ± 2.3% with a sensitivity of 90.0 ± 2.4% (at 95% specificity), and the corresponding Dice coefficient for the reconstructed images was 0.86 ± 0.04. By changing the magnitudes of PC in steps, we were able to reveal how the morphology of the ONH changes as one transitions from a "nonglaucoma" to a "glaucoma" condition.

CONCLUSIONS

Our network was able to identify novel biomarkers of the ONH for glaucoma diagnosis. Specifically, the structural features identified by our algorithm were found to be related to clinical observations of glaucoma.

Measuring optic nerve head perfusion to monitor glaucoma: a study on structure-function relationships using laser speckle flowgraphy

PURPOSE

We aimed to describe the global and localized correlations among visual field (VF) sensitivity, optic nerve head (ONH) perfusion measured by laser speckle flowgraphy (LSFG) and neural structure measured by optical coherence tomography (OCT) in open-angle glaucoma (OAG) and to compare the floor effect for LSFG and OCT.

METHODS

Cross-sectional, multicenter study including one eye each from fifty OAG patients (mean age 69.3 years; average VF mean deviation, MD, -8.5 dB, range -25.17 to 0.85 dB) and fifty-one controls. Patients underwent SITA standard 24-2 automated perimetry and measurement of ONH perfusion, peripapillary retinal nerve fibre layer thickness (RNFLT) and macular ganglion cell-inner plexiform layer thickness (GCIPLT). We tested the presence of a significant change (breakpoint) in the correlation slope with VF sensitivity to assess floor effect.

RESULTS

The correlation between the LSFG parameter Mean All (MA) of the global disc area and MD (r = 0.56, p < 0.001) did not show a breakpoint, in contrast to the correlations between MD and OCT global parameters, which showed breakpoints at -8.53 and -4.05 dB for RNFLT and GCIPLT, respectively. Global and localized correlations with VF sensitivity were stronger for LSFG compared to OCT. In particular, LSFG outperformed OCT in the correlation with the central VF sector (r = 0.50, p < 0.001 and r = 0.06, p = 0.67 for MA and RNFLT, respectively).

CONCLUSION

The global and sectoral correlations with VF sensitivity and the favourable floor effect compared to OCT indicate LSFG as a promising tool to monitor progression particularly in late-stage glaucoma. Further longitudinal studies are warranted.

In Vivo Sublayer Analysis of Human Retinal Inner Plexiform Layer Obtained by Visible-Light Optical Coherence Tomography

Purpose

Growing evidence suggests that dendrite retraction or degeneration in a subpopulation of the retinal ganglion cells (RGCs) may precede detectable soma abnormalities and RGC death in glaucoma. Visualization of the lamellar structure of the inner plexiform layer (IPL) could advance clinical management and fundamental understanding of glaucoma. We investigated whether visible-light optical coherence tomography (vis-OCT) could detect the difference in the IPL sublayer thicknesses between small cohorts of healthy and glaucomatous subjects.

Method

We imaged nine healthy and five glaucomatous subjects with vis-OCT. Four of the healthy subjects were scanned three times each in two separate visits, and five healthy and five glaucoma subjects were scanned three times during a single visit. IPL sublayers were manually segmented using averaged A-line profiles.

Results

The mean ages of glaucoma and healthy subjects are 59.6 ± 13.4 and 45.4 ± 14.4 years (P = 0.02.) The visual field mean deviations (MDs) are −26.4 to −7.7 dB in glaucoma patients and −1.6 to 1.1 dB in healthy subjects (P = 0.002). Median coefficients of variation (CVs) of intrasession repeatability for the entire IPL and three sublayers are 3.1%, 5.6%, 6.9%, and 5.6% in healthy subjects and 1.8%, 6.0%, 7.7%, and 6.2% in glaucoma patients, respectively. The mean IPL thicknesses are 36.2 ± 1.5 µm in glaucomatous and 40.1 ± 1.7 µm in healthy eyes (P = 0.003).

Conclusions

IPL sublayer analysis revealed that the middle sublayer could be responsible for the majority of IPL thinning in glaucoma. Vis-OCT quantified IPL sublayers with good repeatability in both glaucoma and healthy subjects.

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.

Attention-Guided 3D-CNN Framework for Glaucoma Detection and Structural-Functional Association Using Volumetric Images

The direct analysis of 3D Optical Coherence Tomography (OCT) volumes enables deep learning models (DL) to learn spatial structural information and discover new bio-markers that are relevant to glaucoma. Downsampling 3D input volumes is the state-of-art solution to accommodate for the limited number of training volumes as well as the available computing resources. However, this limits the network's ability to learn from small retinal structures in OCT volumes. In this paper, our goal is to improve the performance by providing guidance to DL model during training in order to learn from finer ocular structures in 3D OCT volumes. Therefore, we propose an end-to-end attention guided 3D DL model for glaucoma detection and estimating visual function from retinal structures. The model consists of three pathways with the same network architecture but different inputs. One input is the original 3D-OCT cube and the other two are computed during training guided by the 3D gradient class activation heatmaps. Each pathway outputs the class-label and the whole model is trained concurrently to minimize the sum of losses from three pathways. The final output is obtained by fusing the predictions of the three pathways. Also, to explore the robustness and generalizability of the proposed model, we apply the model on a classification task for glaucoma detection as well as a regression task to estimate visual field index (VFI) (a value between 0 and 100). A 5-fold cross-validation with a total of 3782 and 10,370 OCT scans is used to train and evaluate the classification and regression models, respectively. The glaucoma detection model achieved an area under the curve (AUC) of 93.8% compared with 86.8% for a baseline model without the attention-guided component. The model also outperformed six different feature based machine learning approaches that use scanner computed measurements for training. Further, we also assessed the contribution of different retinal layers that are relevant to glaucoma. The VFI estimation model achieved a Pearson correlation and median absolute error of 0.75 and 3.6%, respectively, for a test set of size 3100 cubes.

Focal alteration of the intraretinal layers in neurodegenerative disorders

Focal intraretinal alterations have been studied to advance our understanding of the pathology of neurodegenerative diseases. The current literature involving focal alterations in the intraretinal layers was reviewed through PubMed using the search terms "focal alteration", "region of interest", "optical coherence tomography", "glaucoma", "multiple sclerosis", "Alzheimer's disease", "Parkinson disease", "neurodegenerative diseases" and other related items. It was found that focal alterations of intraretinal layers were different in various neurodegenerative diseases. The typical focal thinning might help differentiate various ocular and cerebral diseases, track disease progression, and evaluate the outcome of clinical trials. Advanced exploration of focal intraretinal alterations will help to further validate their clinical and research utility.

Estimating Visual Field Mean Deviation using Optical Coherence Tomographic Nerve Fiber Layer Measurements in Glaucoma Patients

To construct an optical coherence tomography (OCT) nerve fiber layer (NFL) parameter that has maximal correlation and agreement with visual field (VF) mean deviation (MD). The NFL_MD parameter in dB scale was calculated from the peripapillary NFL thickness profile nonlinear transformation and VF area-weighted averaging. From the Advanced Imaging for Glaucoma study, 245 normal, 420 pre-perimetric glaucoma (PPG), and 289 perimetric glaucoma (PG) eyes were selected. NFL_MD had significantly higher correlation (Pearson R: 0.68 vs 0.55, p < 0.001) with VF_MD than the overall NFL thickness. NFL_MD also had significantly higher sensitivity in detecting PPG (0.14 vs 0.08) and PG (0.60 vs 0.43) at the 99% specificity level. NFL_MD had better reproducibility than VF_MD (0.35 vs 0.69 dB, p < 0.001). The differences between NFL_MD and VF_MD were -0.34 ± 1.71 dB, -0.01 ± 2.08 dB and 3.54 ± 3.18 dB and 7.17 ± 2.68 dB for PPG, early PG, moderate PG, and severe PG subgroups, respectively. In summary, OCT-based NFL_MD has better correlation with VF_MD and greater diagnostic sensitivity than the average NFL thickness. It has better reproducibility than VF_MD, which may be advantageous in detecting progression. It agrees well with VF_MD in early glaucoma but underestimates damage in moderate~advanced stages.