To develop a deep learning approach to digitally stain optical coherence tomography (OCT) images of the optic nerve head (ONH).
A horizontal B-scan was acquired through the center of the ONH using ...OCT (Spectralis) for one eye of each of 100 subjects (40 healthy and 60 glaucoma). All images were enhanced using adaptive compensation. A custom deep learning network was then designed and trained with the compensated images to digitally stain (i.e., highlight) six tissue layers of the ONH. The accuracy of our algorithm was assessed (against manual segmentations) using the dice coefficient, sensitivity, specificity, intersection over union (IU), and accuracy. We studied the effect of compensation, number of training images, and performance comparison between glaucoma and healthy subjects.
For images it had not yet assessed, our algorithm was able to digitally stain the retinal nerve fiber layer + prelamina, the RPE, all other retinal layers, the choroid, and the peripapillary sclera and lamina cribrosa. For all tissues, the dice coefficient, sensitivity, specificity, IU, and accuracy (mean) were 0.84 ± 0.03, 0.92 ± 0.03, 0.99 ± 0.00, 0.89 ± 0.03, and 0.94 ± 0.02, respectively. Our algorithm performed significantly better when compensated images were used for training (P < 0.001). Besides offering a good reliability, digital staining also performed well on OCT images of both glaucoma and healthy individuals.
Our deep learning algorithm can simultaneously stain the neural and connective tissues of the ONH, offering a framework to automatically measure multiple key structural parameters of the ONH that may be critical to improve glaucoma management.
Given that the neural and connective tissues of the optic nerve head (ONH) exhibit complex morphological changes with the development and progression of glaucoma, their simultaneous isolation from ...optical coherence tomography (OCT) images may be of great interest for the clinical diagnosis and management of this pathology. A deep learning algorithm (custom U-NET) was designed and trained to segment 6 ONH tissue layers by capturing both the local (tissue texture) and contextual information (spatial arrangement of tissues). The overall Dice coefficient (mean of all tissues) was 0.91 ± 0.05 when assessed against manual segmentations performed by an expert observer. Further, we automatically extracted six clinically relevant neural and connective tissue structural parameters from the segmented tissues. We offer here a robust segmentation framework that could also be extended to the 3D segmentation of the ONH tissues.
Optical coherence tomography (OCT) has become an established clinical routine for the in vivo imaging of the optic nerve head (ONH) tissues, that is crucial in the diagnosis and management of various ...ocular and neuro-ocular pathologies. However, the presence of speckle noise affects the quality of OCT images and its interpretation. Although recent frame-averaging techniques have shown to enhance OCT image quality, they require longer scanning durations, resulting in patient discomfort. Using a custom deep learning network trained with 2,328 'clean B-scans' (multi-frame B-scans; signal averaged), and their corresponding 'noisy B-scans' (clean B-scans + Gaussian noise), we were able to successfully denoise 1,552 unseen single-frame (without signal averaging) B-scans. The denoised B-scans were qualitatively similar to their corresponding multi-frame B-scans, with enhanced visibility of the ONH tissues. The mean signal to noise ratio (SNR) increased from 4.02 ± 0.68 dB (single-frame) to 8.14 ± 1.03 dB (denoised). For all the ONH tissues, the mean contrast to noise ratio (CNR) increased from 3.50 ± 0.56 (single-frame) to 7.63 ± 1.81 (denoised). The mean structural similarity index (MSSIM) increased from 0.13 ± 0.02 (single frame) to 0.65 ± 0.03 (denoised) when compared with the corresponding multi-frame B-scans. Our deep learning algorithm can denoise a single-frame OCT B-scan of the ONH in under 20 ms, thus offering a framework to obtain superior quality OCT B-scans with reduced scanning times and minimal patient discomfort.
Anterior segment optical coherence tomography (AS-OCT) provides an objective imaging modality for visually identifying anterior segment structures. An automated detection system could assist ...ophthalmologists in interpreting AS-OCT images for the presence of angle closure.
Development of an artificial intelligence automated detection system for the presence of angle closure.
A deep learning system for automated angle-closure detection in AS-OCT images was developed, and this was compared with another automated angle-closure detection system based on quantitative features. A total of 4135 Visante AS-OCT images from 2113 subjects (8270 anterior chamber angle images with 7375 open-angle and 895 angle-closure) were examined. The deep learning angle-closure detection system for a 2-class classification problem was tested by 5-fold cross-validation. The deep learning system and the automated angle-closure detection system based on quantitative features were evaluated against clinicians' grading of AS-OCT images as the reference standard.
The area under the receiver operating characteristic curve of the system using quantitative features was 0.90 (95% confidence interval CI 0.891–0.914) with a sensitivity of 0.79 ± 0.037 and a specificity of 0.87 ± 0.009, while the area under the receiver operating characteristic curve of the deep learning system was 0.96 (95% CI 0.953–0.968) with a sensitivity of 0.90 ± 0.02 and a specificity of 0.92 ± 0.008, against clinicians' grading of AS-OCT images as the reference standard.
The results demonstrate the potential of the deep learning system for angle-closure detection in AS-OCT images.
Abstract
To investigate the association of peripheral anterior synechiae (PAS) with intraocular pressure (IOP) and anterior-segment parameters in subjects with primary angle-closure glaucoma (PACG). ...A total of 267 subjects with PACG were recruited and underwent gonioscopy and anterior-segment optical coherence tomography (ASOCT). Customized software was used to measure ASOCT parameters, including angle opening distance (AOD750) and trabecular-iris-space-area (TISA750) at 750 µm from the scleral spur, anterior chamber depth, width, area and volume (ACD, ACW, ACA, ACV), iris thickness (IT750), iris area (IAREA), and lens vault (LV). Presenting IOP was defined as the first IOP reading before the initiation of IOP-lowering treatment. The mean age of the 267 subjects was 67.0 ± 8.9 years, 140 (52.4%) were male, and 246 (92.1%) were of Chinese ethnicity. PAS was present in 122 (45.7%) subjects, and was most frequently found in the superior quadrant (79.5%). Subjects with PAS had greater presenting IOP (28.7 ± 12.9 vs 22.4 ± 9.7 mmHg, p < 0.001), narrower AOD750 (p < 0.001), smaller TISA750 (p < 0.001), ACD (p = 0.04), ACA (p = 0.02), ACV (p = 0.01) and larger LV (p = 0.01) compared to PACG eyes without PAS. No significant differences were noted for iris parameters. A multivariate logistic regression analysis showed that higher presenting IOP (β = 0.20, p < 0.001), worse visual field mean deviation (β = − 0.20, p = 0.01) and narrower AOD750 (β = − 0.25, p = 0.03) were the only parameters that significantly correlated with the extent of PAS in clock hours. Almost one-half of the subjects with PACG demonstrated PAS; these eyes were associated with higher presenting IOP, smaller anterior segment dimensions and more severe disease.
To study the associations between optic nerve head (ONH) strains under intraocular pressure (IOP) elevation with retinal sensitivity in patients with glaucoma.
Clinic-based cross-sectional study.
Two ...hundred twenty-nine patients with primary open-angle glaucoma (subdivided into 115 patients with high-tension glaucoma HTG and 114 patients with normal-tension glaucoma NTG).
For 1 eye of each patient, we imaged the ONH using spectral-domain OCT under the following conditions: (1) primary gaze and (2) primary gaze with acute IOP elevation (to approximately 35 mmHg) achieved through ophthalmodynamometry. A 3-dimensional strain-mapping algorithm was applied to quantify IOP-induced ONH tissue strain (i.e., deformation) in each ONH. Strains in the prelaminar tissue (PLT), the retina, the choroid, the sclera, and the lamina cribrosa (LC) were associated (using linear regression) with measures of retinal sensitivity from the 24-2 Humphrey visual field test (Carl Zeiss Meditec). This was performed globally, then locally according to a previously published regionalization scheme.
Associations between ONH strains and values of retinal sensitivity from visual field testing.
For patients with HTG, we found (1) significant negative linear associations between ONH strains and retinal sensitivity (P < 0.001; on average, a 1% increase in ONH strains corresponded to a decrease in retinal sensitivity of 1.1 decibels dB), (2) that high-strain regions colocalized with anatomically mapped regions of high visual field loss, and (3) that the strongest negative associations were observed in the superior region and in the PLT. In contrast, for patients with NTG, no significant associations between strains and retinal sensitivity were observed except in the superotemporal region of the LC.
We found significant negative associations between IOP-induced ONH strains and retinal sensitivity in a relatively large glaucoma cohort. Specifically, patients with HTG who experienced higher ONH strains were more likely to exhibit lower retinal sensitivities. Interestingly, this trend in general was less pronounced in patients with NTG, which could suggest a distinct pathophysiologic relationship between the two glaucoma subtypes.
To compare intraocular pressure (IOP) and anterior segment parameters between eyes with unilateral primary angle closure glaucoma (PACG) and their fellow eyes with primary angle closure (PAC) or ...primary angle closure suspect (PACS).
Subjects underwent anterior segment imaging using 360-degree swept-source optical coherence tomography (SS-OCT, CASIA Tomey, Nagoya, Japan) and ocular investigations including gonioscopy and IOP measurement. Each SS-OCT scan (divided into 8 frames, 22.5 degrees apart) was analysed and an average was obtained for the following anterior segment parameters: iridotrabecular contact (ITC), angle opening distance (AOD750), iris thickness and curvature, anterior chamber width, depth and area (ACW, ACD and ACA) and lens vault (LV).
Among 132 unilateral PACG subjects (mean age: 62.91 ± 7.2 years; 59.1% male), eyes with PACG had significantly higher presenting IOP (24.81 ± 0.94 vs. 18.43 ± 0.57 mmHg, p < 0.001), smaller gonioscopic Shaffer grade (2.07 ± 0.07 vs. 2.31 ± 0.07, p < 0.001) and a greater extent of peripheral anterior synechiae (PAS, 1.21 ± 0.21 vs. 0.54 ± 0.16 clock hours, p = 0.001). PACG eyes also exhibited increased ITC, ITC area, greater LV and smaller AOD750, ACD and ACA (all p < 0.05). Using the forward stepwise regression model, an increase in 1 mmHg in presenting IOP before laser peripheral iridotomy (LPI) increases the odds of having PACG by 9% (95% confidence interval 5%-14%).
PACG eyes have higher presenting IOP, smaller anterior segment parameters, greater extent of PAS, and larger LV compared to their fellow eyes with angle closure. Narrower anterior chamber dimensions and higher presenting IOP before LPI may increase risk of chronic elevated IOP and glaucomatous optic neuropathy after LPI.
Current management of glaucomatous optic neuropathy is limited to intraocular pressure control. Neuroglobin (Ngb) is an endogenous neuroprotectant expressed in neurons and astrocytes. We recently ...showed that exogenous intravitreal Ngb reduced inflammatory cytokines and microglial activation in a rodent model of hypoxia. We thus hypothesised that IVT-Ngb may also be neuroprotective in experimental glaucoma (EG) by mitigating optic nerve (ON) astrogliosis and microgliosis as well as structural damage. In this study using a microbead-induced model of EG in six Cynomolgus primates, optical coherence imaging showed that Ngb-treated EG eyes had significantly less thinning of the peripapillary minimum rim width, retinal nerve fibre layer thickness, and ON head cupping than untreated EG eyes. Immunohistochemistry confirmed that ON astrocytes overexpressed Ngb following Ngb treatment. A reduction in complement 3 and cleaved-caspase 3 activated microglia and astrocytes was also noted. Our findings in higher-order primates recapitulate the effects of neuroprotection by Ngb treatment in rodent EG studies and suggest that Ngb may be a potential candidate for glaucoma neuroprotection in humans.
Primary angle closure disease (PACD) covers a spectrum that includes primary angle closure suspect, primary angle closure, primary angle closure glaucoma, and acute primary angle closure. ...Accumulating evidence suggests that the pathogenesis of PACD is complex, with multiple contributory factors including variations in the anatomic or biometric characteristics of the angle segment structures. Advances in anterior segment optical coherence tomography technology have further enhanced our understanding of the risk factors and mechanisms involved in the disease process. This review discusses the potential clinical role of the anterior segment optical coherence tomography in the diagnosis, mechanistic evaluation, and as a predictor for future clinical outcomes of patients with PACD.
PDF
