Automated retinal layers segmentation in SD-OCT images using dual-gradient and spatial correlation smoothness constraint

Boundary-Repairing Dual-Path Network for Retinal Layer Segmentation in OCT Image with Pigment Epithelial Detachment

Automatic retinal layer segmentation in optical coherence tomography (OCT) images is crucial for the diagnosis of ocular diseases. Currently, automatic retinal layer segmentation works well with normal OCT images. However, pigment epithelial detachment (PED) dramatically alters the retinal structure, causing blurred boundaries and partial disappearance of the Bruch's Membrane (BM), thus posing challenges to the segmentation. To tackle these problems, we propose a novel dual-path U-shaped network for simultaneous layer segmentation and boundary regression. This network first designs a feature interaction fusion (FIF) module to strengthen the boundary shape constraints in the layer path. To address the challenge posed by partial BM disappearance and boundary-blurring, we propose a layer boundary repair (LBR) module. This module aims to use contrastive loss to enhance the confidence of blurred boundary regions and refine the segmentation of layer boundaries through the re-prediction head. In addition, we introduce a novel bilateral threshold distance map (BTDM) designed for the boundary path. The BTDM serves to emphasize information within boundary regions. This map, combined with the updated probability map, culminates in topology-guaranteed segmentation results achieved through a topology correction (TC) module. We investigated the proposed network on two severely deformed datasets (i.e., OCTA-500 and Aier-PED) and one slightly deformed dataset (i.e., DUKE). The proposed method achieves an average Dice score of 94.26% on the OCTA-500 dataset, which was 1.5% higher than BAU-Net and outperformed other methods. In the DUKE and Aier-PED datasets, the proposed method achieved average Dice scores of 91.65% and 95.75%, respectively.

Association of complement C3 inhibitor pegcetacoplan with reduced photoreceptor degeneration beyond areas of geographic atrophy

Preservation of photoreceptors beyond areas of retinal pigment epithelium atrophy is a critical treatment goal in eyes with geographic atrophy (GA) to prevent vision loss. Thus, we assessed the association of treatment with the complement C3 inhibitor pegcetacoplan with optical coherence tomography (OCT)-based photoreceptor laminae thicknesses in this post hoc analysis of the FILLY trial (NCT02503332). Retinal layers in OCT were segmented using a deep-learning-based pipeline and extracted along evenly spaced contour-lines surrounding areas of GA. The primary outcome measure was change from baseline in (standardized) outer nuclear layer (ONL) thickness at the 5.16°-contour-line at month 12. Participants treated with pegcetacoplan monthly had a thicker ONL along the 5.16° contour-line compared to the pooled sham arm (mean difference [95% CI] + 0.29 z-score units [0.16, 0.42], P < 0.001). The same was evident for eyes treated with pegcetacoplan every other month (+ 0.26 z-score units [0.13, 0.4], P < 0.001). Additionally, eyes treated with pegcetacoplan exhibited a thicker photoreceptor inner segment layer along the 5.16°-contour-line at month 12. These findings suggest that pegcetacoplan could slow GA progression and lead to reduced thinning of photoreceptor layers beyond the GA boundary. Future trials in earlier disease stages, i.e., intermediate AMD, aiming to slow photoreceptor degeneration warrant consideration.

Reference Database of Inner Retinal Layer Thickness and Thickness Asymmetry in Healthy Thai Adults as Measured by the Spectralis Spectral-Domain Optical Coherence Tomography

INTRODUCTION

The study aimed to determine a reference database of the thickness and intraocular thickness asymmetry of total retina, retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL) in healthy Thai subjects measured by the Spectralis spectral-domain optical coherence tomography.

METHODS

This cross-sectional study recruited the healthy subjects age ≥18 years, having spherical refraction within ±6 diopters and cylindrical refraction ±3 diopters, from a hospital's personnel and the people visiting the ophthalmology department. Only 1 eye of each subject was randomly selected for an analysis. Macular images were obtained using posterior pole thickness scan protocol over a 24° × 24° area at the center of the fovea. The automated retinal thickness segmentation values of total retina and three inner retinal layers were calculated for the mean and the mean intraocular thickness difference between superior and inferior retinal hemispheres. The influence of age, gender, and axial length on thickness and thickness asymmetry of individualized retinal layer was evaluated.

RESULTS

252 subjects were included in study with a mean (SD) age of 46.7 (15.8) years, and 120 (47.6%) were males. According to the Early Treatment Diabetic Retinopathy Study map, the inner ring area was the thickest location of the total retina (range; 326.0-341.5 µm), GCL (range; 47.7-52.7 µm), and IPL (range; 39.9-42.1 µm), whereas the thickest location of RNFL was at the outer ring area (range; 18.8-47.5 µm). For posterior pole intraocular thickness asymmetry, the greatest mean ± SD difference was observed for total retina (9.0 ± 2.2 µm), followed by RNFL (9.9 ± 3.2 µm) and GCL (2.7 ± 0.6 µm), and the lowest mean difference was noted for IPL (2.4 ± 0.5 µm). The thickness and thickness asymmetry of each retinal layer were variably influenced by age, gender, and axial length; however, these factors had a minimal influence on the thickness asymmetry maps of GCL and RNFL.

CONCLUSION

The reference database of the macular thickness and thickness asymmetry from this study would be beneficial in determining physiologic variations of the OCT parameters in the healthy Thai population.

Automated foveal location detection on spectral-domain optical coherence tomography in geographic atrophy patients

PURPOSE

To develop a fully automated algorithm for accurate detection of fovea location in atrophic age-related macular degeneration (AMD), based on spectral-domain optical coherence tomography (SD-OCT) scans.

METHODS

Image processing was conducted on a cohort of patients affected by geographic atrophy (GA). SD-OCT images (cube volume) from 55 eyes (51 patients) were extracted and processed with a layer segmentation algorithm to segment Ganglion Cell Layer (GCL) and Inner Plexiform Layer (IPL). Their en face thickness projection was convolved with a 2D Gaussian filter to find the global maximum, which corresponded to the detected fovea. The detection accuracy was evaluated by computing the distance between manual annotation and predicted location.

RESULTS

The mean total location error was 0.101±0.145mm; the mean error in horizontal and vertical en face axes was 0.064±0.140mm and 0.063±0.060mm, respectively. The mean error for foveal and extrafoveal retinal pigment epithelium and outer retinal atrophy (RORA) was 0.096±0.070mm and 0.107±0.212mm, respectively. Our method obtained a significantly smaller error than the fovea localization algorithm inbuilt in the OCT device (0.313±0.283mm, p <.001) or a method based on the thinnest central retinal thickness (0.843±1.221, p <.001). Significant outliers are depicted with the reliability score of the method.

CONCLUSION

Despite retinal anatomical alterations related to GA, the presented algorithm was able to detect the foveal location on SD-OCT cubes with high reliability. Such an algorithm could be useful for studying structural-functional correlations in atrophic AMD and could have further applications in different retinal pathologies.

Circumpapillary OCT-focused hybrid learning for glaucoma grading using tailored prototypical neural networks

Glaucoma is one of the leading causes of blindness worldwide and Optical Coherence Tomography (OCT) is the quintessential imaging technique for its detection. Unlike most of the state-of-the-art studies focused on glaucoma detection, in this paper, we propose, for the first time, a novel framework for glaucoma grading using raw circumpapillary B-scans. In particular, we set out a new OCT-based hybrid network which combines hand-driven and deep learning algorithms. An OCT-specific descriptor is proposed to extract hand-crafted features related to the retinal nerve fibre layer (RNFL). In parallel, an innovative CNN is developed using skip-connections to include tailored residual and attention modules to refine the automatic features of the latent space. The proposed architecture is used as a backbone to conduct a novel few-shot learning based on static and dynamic prototypical networks. The k-shot paradigm is redefined giving rise to a supervised end-to-end system which provides substantial improvements discriminating between healthy, early and advanced glaucoma samples. The training and evaluation processes of the dynamic prototypical network are addressed from two fused databases acquired via Heidelberg Spectralis system. Validation and testing results reach a categorical accuracy of 0.9459 and 0.8788 for glaucoma grading, respectively. Besides, the high performance reported by the proposed model for glaucoma detection deserves a special mention. The findings from the class activation maps are directly in line with the clinicians' opinion since the heatmaps pointed out the RNFL as the most relevant structure for glaucoma diagnosis.

Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary OCT images

An accurate and automated tissue segmentation algorithm for retinal optical coherence tomography (OCT) images is crucial for the diagnosis of glaucoma. However, due to the presence of the optic disc, the anatomical structure of the peripapillary region of the retina is complicated and is challenging for segmentation. To address this issue, we develop a novel graph convolutional network (GCN)-assisted two-stage framework to simultaneously label the nine retinal layers and the optic disc. Specifically, a multi-scale global reasoning module is inserted between the encoder and decoder of a U-shape neural network to exploit anatomical prior knowledge and perform spatial reasoning. We conduct experiments on human peripapillary retinal OCT images. We also provide public access to the collected dataset, which might contribute to the research in the field of biomedical image processing. The Dice score of the proposed segmentation network is 0.820 ± 0.001 and the pixel accuracy is 0.830 ± 0.002, both of which outperform those from other state-of-the-art techniques.

Progression of Photoreceptor Degeneration in Geographic Atrophy Secondary to Age-related Macular Degeneration

Importance

Sensitive outcome measures for disease progression are needed for treatment trials in geographic atrophy (GA) secondary to age-related macular degeneration (AMD).

Objective

To quantify photoreceptor degeneration outside regions of GA in eyes with nonexudative AMD, to evaluate its association with future GA progression, and to characterize its spatio-temporal progression.

Design, Setting, and Participants

Monocenter cohort study (Directional Spread in Geographic Atrophy [NCT02051998]) and analysis of data from a normative data study at a tertiary referral center. One hundred fifty-eight eyes of 89 patients with a mean (SD) age of 77.7 (7.1) years, median area of GA of 8.87 mm2 (IQR, 4.09-15.60), and median follow-up of 1.1 years (IQR, 0.52-1.7 years), as well as 93 normal eyes from 93 participants.

Exposures

Longitudinal spectral-domain optical coherence tomography (SD-OCT) volume scans (121 B-scans across 30° × 25°) were segmented with a deep-learning pipeline and standardized in a pointwise manner with age-adjusted normal data (z scores). Outer nuclear layer (ONL), photoreceptor inner segment (IS), and outer segment (OS) thickness were quantified along evenly spaced contour lines surrounding GA lesions. Linear mixed models were applied to assess the association between photoreceptor-related imaging features and GA progression rates and characterize the pattern of photoreceptor degeneration over time.

Main Outcomes and Measures

Association of ONL thinning with follow-up time (after adjusting for age, retinal topography [z score], and distance to the GA boundary).

Results

The study included 158 eyes of 89 patients (51 women and 38 men) with a mean (SD) age of 77.7 (7.1) years. The fully automated B-scan segmentation was accurate (dice coefficient, 0.82; 95% CI, 0.80-0.85; compared with manual markings) and revealed a marked interpatient variability in photoreceptor degeneration. The ellipsoid zone (EZ) loss-to-GA boundary distance and OS thickness were prognostic for future progression rates. Outer nuclear layer and IS thinning over time was significant even when adjusting for age and proximity to the GA boundary (estimates of -0.16 μm/y; 95% CI, -0.30 to -0.02; and -0.17 μm/y; 95% CI, -0.26 to -0.09).

Conclusions and Relevance

Distinct and progressive alterations of photoreceptor laminae (exceeding GA spatially) were detectable and quantifiable. The degree of photoreceptor degeneration outside of regions of retinal pigment epithelium atrophy varied markedly between eyes and was associated with future GA progression. Macula-wide photoreceptor laminae thinning represents a potential candidate end point to monitor treatment effects beyond mere GA lesion size progression.

Towards label-free 3D segmentation of optical coherence tomography images of the optic nerve head using deep learning

Recently proposed deep learning (DL) algorithms for the segmentation of optical coherence tomography (OCT) images to quantify the morphological changes to the optic nerve head (ONH) tissues during glaucoma have limited clinical adoption due to their device specific nature and the difficulty in preparing manual segmentations (training data). We propose a DL-based 3D segmentation framework that is easily translatable across OCT devices in a label-free manner (i.e. without the need to manually re-segment data for each device). Specifically, we developed 2 sets of DL networks: the 'enhancer' (enhance OCT image quality and harmonize image characteristics from 3 devices) and the 'ONH-Net' (3D segmentation of 6 ONH tissues). We found that only when the 'enhancer' was used to preprocess the OCT images, the 'ONH-Net' trained on any of the 3 devices successfully segmented ONH tissues from the other two unseen devices with high performance (Dice coefficients > 0.92). We demonstrate that is possible to automatically segment OCT images from new devices without ever needing manual segmentation data from them.

Clinically Verified Hybrid Deep Learning System for Retinal Ganglion Cells Aware Grading of Glaucomatous Progression

OBJECTIVE

Glaucoma is the second leading cause of blindness worldwide. Glaucomatous progression can be easily monitored by analyzing the degeneration of retinal ganglion cells (RGCs). Many researchers have screened glaucoma by measuring cup-to-disc ratios from fundus and optical coherence tomography scans. However, this paper presents a novel strategy that pays attention to the RGC atrophy for screening glaucomatous pathologies and grading their severity.

METHODS

The proposed framework encompasses a hybrid convolutional network that extracts the retinal nerve fiber layer, ganglion cell with the inner plexiform layer and ganglion cell complex regions, allowing thus a quantitative screening of glaucomatous subjects. Furthermore, the severity of glaucoma in screened cases is objectively graded by analyzing the thickness of these regions.

RESULTS

The proposed framework is rigorously tested on publicly available Armed Forces Institute of Ophthalmology (AFIO) dataset, where it achieved the F₁ score of 0.9577 for diagnosing glaucoma, a mean dice coefficient score of 0.8697 for extracting the RGC regions and an accuracy of 0.9117 for grading glaucomatous progression. Furthermore, the performance of the proposed framework is clinically verified with the markings of four expert ophthalmologists, achieving a statistically significant Pearson correlation coefficient of 0.9236.

CONCLUSION

An automated assessment of RGC degeneration yields better glaucomatous screening and grading as compared to the state-of-the-art solutions.

SIGNIFICANCE

An RGC-aware system not only screens glaucoma but can also grade its severity and here we present an end-to-end solution that is thoroughly evaluated on a standardized dataset and is clinically validated for analyzing glaucomatous pathologies.

HyCAD-OCT: A Hybrid Computer-Aided Diagnosis of Retinopathy by Optical Coherence Tomography Integrating Machine Learning and Feature Maps Localization

Optical Coherence Tomography (OCT) imaging has major advantages in effectively identifying the presence of various ocular pathologies and detecting a wide range of macular diseases. OCT examinations can aid in the detection of many retina disorders in early stages that could not be detected in traditional retina images. In this paper, a new hybrid computer-aided OCT diagnostic system (HyCAD) is proposed for classification of Diabetic Macular Edema (DME), Choroidal Neovascularization (CNV) and drusen disorders, while separating them from Normal OCT images. The proposed HyCAD hybrid learning system integrates the segmentation of Region of Interest (RoI), based on central serious chorioretinopathy (CSC) in Spectral Domain Optical Coherence Tomography (SD-OCT) images, with deep learning architectures for effective diagnosis of retinal disorders. The proposed system assimilates a range of techniques including RoI localization and feature extraction, followed by classification and diagnosis. An efficient feature fusion phase has been introduced for combining the OCT image features, extracted by Deep Convolutional Neural Network (CNN), with the features extracted from the RoI segmentation phase. This fused feature set is used to predict multiclass OCT retina disorders. The proposed segmentation phase of retinal RoI regions adds substantial contribution as it draws attention to the most significant areas that are candidate for diagnosis. A new modified deep learning architecture (Norm-VGG16) is introduced integrating a kernel regularizer. Norm-VGG16 is trained from scratch on a large benchmark dataset and used in RoI localization and segmentation. Various experiments have been carried out to illustrate the performance of the proposed system. Large Dataset of Labeled Optical Coherence Tomography (OCT) v3 benchmark is used to validate the efficiency of the model compared with others in literature. The experimental results show that the proposed model achieves relatively high-performance in terms of accuracy, sensitivity and specificity. An average accuracy, sensitivity and specificity of 98.8%, 99.4% and 98.2% is achieved, respectively. The remarkable performance achieved reflects that the fusion phase can effectively improve the identification ratio of the urgent patients’ diagnostic images and clinical data. In addition, an outstanding performance is achieved compared to others in literature.

Segmentation errors and motion artifacts in OCT-A associated with epiretinal membranes

OBJECTIVE

To explore segmentation errors, image quality, and motion-associated artifacts in eyes with idiopathic epiretinal membrane (ERM).

METHODS

This is a prospective observational study. We included 39 eyes affected by ERM and 40 eyes from age-matched healthy subjects. Optical coherence tomography-angiography (OCT-A) was performed in both groups. Segmentation was automatically performed by intergraded software. Segmentation was regarded as inaccurate if either border deviated from the correct plane by more than 50 μm. Presence of motion artifacts (blink lines, displacement, stretch artifacts, quilting, vessel doubling) and image quality index were reported.

RESULTS

Quality index score was 7.2 ± 0.9 for the ERM patients. Phakic eyes with ERM had quality index score of 7.71 ± 1.06, and pseudo-phakic eyes with ERM had a quality index score of 7.32 ± 0.85 (p = 0.22). Motion artifacts were 1.22 ± 0.7 in the study cohort. Segmentation was accurate in all healthy subjects (n = 40). Segmentation errors occurred in 64.1% of ERM patients. The inner plexiform layer was the segmentation boundary most prone to inaccurate segmentation, followed by the internal limiting membrane. Segmentation of retinal pigment epithelial layer was accurate in 96.7% of all cases.

CONCLUSIONS

OCT-A image quality cannot be accurately reproduced in pathological conditions, such as in ERM patients, and is prone to motion artifacts and segmentation errors. Incorrect segmentation results in anatomically incorrect en-face OCT-A images and subsequently in false quantification measures.

Multi-phase level set algorithm based on fully convolutional networks (FCN-MLS) for retinal layer segmentation in SD-OCT images with central serous chorioretinopathy (CSC)

As a function of the spatial position of the optical coherence tomography (OCT) image, retinal layer thickness is an important diagnostic indicator for many retinal diseases. Reliable segmentation of the retinal layer is necessary for extracting useful clinical information. However, manual segmentation of these layers is time-consuming and prone to bias. Furthermore, due to speckle noise, low image contrast, retinal detachment, and also irregular morphological features make the automatic segmentation task challenging. To alleviate these challenges, in this paper, we propose a new coarse-fine framework combining the full convolutional network (FCN) with a multiphase level set (named FCN-MLS) for automatic segmentation of nine boundaries in retinal spectral OCT images. In the coarse stage, FCN is used to learn the characteristics of specific retinal layer boundaries and achieve classification of four retinal layers. The boundaries are then extracted and the remaining boundaries are initialized based on a priori information about the thickness of the retinal layer. In order to prevent the overlapping of the segmentation interfaces, a regional restriction technique is used in the multi-phase level to evolve the boundaries to achieve fine nine retinal layers segmentation. Experimental results on 1280 B-scans show that the proposed method can segment nine retinal boundaries accurately. Compared with the manual delineation, the overall mean absolute boundary location difference and the overall mean absolute thickness difference were 5.88 ± 2.38μm and 5.81 ± 2.19μm, which showed a good consistency with manual segmentation by the physicians. Our experimental results also outperform state-of-the-art methods.

Prevalences of segmentation errors and motion artifacts in OCT-angiography differ among retinal diseases

PURPOSE

To assess the prevalences of segmentation errors and motion artifacts in optical coherence tomography angiography (OCT-A) in different retinal diseases METHODS: In a retrospective analysis, multimodal retinal imaging including OCT-A was performed in one eye of 57 healthy controls (50.96 ± 22.4 years) and 149 patients (66.42 ± 14.1 years) affected by different chorioretinal diseases: early/intermediate age-related macular degeneration (AMD; n = 26), neovascular AMD (nAMD; n = 22), geographic atrophy due to AMD (GA; n = 6), glaucoma (n = 28), central serous chorioretinopathy (CSC; n = 14), epiretinal membrane (EM; n = 26), retinal vein occlusion (RVO; n = 11), and retinitis pigmentosa (RP; n = 16). Central 3 × 3 mm² OCT-A imaging was performed with active eye-tracking (AngioVue, Optovue). Best-corrected visual acuity (BCVA) and signal strength index (SSI) were recorded. Images were independently evaluated by two graders using the OCT-A motion artifact score (MAS; scores I-IV) as well as a newly introduced segmentation accuracy score (SAS; score I-IIB).

RESULTS

Mean SSI was 63.67 ± 9.2 showing a negative correlation with increasing age (rSp = - 0.42, p < 0.001, n = 206). In the healthy cohort, mean MAS was 1.45 ± 0.8 and segmentation was accurate (SAS I) in all eyes. In eyes with retinal pathologies, mean MAS was 2.1 ± 0.9 (p < 0.001). Lowest MAS was observed in GA (2.67 ± 0.5) and RVO (2.45 ± 1.1). Compared to an accurate segmentation in 100% in healthy subjects, 34.2% (n = 51) of all patients showed highest segmentation quality (p < 0.001). 63.8% showed segmentation errors in more than 5% of all single b-scans in one (SAS IIA, n = 58) or at least two (SAS IIB, n = 40) segmentation boundaries. Highest percentages of inaccurate segmentation (SAS IIA or IIB) were observed in the nAMD group (90.1%). The inner plexiform layer was the segmentation boundary most prone to inaccurate segmentation in all pathologies compared to the inner limiting membrane (ILM) and retinal pigment epithelium (RPE) segmentation layer. Incorrect ILM segmentation was only seen in patients with EM.

CONCLUSIONS

Prior to both qualitative and quantitative analysis, OCT-A images must be carefully reviewed as motion artifacts and segmentation errors in current OCT-A technology are frequent particularly in pathologically altered maculae.

DRUNET: a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images

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.

Retinal Layer Abnormalities as Biomarkers of Schizophrenia

OBJECTIVE

Schizophrenia is associated with several brain deficits, as well as visual processing deficits, but clinically useful biomarkers are elusive. We hypothesized that retinal layer changes, noninvasively visualized using spectral-domain optical coherence tomography (SD-OCT), may represent a possible "window" to these abnormalities.

METHODS

A Leica EnvisuTM SD-OCT device was used to obtain high-resolution central foveal B-scans in both eyes of 35 patients with schizophrenia and 50 demographically matched controls. Manual retinal layer segmentation was performed to acquire individual and combined layer thickness measurements in 3 macular regions. Contrast sensitivity was measured at 3 spatial frequencies in a subgroup of each cohort. Differences were compared using adjusted linear models and significantly different layer measures in patients underwent Spearman Rank correlations with contrast sensitivity, quantified symptoms severity, disease duration, and antipsychotic medication dose.

RESULTS

Total retinal and photoreceptor complex thickness was reduced in all regions in patients (P < .0001). Segmentation revealed consistent thinning of the outer nuclear layer (P < .001) and inner segment layer (P < .05), as well as a pattern of parafoveal ganglion cell changes. Low spatial frequency contrast sensitivity was reduced in patients (P = .002) and correlated with temporal parafoveal ganglion cell complex thinning (R = .48, P = .01). Negative symptom severity was inversely correlated with foveal photoreceptor complex thickness (R = -.54, P = .001) and outer nuclear layer thickness (R = -.47, P = .005).

CONCLUSIONS

Our novel findings demonstrate considerable retinal layer abnormalities in schizophrenia that are related to clinical features and visual function. With time, SD-OCT could provide easily-measurable biomarkers to facilitate clinical assessment and further our understanding of the disease.

Normative Data for Retinal-Layer Thickness Maps Generated by Spectral-Domain OCT in a White Population

PURPOSE

(1) To collect a dataset of normative Early Treatment Diabetic Retinopathy Study (ETDRS) thickness map values for single retinal layers automatically segmented by Spectralis (Heidelberg Engineering, Heidelberg, Germany) spectral-domain OCT (SD-OCT) in a healthy white population. (2) To test the effect of age, sex, and axial length (AXL) on such values.

DESIGN

Cross-sectional study.

SUBJECTS

Healthy adult emmetropic white subjects with no history of ongoing or past conditions known to affect retinal anatomy.

METHODS

SD-OCT scans (30 × 25-degree volume) centered on the fovea were collected. Retinal-layer automatic segmentation was performed. Mean thickness values of 9 ETDRS sectors were calculated for each layer in 1 eye from each subject. The effect of age, sex, and AXL on the thickness of the central subfield, inner ring (IR), and outer ring (OR) of the ETDRS grid was tested. Scans were performed twice on a subset of patients to assess the repeatability of measurements.

MAIN OUTCOME MEASURES

Retinal-layer thickness.

RESULTS

Two hundred eyes from 200 subjects (110 females, mean age 39.9±13.9 years [range 20-74 years]) were used for this study. The mean AXL was 24.30±1.07 mm (range 22.23-27.14 mm). Full retinal thickness was higher in males regardless of the subfield (all P < 0.05). Ganglion cell layer thickness correlated positively with AXL in the C (P = 0.02) but negatively in the OR (P = 0.0001). The inner plexiform layer was thicker in males in the IR (P = 0.01) and thinner in longer eyes in the OR (P = 0.002). The inner nuclear layer was thicker in males in the C and the IR (P = 0.002 and P = 0.0009, respectively). The outer plexiform layer thickness did not change with age and gender but correlated positively with AXL in the C (P = 0.009). Males had thicker outer nuclear layers in all subfields (all P < 0.05). The thickness of the nerve fiber layer and retinal pigment epithelium was not affected by the studied variables in any subfield. The intraclass correlation coefficient ranged from 0.872 for the outer plexiform layer to 0.990 for the retinal nerve fiber layer and the ganglion cell layer.

CONCLUSIONS

The thickness values of each retinal layer in a large white population are provided. The thickness of retinal layers is influenced by gender, sex, and AXL, with a variable extent depending on the analyzed ETDRS map ring.

Signal reduction in choriocapillaris and segmentation errors in spectral domain OCT angiography caused by soft drusen

PURPOSE

To analyze signal reduction in choriocapillaris (CC) and segmentation errors in spectral domain optical coherence tomography angiography (OCT-A) caused by soft drusen due to age-related macular degeneration (AMD).

METHODS

Twenty-four eyes of 24 patients underwent multimodal retinal imaging including central 3 × 3mm² OCT-A (AngioVue, Optovue). Three drusen per study eye were randomly chosen and evaluated regarding drusen height, diameter, and accuracy of OCT-A layer segmentation in lesion proximity. Structural en-face OCT CC images were graded qualitatively and quantitatively regarding signal loss underneath the individual drusen area. Those drusen that showed no distinct signal loss in structural en-face OCT CC images were further evaluated in OCT-A. CC decorrelation signal index was measured within a 30-μm OCT-A CC slab in the exact area of drusen affection. Data were compared to healthy age-matched control subjects. Accuracy of layer segmentation, OCT CC data, and OCT-A CC data were correlated to morphological drusen parameters.

RESULTS

Mean drusen height and diameter were 91.57 ± 19.5μm and 315.17 ± 116.7μm. OCT-A layer segmentation of the inner plexiform layer (IPL) was disturbed by more than 50 μm in proximity to 26 drusen (36.1%). In these patients, drusen height was significantly higher compared to those with accurate IPL segmentation (p = 0.0126). Sixty-six out of 72 drusen (91.7%) caused a distinct signal loss in the structural en-face OCT CC image. Drusen height and drusen diameter were significantly higher in this group compared to the six drusen with a sufficient signal (p = 0.0276, p = 0.0025). CC decorrelation signal index measured in the area of these six drusen without OCT signal loss (8.3%) was reduced compared to age-matched healthy controls (73.6 vs. 100.1; p = 0.001).

CONCLUSIONS

Signal attenuation in CC slabs and segmentation errors of the IPL depend on drusen morphology. Both are frequent artifacts in OCT-A imaging in patients with soft drusen and must be considered during image analysis.

CuBe: parametric modeling of 3D foveal shape using cubic Bézier

Optical coherence tomography (OCT) allows three-dimensional (3D) imaging of the retina, and is commonly used for assessing pathological changes of fovea and macula in many diseases. Many neuroinflammatory conditions are known to cause modifications to the fovea shape. In this paper, we propose a method for parametric modeling of the foveal shape. Our method exploits invariant features of the macula from OCT data and applies a cubic Bézier polynomial along with a least square optimization to produce a best fit parametric model of the fovea. Additionally, we provide several parameters of the foveal shape based on the proposed 3D parametric modeling. Our quantitative and visual results show that the proposed model is not only able to reconstruct important features from the foveal shape, but also produces less error compared to the state-of-the-art methods. Finally, we apply the model in a comparison of healthy control eyes and eyes from patients with neuroinflammatory central nervous system disorders and optic neuritis, and show that several derived model parameters show significant differences between the two groups.

The Edge Detectors Suitable for Retinal OCT Image Segmentation

Retinal layer thickness measurement offers important information for reliable diagnosis of retinal diseases and for the evaluation of disease development and medical treatment responses. This task critically depends on the accurate edge detection of the retinal layers in OCT images. Here, we intended to search for the most suitable edge detectors for the retinal OCT image segmentation task. The three most promising edge detection algorithms were identified in the related literature: Canny edge detector, the two-pass method, and the EdgeFlow technique. The quantitative evaluation results show that the two-pass method outperforms consistently the Canny detector and the EdgeFlow technique in delineating the retinal layer boundaries in the OCT images. In addition, the mean localization deviation metrics show that the two-pass method caused the smallest edge shifting problem. These findings suggest that the two-pass method is the best among the three algorithms for detecting retinal layer boundaries. The overall better performance of Canny and two-pass methods over EdgeFlow technique implies that the OCT images contain more intensity gradient information than texture changes along the retinal layer boundaries. The results will guide our future efforts in the quantitative analysis of retinal OCT images for the effective use of OCT technologies in the field of ophthalmology.

Joint Segmentation of Retinal Layers and Focal Lesions in 3-D OCT Data of Topologically Disrupted Retinas

Accurate quantification of retinal structures in 3-D optical coherence tomography data of eyes with pathologies provides clinically relevant information. We present an approach to jointly segment retinal layers and lesions in eyes with topology-disrupting retinal diseases by a loosely coupled level set framework. In the new approach, lesions are modeled as an additional space-variant layer delineated by auxiliary interfaces. Furthermore, the segmentation of interfaces is steered by local differences in the signal between adjacent retinal layers, thereby allowing the approach to handle local intensity variations. The accuracy of the proposed method of both layer and lesion segmentation has been evaluated on eyes affected by central serous retinopathy and age-related macular degeneration. In addition, layer segmentation of the proposed approach was evaluated on eyes without topology-disrupting retinal diseases. Good agreement between the segmentation performed manually by a medical doctor and results obtained from the automatic segmentation was found for all data types. The mean unsigned error for all interfaces varied between 2.3 and 11.9 μm (0.6-3.1 pixels). Furthermore, lesion segmentation showed a Dice coefficient of 0.68 for drusen and 0.89 for fluid pockets. Overall, the method provides a flexible and accurate solution to jointly segment lesions and retinal layers.

The measurement repeatability using different partition methods of intraretinal tomographic thickness maps in healthy human subjects

Purpose

To determine the repeatability and profiles with different partition methods in intraretinal thickness layers in healthy human subjects, using optical coherence tomography (OCT).

Methods

A custom-built ultrahigh-resolution OCT was used to acquire three-dimensional volume of the macula in 20 healthy subjects. The dataset was acquired twice using the macular cube 512×128 protocol in an area of 6×6 mm² centered on the fovea. Commercially available segmentation software (Orion™) was used to segment the dataset into thickness maps of six intraretinal layers. The coefficient of repeatability and intraclass coefficient of correlation (ICC) were analyzed using hemispheric zoning and sectors defined by the Early Treatment Diabetic Retinopathy Study (ETDRS).

Results

All datasets were successfully segmented to create six thickness maps of individual intraretinal layers. Coefficients of repeatabilities of these layers in hemispheric zones ranged from 0.9 to 6.6 µm, with an average of 3.6 µm (standard deviation [SD] 1.4), which was not significantly different compared to ETDRS sectors (P>0.05). ICCs of these layers in hemispheric zones ranged from 0.68 to 0.99, with an average of 0.91 (SD 0.07). There were no significant differences in ICCs between two zoning methods (P>0.05). Significant variations of tomographic intraretinal thicknesses were found between the inner and outer annuli and among the quadrantal sectors within the inner and outer annuli (P<0.05). Significant variations of the quadrantal sectors including both inner and outer annuli were evident in intraretinal layers (P<0.05) except for the outer plexiform layer.

Conclusion

The measurement repeatabilities of tomographic thicknesses of intraretinal layers are comparable using both hemispheric and ETDRS partitions in volumetric data combined with the commercially available segmentation software. In keeping with known, normal anatomical variation, significant differences in tomographic thickness in various intraretinal layers were apparent in both hemispheric and ETDRS sectors.

Retinal status analysis method based on feature extraction and quantitative grading in OCT images

Background

Optical coherence tomography (OCT) is widely used in ophthalmology for viewing the morphology of the retina, which is important for disease detection and assessing therapeutic effect. The diagnosis of retinal diseases is based primarily on the subjective analysis of OCT images by trained ophthalmologists. This paper describes an OCT images automatic analysis method for computer-aided disease diagnosis and it is a critical part of the eye fundus diagnosis.

Methods

This study analyzed 300 OCT images acquired by Optovue Avanti RTVue XR (Optovue Corp., Fremont, CA). Firstly, the normal retinal reference model based on retinal boundaries was presented. Subsequently, two kinds of quantitative methods based on geometric features and morphological features were proposed. This paper put forward a retinal abnormal grading decision-making method which was used in actual analysis and evaluation of multiple OCT images.

Results

This paper showed detailed analysis process by four retinal OCT images with different abnormal degrees. The final grading results verified that the analysis method can distinguish abnormal severity and lesion regions. This paper presented the simulation of the 150 test images, where the results of analysis of retinal status showed that the sensitivity was 0.94 and specificity was 0.92.The proposed method can speed up diagnostic process and objectively evaluate the retinal status.

Conclusions

This paper aims on studies of retinal status automatic analysis method based on feature extraction and quantitative grading in OCT images. The proposed method can obtain the parameters and the features that are associated with retinal morphology. Quantitative analysis and evaluation of these features are combined with reference model which can realize the target image abnormal judgment and provide a reference for disease diagnosis.