ReLayer: a Free, Online Tool for Extracting Retinal Thickness From Cross-Platform OCT Images

En Face and Volumetric Comparison of Hypertransmission Defects Evaluated by Cirrus and Spectralis Optical Coherence Tomography

PURPOSE

To evaluate and compare en face and 3-dimensional (3-D) properties of hypertransmission defects (HTDs) between different optical coherence tomography (OCT) devices using OCT volumes and reconstructed en face images.

SETTINGS

Comparative diagnostic evaluation study.

METHODS

Thirty eyes with dry age-related macular degeneration (AMD) that underwent dense OCT macular volume scans with both the Spectralis (97 B-scans/volume; 2910 B-scans in total) and Cirrus OCT (128 B-scans/volume; 3840 B-scans in total) from the Amish Eye Study cohort were included in this analysis. HTD regions were labeled on each B-scan and reconstructed into en face and 3-D volume images. Properties of HTD volume were compared between the 2 devices.

RESULTS

The qualitative score of en face images for HTD was higher for the Cirrus compared to the Spectralis (P < .01). The quality of Spectralis en face images improved after preprocessing and reconstruction. The 2-D HTD area on en face obtained from 2-D projections of 3-D volume did not differ between devices (P = .478, ICC = 0.998; Jaccard index 0.721 ± 0.086). There was no difference in the number, volume, PALs, and surface areas of HTDs between devices in the volumetric analysis (all P ≥ .090). The signal intensity of HTD normalized by the mean choroidal signal intensity did not differ between devices (P = .861).

CONCLUSIONS

The visualization of HTD on en face images from Spectralis OCT could be enhanced through image processing. The equivalence in 3-D HTD parameters between the 2 devices suggests interchangeability for assessing these lesions in AMD.

Prediction of Long-Term Treatment Outcomes for Diabetic Macular Edema Using a Generative Adversarial Network

Purpose

The purpose of this study was to analyze optical coherence tomography (OCT) images of generative adversarial networks (GANs) for the prediction of diabetic macular edema after long-term treatment.

Methods

Diabetic macular edema (DME) eyes (n = 327) underwent anti-vascular endothelial growth factor (VEGF) treatments every 4 weeks for 52 weeks from a randomized controlled trial (CRTH258B2305, KINGFISHER) were included. OCT B-scan images through the foveal center at weeks 0, 4, 12, and 52, fundus photography, and retinal thickness (RT) maps were collected. GAN models were trained to generate probable OCT images after treatment. Input for each model were comprised of either the baseline B-scan alone or combined with additional OCT, thickness map, or fundus images. Generated OCT B-scan images were compared with real week 52 images.

Results

For 30 test images, 28, 29, 15, and 30 gradable OCT images were generated by CycleGAN, UNIT, Pix2PixHD, and RegGAN, respectively. In comparison with the real week 52, these GAN models showed positive predictive value (PPV), sensitivity, specificity, and kappa for residual fluid ranging from 0.500 to 0.889, 0.455 to 1.000, 0.357 to 0.857, and 0.537 to 0.929, respectively. For hard exudate (HE), they were ranging from 0.500 to 1.000, 0.545 to 0.900, 0.600 to 1.000, and 0.642 to 0.894, respectively. Models trained with week 4 and 12 B-scans as additional inputs to the baseline B-scan showed improved performance.

Conclusions

GAN models could predict residual fluid and HE after long-term anti-VEGF treatment of DME.

Translational Relevance

The implementation of this tool may help identify potential nonresponders after long-term treatment, thereby facilitating management planning for these eyes.

Automated quantification of uveitic keratic precipitates by use of anterior segment optical coherence tomography

BACKGROUND

Evaluation of ocular inflammation via common imaging modalities like optical coherence tomography (OCT) has emphasised cell visualisation, but automated detection of uveitic keratic precipitates (KPs) remains unexplored.

METHODS

Anterior segment (AS)-OCT dense volumes of the corneas of patients with uveitic KPs were collected at three timepoints: with active (T0), clinically improving (T1), and resolved (T2) inflammation. At each visit, visual acuity and clinical grading of the anterior chamber cells were assessed. A bespoke algorithm was used to create an en face rendering of the KPs and to calculate their volume and a ratio of the volume of precipitates over the analysed area. The variation of AS-OCT-derived measurements over time was assessed, and compared with clinical grading.

RESULTS

Twenty eyes from 20 patients (13 females, mean age 39 years) were studied. At T0, the mean volume of the corneal KPs was 0.1727 mm3 , and it significantly reduced to 0.1111 mm3 (p = 0.03) only at T2. The ratio between the volume of the KPs and the corneal area decreased from T0 (0.007) to T1 (0.006; p = 0.2) and T2 (0.004; p = 0.009). There was a statistically significant correlation between the AC cell count and the AS-OCT volume measurements of the KPs at the three time points.

CONCLUSIONS

AS-OCT can image uveitic KPs and through a bespoke algorithm we were able to create an en face rendering allowing us to extrapolate their volume. We found that objective quantification of KPs correlated with inflammatory cell counts in the anterior chamber.

OCT Assisted Quantification of Vitreous Inflammation in Uveitis

Purpose

Vitreous haze (VH) is a key marker of inflammation in uveitis but limited by its subjectivity. Optical coherence tomography (OCT) has potential as an objective, noninvasive method for quantifying VH. We test the hypotheses that OCT can reliably quantify VH and the measurement is associated with slit-lamp based grading of VH.

Methods

In this prospective study, participants underwent three repeated OCT macular scans to evaluate the within-eye reliability of the OCT vitreous intensity (VI). Association between OCT VI and clinical findings (including VH grade, phakic status, visual acuity [VA], anterior chamber cells, and macular thickness) were assessed.

Results

One hundred nineteen participants were included (41 healthy participants, 32 patients with uveitis without VH, and 46 patients with uveitis with VH). Within-eye test reliability of OCT VI was high in healthy eyes and in all grades of VH (intraclass correlation coefficient [ICC] > 0.79). Average OCT VI was significantly different between healthy eyes and uveitic eyes without and uveitic eyes with VH, and was associated with increasing clinical VH grade (P < 0.05). OCT VI was significantly associated with VA, whereas clinical VH grading was not. Cataract was also associated with higher OCT VI (P = 0.03).

Conclusions

OCT VI is a fast, noninvasive, objective, and automated method for measuring vitreous inflammation. It is associated with clinician grading of vitreous inflammation and VA, however, it can be affected by media opacities.

Translational Relevance

OCT imaging for quantifying vitreous inflammation shows high within-eye repeatability and is associated with clinical grading of vitreous haze. OCT measurements are also associated with visual acuity but may be affected by structures anterior to the acquisition window, such as lens opacity and other anterior segment changes.

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.

A novel quantitative analysis method for idiopathic epiretinal membrane

PURPOSE

To introduce a novel method to quantitively analyse in three dimensions traction forces in a vast area of the ocular posterior pole.

METHODS

Retrospective analysis of 14 eyes who underwent peeling surgery for idiopathic, symptomatic and progressive epiretinal membrane. The technique measures the shift in position of vascular crossings after surgery from a fixed point, which is the retinal pigmented epithelium. This shift is defined as the relaxation index (RI) and represents a measure of the postoperative movement of the retina due to released traction after surgery.

RESULTS

Best-corrected visual acuity was significantly better than baseline at all follow ups while the RI had its maximum value at baseline. Moreover, we found a significant correlation between best-corrected visual acuity at 6 months and RI at baseline.

CONCLUSION

While all previous published methods focused on bi-dimensional changes observed in a small region, this study introduces a three-dimensional assessment of tractional forces. Future integration of RI into built-in processing software will allow systematic three-dimensional measurement of intraretinal traction.

Kim P, Kim J. Retinal Healthcare Diagnosis Approaches with Deep Learning Techniques

The retina is an important organ of the human body, with a crucial function in the vision mechanism. A minor disturbance in the retina can cause various abnormalities in the eye, as well as complex retinal diseases such as diabetic retinopathy. To diagnose such diseases in early stages, many researchers are incorporating machine learning (ML) technique. The combination of medical science with ML improves the healthcare diagnosis systems of hospitals, clinics, and other providers. Recently, AI-based healthcare diagnosis systems assist clinicians in handling more patients in less time and improves diagnosis accuracy. In this paper, we review cutting-edge AI-based retinal diagnosis technologies. This article also briefly describes the potential of the latest densely connected convolutional networks (DenseNets) to improve the performance of diagnosis systems. Moreover, this paper focuses on state-of-the-art results from comprehensive investigations in retinal diagnosis and the development of AI-based retinal healthcare diagnosis approaches with deep-learning models.

Structure-Function Analysis in Macular Drusen With Mesopic and Scotopic Microperimetry

Purpose

To investigate the structure–function relationship in eyes with drusen with mesopic and scotopic microperimetry.

Methods

We analyzed structural and functional data from 43 eyes with drusen. Functional data were acquired with mesopic and scotopic two-color (red and cyan) microperimetry. Normative values were calculated using data from 56 healthy eyes. Structural measurements were green autofluorescence and dense macular optical coherence tomography scans. The latter were used to calculate the retinal pigment epithelium elevation (RPE-E) and the photoreceptor reflectivity ratio (PRR). The pointwise structure–function relationship was measured with linear mixed models having the log-transformed structural parameters as predictors and the sensitivity loss (SL, deviation from normal) as the response variable.

Results

In the univariable analysis, the structural predictors were all significantly correlated (P < 0.05) with the SL in the mesopic and scotopic tests. In a multivariable model, mesopic microperimetry yielded the best structure–function relationship. All predictors were significant (P < 0.05), but the predictive power was weak (best R² = 0.09). The relationship was improved when analyzing locations with abnormal RPE-E (best R² = 0.18).

Conclusions

Mesopic microperimetry shows better structure–function relationship compared to scotopic microperimetry; the relationship is weak, likely due to the early functional damage and the small number of tested locations affected by drusen. The relationship is stronger when locations with drusen are isolated for the mesopic and scotopic cyan test.

Translational Relevance

These results could be useful to devise integrated structure–function methods to detect disease progression in intermediate age-related macular degeneration.

A recommended "minimum data set" framework for SD-OCT retinal image acquisition and analysis from the Atlas of Retinal Imaging in Alzheimer's Study (ARIAS)

INTRODUCTION

We propose a minimum data set framework for the acquisition and analysis of retinal images for the development of retinal Alzheimer's disease (AD) biomarkers. Our goal is to describe methodology that will increase concordance across laboratories, so that the broader research community is able to cross-validate findings in parallel, accumulate large databases with normative data across the cognitive aging spectrum, and progress the application of this technology from the discovery stage to the validation stage in the search for sensitive and specific retinal biomarkers in AD.

METHODS

The proposed minimum data set framework is based on the Atlas of Retinal Imaging Study (ARIAS), an ongoing, longitudinal, multi-site observational cohort study. However, the ARIAS protocol has been edited and refined with the expertise of all co-authors, representing 16 institutions, and research groups from three countries, as a first step to address a pressing need identified by experts in neuroscience, neurology, optometry, and ophthalmology at the Retinal Imaging in Alzheimer's Disease (RIAD) conference, convened by the Alzheimer's Association and held in Washington, DC, in May 2019.

RESULTS

Our framework delineates specific imaging protocols and methods of analysis for imaging structural changes in retinal neuronal layers, with optional add-on procedures of fundus autofluorescence to examine beta-amyloid accumulation and optical coherence tomography angiography to examine AD-related changes in the retinal vasculature.

DISCUSSION

This minimum data set represents a first step toward the standardization of retinal imaging data acquisition and analysis in cognitive aging and AD. A standardized approach is essential to move from discovery to validation, and to examine which retinal AD biomarkers may be more sensitive and specific for the different stages of the disease severity spectrum. This approach has worked for other biomarkers in the AD field, such as magnetic resonance imaging; amyloid positron emission tomography; and, more recently, blood proteomics. Potential context of use for retinal AD biomarkers is discussed.

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.

Microvasculature Segmentation and Intercapillary Area Quantification of the Deep Vascular Complex Using Transfer Learning

Purpose

Optical coherence tomography angiography (OCT-A) permits visualization of the changes to the retinal circulation due to diabetic retinopathy (DR), a microvascular complication of diabetes. We demonstrate accurate segmentation of the vascular morphology for the superficial capillary plexus (SCP) and deep vascular complex (DVC) using a convolutional neural network (CNN) for quantitative analysis.

Methods

The main CNN training dataset consisted of retinal OCT-A with a 6 × 6-mm field of view (FOV), acquired using a Zeiss PlexElite. Multiple-volume acquisition and averaging enhanced the vasculature contrast used for constructing the ground truth for neural network training. We used transfer learning from a CNN trained on smaller FOVs of the SCP acquired using different OCT instruments. Quantitative analysis of perfusion was performed on the resulting automated vasculature segmentations in representative patients with DR.

Results

The automated segmentations of the OCT-A images maintained the distinct morphologies of the SCP and DVC. The network segmented the SCP with an accuracy and Dice index of 0.8599 and 0.8618, respectively, and 0.7986 and 0.8139, respectively, for the DVC. The inter-rater comparisons for the SCP had an accuracy and Dice index of 0.8300 and 0.6700, respectively, and 0.6874 and 0.7416, respectively, for the DVC.

Conclusions

Transfer learning reduces the amount of manually annotated images required while producing high-quality automatic segmentations of the SCP and DVC that exceed inter-rater comparisons. The resulting intercapillary area quantification provides a tool for in-depth clinical analysis of retinal perfusion.

Translational Relevance

Accurate retinal microvasculature segmentation with the CNN results in improved perfusion analysis in diabetic retinopathy.

Automatic Identification and Representation of the Cornea-Contact Lens Relationship Using AS-OCT Images

The clinical study of the cornea-contact lens relationship is widely used in the process of adaptation of the scleral contact lens (SCL) to the ocular morphology of patients. In that sense, the measurement of the adjustment between the SCL and the cornea can be used to study the comfort or potential damage that the lens may produce in the eye. The current analysis procedure implies the manual inspection of optical coherence tomography of the anterior segment images (AS-OCT) by the clinical experts. This process presents several limitations such as the inability to obtain complex metrics, the inaccuracies of the manual measurements or the requirement of a time-consuming process by the expert in a tedious process, among others. This work proposes a fully-automatic methodology for the extraction of the areas of interest in the study of the cornea-contact lens relationship and the measurement of representative metrics that allow the clinicians to measure quantitatively the adjustment between the lens and the eye. In particular, three distance metrics are herein proposed: Vertical, normal to the tangent of the region of interest and by the nearest point. Moreover, the images are classified to characterize the analysis as belonging to the central cornea, peripheral cornea, limbus or sclera (regions where the inner layer of the lens has already joined the cornea). Finally, the methodology graphically presents the results of the identified segmentations using an intuitive visualization that facilitates the analysis and diagnosis of the patients by the clinical experts.