A view of the current and future role of optical coherence tomography in the management of age-related macular degeneration

Contactless optical coherence tomography of the eyes of freestanding individuals with a robotic scanner

Clinical systems for optical coherence tomography (OCT) are used routinely to diagnose and monitor patients with a range of ocular diseases. They are large tabletop instruments operated by trained staff, and require mechanical stabilization of the head of the patient for positioning and motion reduction. Here we report the development and performance of a robot-mounted OCT scanner for the autonomous contactless imaging, at safe distances, of the eyes of freestanding individuals without the need for operator intervention or head stabilization. The scanner uses robotic positioning to align itself with the eye to be imaged, as well as optical active scanning to locate the pupil and to attenuate physiological eye motion. We show that the scanner enables the acquisition of OCT volumetric datasets, comparable in quality to those of clinical tabletop systems, that resolve key anatomic structures relevant for the management of common eye conditions. Robotic OCT scanners may enable the diagnosis and monitoring of patients with eye conditions in non-specialist clinics.

Automated Quantification of Pathological Fluids in Neovascular Age-Related Macular Degeneration, and Its Repeatability Using Deep Learning

Purpose

To develop a reliable algorithm for the automated identification, localization, and volume measurement of exudative manifestations in neovascular age-related macular degeneration (nAMD), including intraretinal (IRF), subretinal fluid (SRF), and pigment epithelium detachment (PED), using a deep-learning approach.

Methods

One hundred seven spectral domain optical coherence tomography (OCT) cube volumes were extracted from nAMD eyes. Manual annotation of IRF, SRF, and PED was performed. Ninety-two OCT volumes served as training and validation set, and 15 OCT volumes from different patients as test set. The performance of our fluid segmentation method was quantified by means of pixel-wise metrics and volume correlations and compared to other methods. Repeatability was tested on 42 other eyes with five OCT volume scans acquired on the same day.

Results

The fully automated algorithm achieved good performance for the detection of IRF, SRF, and PED. The area under the curve for detection, sensitivity, and specificity was 0.97, 0.95, and 0.99, respectively. The correlation coefficients for the fluid volumes were 0.99, 0.99, and 0.91, respectively. The Dice score was 0.73, 0.67, and 0.82, respectively. For the largest volume quartiles the Dice scores were >0.90. Including retinal layer segmentation contributed positively to the performance. The repeatability of volume prediction showed a standard deviations of 4.0 nL, 3.5 nL, and 20.0 nL for IRF, SRF, and PED, respectively.

Conclusions

The deep-learning algorithm can simultaneously acquire a high level of performance for the identification and volume measurements of IRF, SRF, and PED in nAMD, providing accurate and repeatable predictions. Including layer segmentation during training and squeeze-excite block in the network architecture were shown to boost the performance.

Translational Relevance

Potential applications include measurements of specific fluid compartments with high reproducibility, assistance in treatment decisions, and the diagnostic or scientific evaluation of relevant subgroups.

AI-based monitoring of retinal fluid in disease activity and under therapy

Retinal fluid as the major biomarker in exudative macular disease is accurately visualized by high-resolution three-dimensional optical coherence tomography (OCT), which is used world-wide as a diagnostic gold standard largely replacing clinical examination. Artificial intelligence (AI) with its capability to objectively identify, localize and quantify fluid introduces fully automated tools into OCT imaging for personalized disease management. Deep learning performance has already proven superior to human experts, including physicians and certified readers, in terms of accuracy and speed. Reproducible measurement of retinal fluid relies on precise AI-based segmentation methods that assign a label to each OCT voxel denoting its fluid type such as intraretinal fluid (IRF) and subretinal fluid (SRF) or pigment epithelial detachment (PED) and its location within the central 1-, 3- and 6-mm macular area. Such reliable analysis is most relevant to reflect differences in pathophysiological mechanisms and impacts on retinal function, and the dynamics of fluid resolution during therapy with different regimens and substances. Yet, an in-depth understanding of the mode of action of supervised and unsupervised learning, the functionality of a convolutional neural net (CNN) and various network architectures is needed. Greater insight regarding adequate methods for performance, validation assessment, and device- and scanning-pattern-dependent variations is necessary to empower ophthalmologists to become qualified AI users. Fluid/function correlation can lead to a better definition of valid fluid variables relevant for optimal outcomes on an individual and a population level. AI-based fluid analysis opens the way for precision medicine in real-world practice of the leading retinal diseases of modern times.

Quantification of Key Retinal Features in Early and Late Age-Related Macular Degeneration Using Deep Learning

PURPOSE

We sought to develop and validate a deep learning model for segmentation of 13 features associated with neovascular and atrophic age-related macular degeneration (AMD).

DESIGN

Development and validation of a deep-learning model for feature segmentation.

METHODS

Data for model development were obtained from 307 optical coherence tomography volumes. Eight experienced graders manually delineated all abnormalities in 2712 B-scans. A deep neural network was trained with these data to perform voxel-level segmentation of the 13 most common abnormalities (features). For evaluation, 112 B-scans from 112 patients with a diagnosis of neovascular AMD were annotated by 4 independent observers. The main outcome measures were Dice score, intraclass correlation coefficient, and free-response receiver operating characteristic curve.

RESULTS

On 11 of 13 features, the model obtained a mean Dice score of 0.63 ± 0.15, compared with 0.61 ± 0.17 for the observers. The mean intraclass correlation coefficient for the model was 0.66 ± 0.22, compared with 0.62 ± 0.21 for the observers. Two features were not evaluated quantitatively because of a lack of data. Free-response receiver operating characteristic analysis demonstrated that the model scored similar or higher sensitivity per false positives compared with the observers.

CONCLUSIONS

The quality of the automatic segmentation matches that of experienced graders for most features, exceeding human performance for some features. The quantified parameters provided by the model can be used in the current clinical routine and open possibilities for further research into treatment response outside clinical trials.

The role of future treatments in the management of neovascular age-related macular degeneration in Europe

Anti-vascular endothelial growth factor (VEGF) agents have transformed the management of patients with neovascular age-related macular degeneration (nAMD) over the past two decades. However, as more long-term real-world data become available, it is clear that treatment outcomes are inferior to those reported in large, controlled clinical trials. This is largely driven by undertreatment, that is, not maintaining a consistent injection frequency to achieve sustained VEGF suppression, whether due to patient non-compliance, an important injection burden, or non/incomplete anatomical response. Newer therapeutic advances under evaluation hold promise in achieving more, for less. We review the latest drugs currently in or having successfully finished phase III clinical trials, and determine their potential place in the management of patients with nAMD in Europe.

CURRENT CONCEPTS AND MODALITIES FOR MONITORING THE FELLOW EYE IN NEOVASCULAR AGE-RELATED MACULAR DEGENERATION: An Expert Panel Consensus

Neovascular age-related macular degeneration in one eye is a major risk factor for developing neovascular age-related macular degeneration in the fellow eye; effective monitoring is therefore critical. This review summarizes existing and developing methods to monitor the fellow eye of patients with unilateral neovascular age-related macular degeneration and provides guidance for patients and clinicians.

The presence of neovascular age-related macular degeneration (nAMD) in one eye is a major risk factor for the development of disease in the fellow eye. Several methods exist to help physicians monitor the fellow eye, with new technologies becoming increasingly available.

Fluid as a critical biomarker in neovascular age-related macular degeneration management: literature review and consensus recommendations

Current guidelines on the management of patients with neovascular age-related macular degeneration (nAMD) lack clear recommendations on the interpretation of fluid as seen on optical coherence tomography (OCT) imaging and the incorporation of this information into an ongoing disease treatment strategy. Our objective was to review current guidelines and scientific evidence on the role of fluid as a biomarker in the management of nAMD, and develop a clinically oriented, practical algorithm for diagnosis and management based on a consensus of expert European retinal specialists. PubMed was searched for articles published since 2006 relating to the role of fluid in nAMD. A total of 654 publications were screened for relevance and 66 publications were included for review. Of these, 14 were treatment guidelines, consensus statements and systematic reviews or meta-analyses, in which OCT was consistently recommended as an important tool in the initial diagnosis and ongoing management of nAMD. However, few guidelines distinguished between types of fluid when providing recommendations. A total of 52 publications reported primary evidence from clinical trials, studies, and chart reviews. Observations from these were sometimes inconsistent, but trends were observed with regard to features reported as being predictive of visual outcomes. Based on these findings, diagnostic recommendations and a treatment algorithm based on a treat-and-extend (T&E) regimen were developed. These provide guidance on the diagnosis of nAMD as well as a simple treatment pathway based on the T&E regimen, with treatment decisions made according to the observations of fluid as a critical biomarker for disease activity.

New optical coherence tomography grading system for macula-off rhegmatogenous retinal detachment: how off is off?

Background/Aims

The classification of retinal detachment is currently still based on many objective criteria such as duration of symptoms and funduscopic macular status, which leaves some important questions unanswered. The most important factor is the macular status, which is determined using direct or indirect ophthalmoscopy. Optical coherence tomography (OCT) has become a standard tool in clinical practice and enables detecting the exact extent of subretinal fluid in macula-off/on retinal detachment. We introduce a new and simple OCT-based grading system for macular detachment to provide a basis for further investigations to determine the optimal timing for surgery.

Methods

We retrospectively included 155 patients who were treated for retinal detachment. We defined the extent of the macular detachment in six stages based on the Early Treatment Diabetic Retinopathy Study (ETDRS) grid of the OCT scan.

The outermost ring of the ETDRS grid was defined as zone 1, the middle ring as zone 2 and the inner ring as zone 3. Only zone 3 differed in the retinal detachment height grades (grade a <250 µm vs grade b >250 µm). Retinal detachment heights that could not be measured were considered grade 4 (ungradable) detachments.

Results

Forty-seven patients had no macular involvement (grade 0). Regarding macular detachment, 14 patients had grade 1, 20 had grade 2, 9 had grade 3a, 29 had grade 3b and 36 had grade 4.

Conclusion

The newly developed OCT grading system for macular involvement following retinal detachment is a crucial tool to objectively classify a retinal detachment in order to be able to make better statements in the future, like for defining the optimal time for surgical intervention. A secondary benefit of this grading system would be that it improves predicting postoperative visual acuity.

Reliability of Retinal Pathology Quantification in Age-Related Macular Degeneration: Implications for Clinical Trials and Machine Learning Applications

Purpose

To investigate the interreader agreement for grading of retinal alterations in age-related macular degeneration (AMD) using a reading center setting.

Methods

In this cross-sectional case series, spectral-domain optical coherence tomography (OCT; Topcon 3D OCT, Tokyo, Japan) scans of 112 eyes of 112 patients with neovascular AMD (56 treatment naive, 56 after three anti-vascular endothelial growth factor injections) were analyzed by four independent readers. Imaging features specific for AMD were annotated using a novel custom-built annotation platform. Dice score, Bland-Altman plots, coefficients of repeatability, coefficients of variation, and intraclass correlation coefficients were assessed.

Results

Loss of ellipsoid zone, pigment epithelium detachment, subretinal fluid, and drusen were the most abundant features in our cohort. Subretinal fluid, intraretinal fluid, hypertransmission, descent of the outer plexiform layer, and pigment epithelium detachment showed highest interreader agreement, while detection and measures of loss of ellipsoid zone and retinal pigment epithelium were more variable. The agreement on the size and location of the respective annotation was more consistent throughout all features.

Conclusions

The interreader agreement depended on the respective OCT-based feature. A selection of reliable features might provide suitable surrogate markers for disease progression and possible treatment effects focusing on different disease stages.

Translational Relevance

This might give opportunities for a more time- and cost-effective patient assessment and improved decision making as well as have implications for clinical trials and training machine learning algorithms.

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.

Retinal Specialist versus Artificial Intelligence Detection of Retinal Fluid from OCT: Age-Related Eye Disease Study 2: 10-Year Follow-On Study

PURPOSE

To evaluate the performance of retinal specialists in detecting retinal fluid presence in spectral domain OCT (SD-OCT) scans from eyes with age-related macular degeneration (AMD) and compare performance with an artificial intelligence algorithm.

DESIGN

Prospective comparison of retinal fluid grades from human retinal specialists and the Notal OCT Analyzer (NOA) on SD-OCT scans from 2 common devices.

PARTICIPANTS

A total of 1127 eyes of 651 Age-Related Eye Disease Study 2 10-year Follow-On Study (AREDS2-10Y) participants with SD-OCT scans graded by reading center graders (as the ground truth).

METHODS

The AREDS2-10Y investigators graded each SD-OCT scan for the presence/absence of intraretinal and subretinal fluid. Separately, the same scans were graded by the NOA.

MAIN OUTCOME MEASURES

Accuracy (primary), sensitivity, specificity, precision, and F1-score.

RESULTS

Of the 1127 eyes, retinal fluid was present in 32.8%. For detecting retinal fluid, the investigators had an accuracy of 0.805 (95% confidence interval [CI], 0.780-0.828), a sensitivity of 0.468 (95% CI, 0.416-0.520), a specificity of 0.970 (95% CI, 0.955-0.981). The NOA metrics were 0.851 (95% CI, 0.829-0.871), 0.822 (95% CI, 0.779-0.859), 0.865 (95% CI, 0.839-0.889), respectively. For detecting intraretinal fluid, the investigator metrics were 0.815 (95% CI, 0.792-0.837), 0.403 (95% CI, 0.349-0.459), and 0.978 (95% CI, 0.966-0.987); the NOA metrics were 0.877 (95% CI, 0.857-0.896), 0.763 (95% CI, 0.713-0.808), and 0.922 (95% CI, 0.902-0.940), respectively. For detecting subretinal fluid, the investigator metrics were 0.946 (95% CI, 0.931-0.958), 0.583 (95% CI, 0.471-0.690), and 0.973 (95% CI, 0.962-0.982); the NOA metrics were 0.863 (95% CI, 0.842-0.882), 0.940 (95% CI, 0.867-0.980), and 0.857 (95% CI, 0.835-0.877), respectively.

CONCLUSIONS

In this large and challenging sample of SD-OCT scans obtained with 2 common devices, retinal specialists had imperfect accuracy and low sensitivity in detecting retinal fluid. This was particularly true for intraretinal fluid and difficult cases (with lower fluid volumes appearing on fewer B-scans). Artificial intelligence-based detection achieved a higher level of accuracy. This software tool could assist physicians in detecting retinal fluid, which is important for diagnostic, re-treatment, and prognostic tasks.

Subretinal Drusenoid Deposits and Photoreceptor Loss Detecting Global and Local Progression of Geographic Atrophy by SD-OCT Imaging

Purpose

To investigate the impact of subretinal drusenoid deposits (SDD) and photoreceptor integrity on global and local geographic atrophy (GA) progression.

Methods

Eighty-three eyes of 49 patients, aged 50 years and older with GA secondary to age-related macular degeneration (AMD), were prospectively included in this study. Participants underwent spectral-domain optical coherence tomography (SD-OCT) and fundus autofluorescence (FAF) imaging at baseline and after 12 months. The junctional zone and presence of SDD were delineated on SD-OCT and FAF images. Linear mixed models were calculated to investigate the association between GA progression and the junctional zone area, baseline GA area, age, global and local presence of SDD and unifocal versus multifocal lesions.

Results

The area of the junctional zone was significantly associated with the progression of GA, both globally and locally (all P < 0.001). SDD were associated with faster growth in the overall model (P = 0.039), as well as in the superior-temporal (P = 0.005) and temporal (P = 0.002) sections. Faster progression was associated with GA baseline area (P < 0.001). No difference was found between unifocal and multifocal lesions (P > 0.05). Age did not have an effect on GA progression (P > 0.05).

Conclusions

Photoreceptor integrity and SDD are useful for predicting global and local growth in GA. Investigation of the junctional zone is merited because this area is destined to become atrophic. Photoreceptor loss visible on SD-OCT might lead to new structural outcome measurements visible before irreversible loss of retinal pigment epithelium occurs.

Plexus-specific retinal vascular anatomy and pathologies as seen by projection-resolved optical coherence tomographic angiography

Optical coherence tomographic angiography (OCTA) is a novel technology capable of imaging retinal vasculature three-dimensionally at capillary scale without the need to inject any extrinsic dye contrast. However, projection artifacts cause superficial retinal vascular patterns to be duplicated in deeper layers, thus interfering with the clean visualization of some retinal plexuses and vascular pathologies. Projection-resolved OCTA (PR-OCTA) uses post-processing algorithms to reduce projection artifacts. With PR-OCTA, it is now possible to resolve up to 4 distinct retinal vascular plexuses in the living human eye. The technology also allows us to detect and distinguish between various retinal and optic nerve diseases. For example, optic nerve diseases such as glaucoma primarily reduces the capillary density in the superficial vascular complex, which comprises the nerve fiber layer plexus and the ganglion cell layer plexus. Outer retinal diseases such as retinitis pigmentosa primarily reduce the capillary density in the deep vascular complex, which comprises the intermediate capillary plexus and the deep capillary plexus. Retinal vascular diseases such as diabetic retinopathy and vein occlusion affect all plexuses, but with different patterns of capillary loss and vascular malformations. PR-OCTA is also useful in distinguishing various types of choroidal neovascularization and monitoring their response to anti-angiogenic medications. In retinal angiomatous proliferation and macular telangiectasia type 2, PR-OCTA can trace the pathologic vascular extension into deeper layers as the disease progress through stages. Plexus-specific visualization and measurement of retinal vascular changes are improving our ability to diagnose, stage, monitor, and assess treatment response in a wide variety of optic nerve and retinal diseases. These applications will be further enhanced with the continuing improvement of the speed and resolution of the OCT platforms, as well as the development of software algorithms to reduce artifacts, improve image quality, and make quantitative measurements.

Current Management of Age-Related Macular Degeneration

Age-related macular degeneration (AMD) remains a leading cause of blindness worldwide. The assessment and management of patients with this condition has evolved in the last decades. In this chapter, current standards for diagnosis, follow-up, and treatment of patients with AMD are reviewed and summarized. Namely, we highlight how current assessment has moved from conventional ophthalmoscopy and fluorescein angiography testing to a multimodal approach, and its important advantages. Alternatives to visual acuity for functional assessment of patients with AMD are also presented. Regarding strategies for follow-up and treatment, we provide specific information for the different stages (i.e., early, intermediate, and late) and forms (for example, choroidal neovascularization and geographic atrophy) of AMD. Specifically, we discuss the relevance and options for self-monitoring and non-pharmacological interventions. Additionally, a summary of the important trials (both on exudative and non-exudative AMD) that have helped inform clinical practice is provided, including data on antiangiogenic agents currently available, and outcomes of the different regimens that have been studied. The influence of advances in imaging on treatment strategies is also discussed.In summary, this chapter is a resource for all clinicians engaged in providing state of the art care for patients with AMD, and can help improve diagnosis, management, and outcomes of individuals with this blinding condition.

Association between central retinal thickness and low luminance visual acuity in early age-related macular degeneration

PURPOSE/AIM

To examine whether central retinal thickness (CRT) is related to mesopic visual acuity (VA) and low luminance deficit (LLD, difference between photopic and mesopic VA) in eyes with early and intermediate age-related macular degeneration (AMD).

MATERIALS AND METHODS

In a cross-sectional study, 50 pseudophakic subjects older than 63 years were divided into three groups (no AMD, early AMD and intermediate AMD). Spectral domain optical coherence tomography (SD-OCT) was used to measure CRT in the 1 mm-central-area. Best-corrected distance VA was measured under photopic or mesopic luminance conditions and LLD calculated. Subjects were stratified by VA impairment to compare CRTs across these groups. Relationships were examined by stepwise multiple linear regression.

RESULTS

No significant differences in mean CRT, photopic and mesopic VA or LLD were detected between the groups no AMD, early AMD and intermediate AMD. However, mean CRTs were 20 microns and 18 microns thicker in the eyes with impaired mesopic VA (> 0.3 logMAR) and impaired LLD (⩾ 0.3 logMAR) compared to the eyes with non-impaired VA or LLD respectively (both p < 0.01). CRT and mesopic pupil size were independent predictors of mesopic VA (p = 0.001). CRT emerged as the only independent predictor of LLD (p = 0.004).

CONCLUSIONS

Increased CRT was linked to worse retinal function when measured under mesopic conditions in eyes without AMD and eyes with early to intermediate AMD. SD-OCT imaging combined with VA measurements under low luminance conditions could be a useful tool to detect early AMD.

Pyruvate dehydrogenase kinase/lactate axis: a therapeutic target for neovascular age-related macular degeneration identified by metabolomics

Neovascular age-related macular degeneration (nAMD) is the leading cause of blindness in aging populations. Here, we applied metabolomics to human sera of patients with nAMD during an active (exudative) phase of the pathology and found higher lactate levels and a shift in the lipoprotein profile (increased VLDL-LDL/HDL ratio). Similar metabolomics changes were detected in the sera of mice subjected to laser-induced choroidal neovascularization (CNV). In this experimental model, we provide evidence for two sites of lactate production: first, a local one in the injured eye, and second a systemic site associated with the recruitment of bone marrow-derived inflammatory cells. Mechanistically, lactate promotes the angiogenic response and M2-like macrophage accumulation in the eyes. The therapeutic potential of our findings is demonstrated by the pharmacological control of lactate levels through pyruvate dehydrogenase kinase (PDK) inhibition by dichloroacetic acid (DCA). Mice treated with DCA exhibited normalized lactate levels and lipoprotein profiles, and inhibited CNV formation. Collectively, our findings implicate the key role of the PDK/lactate axis in AMD pathogenesis and reveal that the regulation of PDK activity has potential therapeutic value in this ocular disease. The results indicate that the lipoprotein profile is a traceable pattern that is worth considering for patient follow-up. KEY MESSAGES: Lactate and lipoprotein profile are associated with the active phase of AMD and CNV development. Lactate is a relevant and functional metabolite correlated with AMD progression. Modulating lactate through pyruvate dehydrogenase kinase led to a decrease of CNV progression. Pyruvate dehydrogenase kinase is a new therapeutic target for neovascular AMD.

Deep learning architectures analysis for age-related macular degeneration segmentation on optical coherence tomography scans

BACKGROUND AND OBJECTIVES

Aged people usually are more to be diagnosed with retinal diseases in developed countries. Retinal capillaries leakage into the retina swells and causes an acute vision loss, which is called age-related macular degeneration (AMD). The disease can not be adequately diagnosed solely using fundus images as depth information is not available. The variations in retina volume assist in monitoring ophthalmological abnormalities. Therefore, high-fidelity AMD segmentation in optical coherence tomography (OCT) imaging modality has raised the attention of researchers as well as those of the medical doctors. Many methods across the years encompassing machine learning approaches and convolutional neural networks (CNN) strategies have been proposed for object detection and image segmentation.

METHODS

In this paper, we analyze four wide-spread deep learning models designed for the segmentation of three retinal fluids outputting dense predictions in the RETOUCH challenge data. We aim to demonstrate how a patch-based approach could push the performance for each method. Besides, we also evaluate the methods using the OPTIMA challenge dataset for generalizing network performance. The analysis is driven into two sections: the comparison between the four approaches and the significance of patching the images.

RESULTS

The performance of networks trained on the RETOUCH dataset is higher than human performance. The analysis further generalized the performance of the best network obtained by fine-tuning it and achieved a mean Dice similarity coefficient (DSC) of 0.85. Out of the three types of fluids, intraretinal fluid (IRF) is more recognized, and the highest DSC value of 0.922 is achieved using Spectralis dataset. Additionally, the highest average DSC score is 0.84, which is achieved by PaDeeplabv3+ model using Cirrus dataset.

CONCLUSIONS

The proposed method segments the three fluids in the retina with high DSC value. Fine-tuning the networks trained on the RETOUCH dataset makes the network perform better and faster than training from scratch. Enriching the networks with inputting a variety of shapes by extracting patches helped to segment the fluids better than using a full image.

Development of Deep Learning Models to Predict Best-Corrected Visual Acuity from Optical Coherence Tomography

Purpose

To develop deep learning (DL) models to predict best-corrected visual acuity (BCVA) from optical coherence tomography (OCT) images from patients with neovascular age-related macular degeneration (nAMD).

Methods

Retrospective analysis of OCT images and associated BCVA measurements from the phase 3 HARBOR trial (NCT00891735). DL regression models were developed to predict BCVA at the concurrent visit and 12 months from baseline using OCT images. Binary classification models were developed to predict BCVA of Snellen equivalent of <20/40, <20/60, and ≤20/200 at the concurrent visit and 12 months from baseline.

Results

The regression model to predict BCVA at the concurrent visit had R² = 0.67 (root-mean-square error [RMSE] = 8.60) in study eyes and R² = 0.84 (RMSE = 9.01) in fellow eyes. The best classification model to predict BCVA at the concurrent visit had an area under the receiver operating characteristic curve (AUC) of 0.92 in study eyes and 0.98 in fellow eyes. The regression model to predict BCVA at month 12 using baseline OCT had R² = 0.33 (RMSE = 14.16) in study eyes and R² = 0.75 (RMSE = 11.27) in fellow eyes. The best classification model to predict BCVA at month 12 had AUC = 0.84 in study eyes and AUC = 0.96 in fellow eyes.

Conclusions

DL shows promise in predicting BCVA from OCTs in nAMD. Further research should elucidate the utility of models in clinical settings.

Translational Relevance

DL models predicting BCVA could be used to enhance understanding of structure–function relationships and develop more efficient clinical trials.

Optical coherence tomography and color fundus photography in the screening of age-related macular degeneration: A comparative, population-based study

Purpose

To analyze the individual value and the contribution of color fundus photography (CFP) and optical coherence tomography (OCT) in the screening of age-related macular degeneration (AMD) of an unselected population.

Methods

CFP and OCT images of 15957 eyes of 8069 subjects older than 55 years, obtained during a population-based screening for AMD using a single diagnostic non-mydriatic imaging device, were analyzed by a blinded examiner. The two techniques were preliminary evaluated considering the dichotomous parameter "gradable/ungradable", then gradable images were classified. CFP were graded according to the standardized classification of AMD lesions. OCT images were also categorized considering the presence of signs of early/intermediate AMD, late AMD, or other retinal diseases. Another blinded operator re-graded 1978 randomly selected images (for both CFP and OCT), to assess test reproducibility.

Results

Of the 15957 eyes, 8356 CFP (52.4%) and 15594 (97.7%) OCT scans were gradable. Moreover, most of the eyes with ungradable CFP (7339, 96.6%) were gradable at OCT. AMD signs were revealed in 7.4% of gradable CFP and in 10.4% of gradable OCT images. Moreover, at OCT, AMD signs were found in 1110 (6.9%) eyes whose CFP were ungradable or without AMD (847 and 263 eyes, respectively). The inter-operator agreement was good for the gradable versus ungradable parameter, and optimal for the AMD grading parameter of CFP. The agreement was optimal for all OCT parameters.

Conclusions

OCT provided gradable images in almost all examined eyes, compared to limited CFP efficiency. Moreover, OCT images allowed to detect more AMD eyes compared to gradable photos. OCT imaging appears to significantly improve the power of AMD screening in a general, unselected population, compared to CFP alone.

Role of Deep Learning-Quantified Hyperreflective Foci for the Prediction of Geographic Atrophy Progression

PURPOSE

To quantitatively measure hyperreflective foci (HRF) during the progression of geographic atrophy (GA) secondary to age-related macular degeneration (AMD) using deep learning (DL) and investigate the association with local and global growth of GA.

METHODS

Eyes with GA were prospectively included. Spectral-domain optical coherence tomography (SDOCT) and fundus autofluorescence images were acquired every 6 months. A 500-μm-wide junctional zone adjacent to the GA border was delineated and HRF were quantified using a validated DL algorithm. HRF concentrations in progressing and nonprogressing areas, as well as correlations between HRF quantifications and global and local GA progression, were assessed.

RESULTS

A total of 491 SDOCT volumes from 87 eyes of 54 patients were assessed with a median follow-up of 28 months. Two-thirds of HRF were localized within a millimeter adjacent to the GA border. HRF concentration was positively correlated with GA progression in unifocal and multifocal GA (all P < .001) and de novo GA development (P = .037). Local progression speed correlated positively with local increase of HRF (P value range <.001-.004). Global progression speed, however, did not correlate with HRF concentrations (P > .05). Changes in HRF over time did not have an impact on the growth in GA (P > .05).

CONCLUSION

Advanced artificial intelligence (AI) methods in high-resolution retinal imaging allows to identify, localize, and quantify biomarkers such as HRF. Increased HRF concentrations in the junctional zone and future macular atrophy may represent progressive migration and loss of retinal pigment epithelium. AI-based biomarker monitoring may pave the way into the era of individualized risk assessment and objective decision-making processes. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.

OPTICAL COHERENCE TOMOGRAPHY, FLUORESCEIN ANGIOGRAPHY, AND DIAGNOSIS OF CHOROIDAL NEOVASCULARIZATION IN AGE-RELATED MACULAR DEGENERATION

In a prospective study, spectral domain optical coherence tomography and fluorescein angiography, combined with color fundus photograph used as a first diagnostic test in patients aged 50 years or older, had a similar sensitivity and specificity for the diagnosis of choroidal neovascularization in age-related macular degeneration.

To determine the sensitivity and specificity of different retinal imaging combinations for the diagnosis of choroidal neovascularization (CNV) in age-related macular degeneration.

Application of Artificial Intelligence in Targeting Retinal Diseases

Retinal diseases affect an increasing number of patients worldwide because of the aging population. Request for diagnostic imaging in ophthalmology is ramping up, while the number of specialists keeps shrinking. Cutting-edge technology embedding artificial intelligence (AI) algorithms are thus advocated to help ophthalmologists perform their clinical tasks as well as to provide a source for the advancement of novel biomarkers. In particular, optical coherence tomography (OCT) evaluation of the retina can be augmented by algorithms based on machine learning and deep learning to early detect, qualitatively localize and quantitatively measure epi/intra/subretinal abnormalities or pathological features of macular or neural diseases. In this paper, we discuss the use of AI to facilitate efficacy and accuracy of retinal imaging in those diseases increasingly treated by intravitreal vascular endothelial growth factor (VEGF) inhibitors (i.e. anti-VEGF drugs), also including integration and interpretation features in the process. We review recent advances by AI in diabetic retinopathy, age-related macular degeneration, and retinopathy of prematurity that envision a potentially key role of highly automated systems in screening, early diagnosis, grading and individualized therapy. We discuss benefits and critical aspects of automating the evaluation of disease activity, recurrences, the timing of retreatment and therapeutically potential novel targets in ophthalmology. The impact of massive employment of AI to optimize clinical assistance and encourage tailored therapies for distinct patterns of retinal diseases is also discussed.

Performance Evaluation Of Convolutions And Atrous Convolutions In Deep Networks For Retinal Disease Segmentation On Optical Coherence Tomography Volumes

The deterioration of the retina center could be the main reason for vision loss. Older people usually ranging from 50 years and above are exposed to age-related macular degeneration (AMD) disease that strikes the retina. The lack of human expertise to interpret the complexity in diagnosing diseases leads to the importance of developing an accurate method to detect and localize the targeted infection. Approaching the performance of ophthalmologists is the consistent main challenge in retinal disease segmentation. Artificial intelligence techniques have shown enormous achievement in various tasks in computer vision. This paper depicts an automated end-to-end deep neural network for retinal disease segmentation on optical coherence tomography (OCT) scans. The work proposed in this study shows the performance difference between convolution operations and atrous convolution operations. Three deep semantic segmentation architectures, namely U-net, Segnet, and Deeplabv3+, have been considered to evaluate the performance of varying convolution operations. Empirical outcomes show a competitive performance to the human level, with an average dice score of 0.73 for retinal diseases.

Influence of pigment epithelial detachment on visual acuity in neovascular age-related macular degeneration

Pigment epithelial detachment (PED), the anatomical separation of the retinal pigment epithelium from the Bruch membrane, is common in many chorioretinal diseases, including neovascular age-related macular degeneration. PED is present in about 30% to 80% of neovascular age-related macular degeneration patients based on the CATT, EXCITE, and VIEW studies. The influence of PED on visual acuity is controversial as a result of inconsistent results reported by various studies. With advances in imaging technologies, it is possible to evaluate not only the presence or absence of PED, but also detailed quantitative parameters, such as height, width, greatest linear diameter, area, volume, and reflectivity within the PED. We performed a comprehensive literature review to evaluate the relationship of PED with visual acuity. In summary, the presence or persistence of a PED may still be compatible with relatively good visual acuity. There is no strong evidence that the presence of a PED or aspects of its morphology has a significant impact on visual acuity. The presence of a PED may be predictive of the need for more regular treatment. More well-designed studies with standardized PED definitions and classifications are needed to evaluate the relationship between PED and visual acuity.

Multimodal Coherent Imaging of Retinal Biomarkers of Alzheimer's Disease in a Mouse Model

We acquired depth-resolved light scattering measurements from the retinas of triple transgenic Alzheimer’s Disease (3xTg-AD) mice and wild type (WT) age-matched controls using co-registered angle-resolved low-coherence interferometry (a/LCI) and optical coherence tomography (OCT). Angle-resolved light scattering measurements were acquired from the nerve fiber layer, outer plexiform layer, and retinal pigmented epithelium using image guidance and segmented thicknesses provided by co-registered OCT B-scans. Analysis of the OCT images showed a statistically significant thinning of the nerve fiber layer in AD mouse retinas compared to WT controls. The a/LCI scattering measurements provided complementary information that distinguishes AD mice by quantitatively characterizing tissue heterogeneity. The AD mouse retinas demonstrated higher mean and variance in nerve fiber layer light scattering intensity compared to WT controls. Further, the difference in tissue heterogeneity was observed through short-range spatial correlations that show greater slopes at all layers of interest for AD mouse retinas compared to WT controls. A greater slope indicates a faster loss of spatial correlation, suggesting a loss of tissue self-similarity characteristic of heterogeneity consistent with AD pathology. Use of this combined modality introduces unique tissue texture characterization to complement development of future AD biomarker analysis.

Replication and Refinement of an Algorithm for Automated Drusen Segmentation on Optical Coherence Tomography

Here, we investigate the extent to which re-implementing a previously published algorithm for OCT-based drusen quantification permits replicating the reported accuracy on an independent dataset. We refined that algorithm so that its accuracy is increased. Following a systematic literature search, an algorithm was selected based on its reported excellent results. Several steps were added to improve its accuracy. The replicated and refined algorithms were evaluated on an independent dataset with the same metrics as in the original publication. Accuracy of the refined algorithm (overlap ratio 36-52%) was significantly greater than the replicated one (overlap ratio 25-39%). In particular, separation of the retinal pigment epithelium and the ellipsoid zone could be improved by the refinement. However, accuracy was still lower than reported previously on different data (overlap ratio 67-76%). This is the first replication study of an algorithm for OCT image analysis. Its results indicate that current standards for algorithm validation do not provide a reliable estimate of algorithm performance on images that differ with respect to patient selection and image quality. In order to contribute to an improved reproducibility in this field, we publish both our replication and the refinement, as well as an exemplary dataset.

Tracing the retina to analyze the integrity and phagocytic capacity of the retinal pigment epithelium

We have developed a new technique to study the integrity, morphology and functionality of the retinal neurons and the retinal pigment epithelium (RPE). Young and old control albino (Sprague-Dawley) and pigmented (Piebald Virol Glaxo) rats, and dystrophic albino (P23H-1) and pigmented (Royal College of Surgeons) rats received a single intravitreal injection of 3% Fluorogold (FG) and their retinas were analyzed from 5 minutes to 30 days later. Retinas were imaged in vivo with SD-OCT and ex vivo in flat-mounts and in cross-sections. Fifteen minutes and 24 hours after intravitreal administration of FG retinal neurons and the RPE, but no glial cells, were labeled with FG-filled vesicles. The tracer reached the RPE 15 minutes after FG administration, and this labeling remained up to 30 days. Tracing for 15 minutes or 24 hours did not cause oxidative stress. Intraretinal tracing delineated the pathological retinal remodelling occurring in the dystrophic strains. The RPE of the P23H-1 strain was highly altered in aged animals, while the RPE of the RCS strain, which is unable to phagocytose, did not accumulate the tracer even at young ages when the retinal neural circuit is still preserved. In both dystrophic strains, the RPE cells were pleomorphic and polymegathic.

Retinal neurodegeneration in patients with end-stage renal disease assessed by spectral-domain optical coherence tomography

Spectral-domain optical coherence tomography (SD-OCT) represents a reliable tool for retinal layer volume and thickness measurement. The aim of this study was to evaluate retinal changes indicating neurodegenerative processes in patients with end-stage renal disease (ESRD) compared to healthy controls. This was a cross-sectional, single-center study comprising 32 ESRD patients and 38 controls. Sectoral retinal nerve fiber layer (RNFL) thickness and retinal layer volumes were obtained by SD-OCT. Age- and gender-adjusted retinal layer volumes such as total retinal volume (p = 0.037), ganglion cell layer volume (GCL, p = 0.003), ganglion cell layer - inner plexiform layer volume (GCL-IPL, p = 0.005) and inner retinal layer volume (IRL, p = 0.042) of the right eye were lower in ESRD patients. Inner plexiform layer volume of both eyes (IPL, right eye: p = 0.017; left eye: 0.044) was reduced, as was RNFL thickness in the temporal superior sector (right eye: p = 0.016). A subgroup analysis excluding patients with diabetes revealed that GCL (p = 0.014) and GCL-IPL volume of the right eye (p = 0.024) and temporal superior sector of the RNFL scan (p = 0.021) in ESRD patients were still significantly thinner. We observed a decrease in several retinal layer volumes and temporal RNFL thickness indicative of retinal neurodegenerative processes in patients with ESRD.

Subretinal Fibrosis Detection Using Polarization Sensitive Optical Coherence Tomography

Purpose

Subretinal fibrosis (SRFib) is an important cause of permanent loss-of-vision diseases with submacular neovascularization, but a reliable diagnostic method is currently missing. This study uses polarization-sensitive optical coherence tomography (PS-OCT) to detect SRFib within retinal lesions by measurement of its birefringent collagen fibers.

Methods

Twenty-five patients were enrolled with retinal pathology in one or both eyes containing (1) suspected SRFib, (2) lesions suspected not to be fibrotic, or (3) lesions with doubtful presence of SRFib. All eyes were evaluated for SRFIb using conventional diagnostics by three retinal specialists. PS-OCT images were visually evaluated for SRFib based on cumulative phase retardation, local birefringence, and optic axis uniformity.

Results

Twenty-nine eyes from 22 patients were scanned successfully. In 13 eyes, SRFib was diagnosed by all retinal specialists; of these, 12 were confirmed by PS-OCT and one was inconclusive. In nine eyes, the retinal specialists expected no SRFib, which was confirmed by PS-OCT in all cases. In seven eyes, the retinal specialists’ evaluations were inconsistent with regard to the presence of SRFib. PS-OCT confirmed the presence of SRFib in four of these eyes and the absence of SRFib in two eyes and was inconclusive in one eye.

Conclusions

In 21 out of 22 eyes, PS-OCT confirmed the evaluation of retinal specialists regarding the presence of SRFib. PS-OCT provided additional information to distinguish SRFib from other tissues within subretinal neovascular lesions in 6 out of 7 eyes.

Translational Relevance

PS-OCT can identify and quantify SRFib in doubtful cases for which a reliable diagnosis is currently lacking.

Artifacts and artifact removal in optical coherence tomographic angiography

Optical coherence tomographic angiography (OCTA) enables rapid imaging of retinal vasculature in three dimensions. While the technique has provided quantification of healthy vessels as well as pathology in several diseases, it is not unusual for OCTA data to contain artifacts that may influence measurement outcomes or defy image interpretation. In this review, we discuss the sources of several OCTA artifacts-including projection, motion, and signal reduction-as well as strategies for their removal. Artifact compensation can improve the accuracy of OCTA measurements, and the most effective use of the technology will incorporate hardware and software that can perform such correction.

[A differentiated approach to analysis of retinal fluid and assessment of its effect on anti-VEGF therapy of neovascular age-related macular degeneration]

Neovascular age-related macular degeneration (nAMD) causes rapid irreversible vision loss presenting a serious socio-economic problem. The recommended approach to the treatment of this pathology is the use of angiogenesis inhibitors (anti-VEGF drugs). Following the proactive principles when conducting anti-VEGF treatment helps achieve the maximum therapeutic efficacy. The evolution of diagnostic capabilities and the rising awareness of the pathogenetic features of nAMD have contributed to implementation of a more personalized approach of conducting intravitreal injections, bringing to light the necessity of determining the diagnostic criteria for repeated anti-VEGF injections. Currently, the discourse looks at the subject of OCT criteria that could act as sufficiently reliable biomarkers to help decide the change in frequency of intravitreal injections. A differentiated approach to defining the role of retinal fluid as a marker of disease activity depending on the compartment of its localization on the OCT images has not been fully determined and is of particular scientific and practical interest. The importance of correct interpretation and understanding of differences in the effects of various types of retinal fluid on the frequency of anti-VEGF injections will be discussed in this review.

Optical coherence tomography in pediatric patients: a clinical review

Optical coherence tomography has improved the ophthalmic clinical examination due to its ability to more accurately characterize pathology of the eye. Optical coherence tomography is now an integral imaging modality for many adult diseases of the retina and is a ubiquitous part of a retinal practice. However, although its use in adults is well recognized, the adoption of optical coherence tomography in pediatric patients may be undervalued as macular diseases in children are relatively uncommon. Recent technological advancements have made optical coherence tomography scans quicker and more precise, generating normative data and leading to more widespread use in children. In this review article, we discuss how pediatric optical coherence tomography data can be used to understand normal development, as well as diagnose and monitor retinal disease. In particular, we highlight clinical optical coherence tomography findings of several pediatric retinal conditions, including retinopathy of prematurity, congenital infections, retinal dystrophies, and phakomatoses such as neurofibromatosis.

Deep learning-based automated detection of retinal diseases using optical coherence tomography images

Retinal disease classification is a significant problem in computer-aided diagnosis (CAD) for medical applications. This paper is focused on a 4-class classification problem to automatically detect choroidal neovascularization (CNV), diabetic macular edema (DME), DRUSEN, and NORMAL in optical coherence tomography (OCT) images. The proposed classification algorithm adopted an ensemble of four classification model instances to identify retinal OCT images, each of which was based on an improved residual neural network (ResNet50). The experiment followed a patient-level 10-fold cross-validation process, on development retinal OCT image dataset. The proposed approach achieved 0.973 (95% confidence interval [CI], 0.971-0.975) classification accuracy, 0.963 (95% CI, 0.960-0.966) sensitivity, and 0.985 (95% CI, 0.983-0.987) specificity at the B-scan level, achieving a matching or exceeding performance to that of ophthalmologists with significant clinical experience. Other performance measures used in the study were the area under receiver operating characteristic curve (AUC) and kappa value. The observations of the study implied that multi-ResNet50 ensembling was a useful technique when the availability of medical images was limited. In addition, we performed qualitative evaluation of model predictions, and occlusion testing to understand the decision-making process of our model. The paper provided an analytical discussion on misclassification and pathology regions identified by the occlusion testing also. Finally, we explored the effect of the integration of retinal OCT images and medical history data from patients on model performance.

Expert-level Automated Biomarker Identification in Optical Coherence Tomography Scans

In ophthalmology, retinal biological markers, or biomarkers, play a critical role in the management of chronic eye conditions and in the development of new therapeutics. While many imaging technologies used today can visualize these, Optical Coherence Tomography (OCT) is often the tool of choice due to its ability to image retinal structures in three dimensions at micrometer resolution. But with widespread use in clinical routine, and growing prevalence in chronic retinal conditions, the quantity of scans acquired worldwide is surpassing the capacity of retinal specialists to inspect these in meaningful ways. Instead, automated analysis of scans using machine learning algorithms provide a cost effective and reliable alternative to assist ophthalmologists in clinical routine and research. We present a machine learning method capable of consistently identifying a wide range of common retinal biomarkers from OCT scans. Our approach avoids the need for costly segmentation annotations and allows scans to be characterized by biomarker distributions. These can then be used to classify scans based on their underlying pathology in a device-independent way.

RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge

Retinal swelling due to the accumulation of fluid is associated with the most vision-threatening retinal diseases. Optical coherence tomography (OCT) is the current standard of care in assessing the presence and quantity of retinal fluid and image-guided treatment management. Deep learning methods have made their impact across medical imaging, and many retinal OCT analysis methods have been proposed. However, it is currently not clear how successful they are in interpreting the retinal fluid on OCT, which is due to the lack of standardized benchmarks. To address this, we organized a challenge RETOUCH in conjunction with MICCAI 2017, with eight teams participating. The challenge consisted of two tasks: fluid detection and fluid segmentation. It featured for the first time: all three retinal fluid types, with annotated images provided by two clinical centers, which were acquired with the three most common OCT device vendors from patients with two different retinal diseases. The analysis revealed that in the detection task, the performance on the automated fluid detection was within the inter-grader variability. However, in the segmentation task, fusing the automated methods produced segmentations that were superior to all individual methods, indicating the need for further improvements in the segmentation performance.

First Clinical Application of Low-Cost OCT

Purpose

We present the design of a new low-cost optical coherence tomography (OCT) system and compare its retinal imaging capabilities to a standard commercial system through a clinical study.

Methods

A spectral-domain OCT system was designed using various cost-reduction techniques to be low-cost, highly portable, and completely stand-alone. Clinical imaging was performed on 120 eyes of 60 patients (60 eyes of normal volunteers and 60 eyes with retinal disease) using both the low-cost OCT and a Heidelberg Engineering Spectralis OCT. Contrast-to-noise ratio (CNR) was measured from resulting images to determine system performance.

Results

The low-cost OCT system was successfully applied to clinical imaging of the retina. The system offers an axial resolution of 8.0 μm, a lateral resolution of 19.6 μm, and an imaging depth of 2.7 mm for a 6.6-mm field of view in the X and Y directions. Total cost is $5037, a significant size reduction compared to current commercial higher performance systems. Mean CNR value of low-cost OCT images is only 5.6% lower compared to the Heidelberg Spectralis.

Conclusions

The images captured with the low-cost OCT were of adequate resolution and allowed for clinical diagnostics. It offers comparable performance as a retinal screening tool at a fraction of the cost of current commercial systems.

Translational Relevance

Low-cost OCT has the potential to increase access to retinal imaging.

Photothermal Optical Coherence Tomography of Anti-Angiogenic Treatment in the Mouse Retina Using Gold Nanorods as Contrast Agents

Purpose

Optical coherence tomography (OCT) is widely used for ocular imaging in clinical and research settings. OCT natively provides structural information based on the reflectivity of the tissues it images. We demonstrate the utility of photothermal OCT (PTOCT) imaging of gold nanorods (GNR) in the mouse retina in vivo in the laser-induced choroidal neovascularization (LCNV) model to provide additional image contrast within the lesion.

Methods

Wild-type C57BL/6 mice were imaged following the intravenous injection of ICAM2-targeted or untargeted GNR. Mice were also imaged following the injection of ICAM2-targeted GNR with or without the additional ocular delivery of a neutralizing monoclonal anti-vascular endothelial growth factor (anti-VEGF) antibody.

Results

Mice cohorts injected with untargeted or ICAM2-targeted GNR demonstrated increased lesion-associated photothermal signal during subsequent imaging relative to phosphate-buffered saline (PBS)-injected controls. Additionally, intravitreal injection of anti-VEGF antibody caused a detectable reduction in the extent of anatomic laser damage and lesion-associated photothermal signal density in mice treated in the LCNV model and injected with ICAM2-targeted GNR.

Conclusions

These experiments demonstrate the ability of PTOCT imaging of GNR to detect anti-VEGF-induced changes in the mouse retina using the LCNV model.

Translational Relevance

This study shows that PTOCT imaging of GNR in the LCNV model can be used to detect clinically relevant, anti-VEGF-induced changes that are not visible using standard OCT systems. In the future this technology could be used to aid in early detection of disease, monitoring disease progress, and assessing its response to therapies.

Action on neovascular age-related macular degeneration (nAMD): recommendations for management and service provision in the UK hospital eye service

This report by a group of UK retina specialists and health professionals considers best practice recommendations for the management of sight-threatening neovascular age-related macular degeneration (nAMD), based on collective experience and expertise in routine clinical practice. The authors provide an update for ophthalmologists, allied healthcare professionals and commissioners on practice principles for optimal patient care and service provision standards. Refinement of care pathways for nAMD has improved access to intravitreal anti-vascular endothelial growth factor therapy but there are still variations in care and reported outcomes between clinic centres. Innovative organisational models of service provision allow providers to better match capacity with increasing demand. The authors review the recent NICE guideline for diagnosis and management of AMD, considerations for switching therapies and stopping treatment and need for regular monitoring of non-affected fellow eyes in patients with unilateral nAMD. Actions for delivery of high-quality care and to improve long-term patient outcomes are discussed. Local pathways need to detail nAMD target time to treat, maintenance of review intervals to ensure proactive treatment regimens are delivered on time and appropriate discharge for patients deemed low risk or no longer benefiting from treatment. Actual visual acuity outcomes achieved and maintenance of the level of vision when disease stability is achieved are considered good measures for judging the quality of care in the treatment of patients with nAMD. Robust community referral pathways must be in place for suspected reactivation of choroidal neovascularisation and rapid referral for second eye involvement. Practical considerations for intravitreal injection therapy are outlined.

Age-related macular degeneration

Age-related macular degeneration is a leading cause of visual impairment and severe vision loss. Clinically, it is classified as early-stage (medium-sized drusen and retinal pigmentary changes) to late-stage (neovascular and atrophic). Age-related macular degeneration is a multifactorial disorder, with dysregulation in the complement, lipid, angiogenic, inflammatory, and extracellular matrix pathways implicated in its pathogenesis. More than 50 genetic susceptibility loci have been identified, of which the most important are in the CFH and ARMS2 genes. The major non-genetic risk factors are smoking and low dietary intake of antioxidants (zinc and carotenoids). Progression from early-stage to late-stage disease can be slowed with high-dose zinc and antioxidant vitamin supplements. Intravitreal anti-vascular endothelial growth factor therapy (eg, ranibizumab, aflibercept, or bevacizumab) is highly effective at treating neovascular age-related macular degeneration, and has markedly decreased the prevalence of visual impairment in populations worldwide. Currently, no proven therapies for atrophic disease are available, but several agents are being investigated in clinical trials. Future progress is likely to be from improved efforts in prevention and risk-factor modification, personalised medicine targeting specific pathways, newer anti-vascular endothelial growth factor agents or other agents, and regenerative therapies.

Multimodal Imaging of Nonneovascular Age-Related Macular Degeneration

Nonneovascular (dry) AMD is a retinal disease with potential for significant central visual impairment. The hallmarks of this disease are macular drusen, RPE alterations, and geographic atrophy (GA). Classification schemes for nonneovascular AMD have evolved over the years as major advances in retinal imaging have enabled a greater understanding of disease pathophysiology. The original classifications of nonneovascular AMD were based on color fundus photography (CFP), while more modern schemes rely on a multimodal imaging approach. Effective diagnosis and management of nonneovascular AMD requires a thorough understanding of its multimodal imaging features as detailed in this review. Future imaging modalities and imaging biomarkers that may aid in diagnosis and management are also discussed.

Clinically applicable deep learning for diagnosis and referral in retinal disease

The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.

Correlation of Color Fundus Photograph Grading with Risks of Early Age-related Macular Degeneration by using Automated OCT-derived Drusen Measurements

We evaluated automated OCT-derived drusen volume measures in a population-based study (n = 4,512) aged ≥40 years, and its correlation with conventional color fundus photographs (CFP)-derived early AMD features. Participants had protocol-based assessment to capture medical and ocular history, genotyping for SNPs in CFH, ARMS2, and CETP, CFP-based AMD grading and automated drusen volume based on SD-OCT using built-in software (Cirrus OCT advanced RPE analysis software). Significantly fewer eyes with early AMD features (drusen, hyperpigmentation, soft or reticular drusen) had drusen volume = 0 mm³ (p < 0.001). In eyes with drusen volume > 0 mm³, increasing AMD severity was associated with increase in drusen volume (correlation coefficient 0.17, p < 0.001). However 220 (59.14%) of 372 participants with AMD based on CFP grading had drusen volume = 0 mm³. Factors associated with drusen volume included age (OR 1.42 per 5 years, 95% confidence interval [CI] 2.76, 4.48), systolic blood pressure (OR1.00, 95% CI 1.00, 1.01), ethnic Malay (OR 1.54, 95% CI 1.29, 1.83) and Chinese (OR 1.66, 95% CI 1.37, 2.01) compared to Indian. The ARMS2 rs10490924 T allele was associated with increased drusen volume in subjects with AMD (multivariable adjusted OR1.54, 95% CI 1.08, 2.19). Automated OCT-derived drusen volume is correlated with CFP-based AMD grading in many, but not all subjects. However the agreement is not good. These two modalities provide complementary information and should be incorporated into future studies.

Morphological Predictive Features on Spectral-Domain Optical Coherence Tomography for Visual Outcomes in Neovascular Age-Related Macular Degeneration Treated with Ranibizumab

Purpose

To identify spectral-domain optical coherence tomography (SD-OCT) predictive morphological features for the outcome of Ranibizumab therapy for neovascular age-related macular degeneration (AMD).

Methods

This is a retrospective multicentric study that involved 64 eyes with naïve AMD. Patients who received three monthly intravitreal injections of Ranibizumab were stratified into (1) "responders" [≥ 5 letters gain on Early Treatment Diabetic Retinopathy Study (ETDRS) scale] and (2) "nonresponders" (< 5 letters gain). Best-corrected visual acuity (BCVA) and SD-OCT morphological features were compared at baseline and one month after three consecutive injections of Ranibizumab. Univariate and multivariate analyses were carried out to correlate these morphological features with the change in BCVA.

Results

Among the 64 patients enrolled, 40 (62.5%) were "responders" and 24 (37.5%) "nonresponders". Age, sex, and BCVA were comparable between both groups. A multivariate correlational analysis found that subfoveal choroidal thickness (SFCT) and the presence of pigment epithelial detachment (PED) > 250 μm at baseline were two independent prognostic indicators of final BCVA. No other SD-OCT morphological studied features seem to affect final BCVA after Ranibizumab treatment.

Conclusion

SFCT and the presence of PED > 250 μm are two significant biomarkers that may predict improvement after Ranibizumab therapy for AMD. These markers may guide ophthalmologists' treatment decision under financial constraints and limited time.

Design and implementation of a low-cost, portable OCT system

Optical coherence tomography (OCT) is a widely used biomedical imaging tool, primarily in ophthalmology to diagnose and stage retinal diseases. In order to increase access for a wider range of applications and in low resource settings, we developed a portable, low-cost OCT system that has comparable imaging performance to commercially available systems. Here, we present the system design and characterization and compare the system performance to other commercially available OCT systems. In addition, future cost reductions and potential additional applications of the low-cost OCT system are discussed.