PROGNOSTIC VALUE OF SHAPE-DESCRIPTIVE FACTORS FOR THE PROGRESSION OF GEOGRAPHIC ATROPHY SECONDARY TO AGE-RELATED MACULAR DEGENERATION

Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus Autofluorescence

Purpose

The region of growth (ROG) of geographic atrophy (GA) throughout the macular area has an impact on visual outcomes. Here, we developed multiple deep learning models to predict the 1-year ROG of GA lesions using fundus autofluorescence (FAF) images.

Design

In this retrospective analysis, 3 types of models were developed using FAF images collected 6 months after baseline to predict the GA lesion area (segmented lesion mask) at 1.5 years, FAF images collected at baseline and 6 months to predict the GA lesion at 1.5 years, and FAF images collected 6 months after baseline to predict the GA lesion at 1 and 1.5 years. The 1-year ROG from the 6-month visit was derived by taking the difference between the GA lesion area (segmented lesion mask) at the 1.5-year and 6-month visits.

Participants

Patients enrolled in the following lampalizumab clinical trials and prospective observational studies: NCT02247479, NCT02247531, NCT02479386, and NCT02399072.

Methods

Datasets of study eyes from 597 patients were split into model training (310), validation (78), and test sets (209), stratified by baseline or initial lesion area, lesion growth rate, foveal involvement, and focality. Deep learning experiments were performed using the 2-dimensional U-Net; whole-lesion and multiclass models were developed.

Main Outcome Measures

The performance of the models was evaluated by calculating the Dice score, coefficient of determination (R2), and the squared Pearson correlation coefficient (r2) between the true and derived GA lesion 1-year ROG.

Results

The model using baseline and 6-month FAF images to predict GA lesion enlargement at 1.5 years had the best performance for the derived 1-year ROG. Mean Dice scores were 0.73, 0.68, and 0.70 in the training, validation, and test sets, respectively. The R2 (0.77, 0.53, and 0.79) and r2 (0.83, 0.61, and 0.79) showed similar trends across the 3 sets.

Conclusions

These findings show the potential of using baseline and/or 6-month visit FAF images to predict 1-year GA ROG using a deep learning approach. This work could potentially help support decision-making in clinical trials and more informed treatment decisions in clinical practice.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Relationships Between Diet and Geographic Atrophy Progression in the Age-Related Eye Diseases Studies 1 and 2

Background/Objectives: The objective of this study was to analyze the relationships between diet and geographic atrophy (GA) progression, both area-based and proximity-based, for dietary pattern, components, and micronutrients. Methods: In the Age-Related Eye Diseases Study (AREDS) and AREDS2, an Alternative Mediterranean Diet Index (aMedi), its nine components, and individual micronutrient intakes were calculated. Mixed-model regression was performed for square root GA area, GA foveal proximity, and acuity. Results: The study populations comprised 657 (AREDS) and 1179 eyes (AREDS2). For area-based progression, a higher aMedi was associated with slower progression in AREDS2 and (in analyses excluding MUFA:SFA) AREDS. A higher intake was associated with slower progression for seven components (including vegetables and fruit at Bonferroni) and four components (including fruit and less red meat at Bonferroni), and seven and 15 nutrients, in AREDS1/2, respectively. For proximity-based progression, a higher aMedi was associated with slower progression in AREDS. A higher intake was associated with slower progression for three components (including vegetables at Bonferroni) and two components, and 10 and 8 nutrients, in AREDS1/2, respectively. With increasing oral supplementation, associations between proximity-based progression and aMedi/components/nutrients were weaker. In AREDS2 eyes with non-central GA, higher aMedi was associated with a slower acuity decline. Conclusions: A Mediterranean-type diet is associated with slower GA area-based progression and slower progression to the fovea, accompanied by a slower decline in acuity. The most important components and micronutrients for incidence, area-based progression, and foveal progression overlap only partially. For the latter two, they include vegetables, fruit, and less red meat. These findings suggest the benefits of targeted nutritional and supplementation strategies.

Artificial intelligence in assessing progression of age-related macular degeneration

The human population is steadily growing with increased life expectancy, impacting the prevalence of age-dependent diseases, including age-related macular degeneration (AMD). Health care systems are confronted with an increasing burden with rising patient numbers accompanied by ongoing developments of therapeutic approaches. Concurrent advances in imaging modalities provide eye care professionals with a large amount of data for each patient. Furthermore, with continuous progress in therapeutics, there is an unmet need for reliable structural and functional biomarkers in clinical trials and practice to optimize personalized patient care and evaluate individual responses to treatment. A fast and objective solution is Artificial intelligence (AI), which has revolutionized assessment of AMD in all disease stages. Reliable and validated AI-algorithms can aid to overcome the growing number of patients, visits and necessary treatments as well as maximize the benefits of multimodal imaging in clinical trials. Therefore, there are ongoing efforts to develop and validate automated algorithms to unlock more information from datasets allowing automated assessment of disease activity and disease progression. This review aims to present selected AI algorithms, their development, applications and challenges regarding assessment and prediction of AMD progression.

Fundus Autofluorescence Variation in Geographic Atrophy of Age-Related Macular Degeneration: A Clinicopathologic Correlation

Purpose

The purpose of this study was to develop ground-truth histology about contributors to variable fundus autofluorescence (FAF) signal and thus inform patient selection for treating geographic atrophy (GA) in age-related macular degeneration (AMD).

Methods

One woman with bilateral multifocal GA, foveal sparing, and thick choroids underwent 535 to 580 nm excitation FAF in 6 clinic visits (11 to 6 years before death). The left eye was preserved 5 hours after death. Eye-tracked ex vivo imaging aligned sub-micrometer epoxy resin sections (n = 140, 60 µm apart) with clinic data. Light microscopic morphology corresponding to FAF features assessed included drusen-driven atrophy, persistent hyperautofluorescence (hyperFAF) islands and peninsulas within atrophy, and hyperFAF and hypoautofluorescence (hypoFAF) inner junctional zone (IJZ) and outer junctional zone (OJZ) relative to descent of external limiting membrane (ELM). Atrophy growth rate was calculated.

Results

HypoFAF atrophic spots appeared in association with drusen, and then expanded and coalesced. Over drusen (n = 45, all calcified), RPE was continuous and thin, photoreceptors were short or absent, and initially intact ELM descended where RPE was absent. In persistent hyperFAF within atrophy and in the OJZ, the RPE was continuous and dysmorphic, photoreceptors were present and short, and BLamD was thick. In the IJZ, mottled FAF corresponded to dissociated RPE atop persistent BLamD. Overall linear growth rate (0.198 mm/ year) typified multifocal GA.

Conclusions

FAF in GA is locally multifactorial, with photoreceptor shortening potentially promoting hyperFAF by increasing incoming excitation light available to RPE fluorophores. RPE dysmorphia may lead to either longer or shorter pathlength for excitation light. At both atrophy initiation and expansion Müller glia are major participants.

Oral Antioxidant and Lutein/Zeaxanthin Supplements Slow Geographic Atrophy Progression to the Fovea in Age-Related Macular Degeneration

PURPOSE

To determine whether oral micronutrient supplementation slows geographic atrophy (GA) progression in age-related macular degeneration (AMD).

DESIGN

Post hoc analysis of Age-Related Eye Disease Study (AREDS) and AREDS2, multicenter randomized placebo-controlled trials of oral micronutrient supplementation, each with 2 × 2 factorial design.

PARTICIPANTS

A total of 392 eyes (318 participants) with GA in AREDS and 1210 eyes (891 participants) with GA in AREDS2.

METHODS

The AREDS participants were randomly assigned to oral antioxidants (500 mg vitamin C, 400 IU vitamin E, 15 mg β-carotene), 80 mg zinc, combination, or placebo. The AREDS2 participants were randomly assigned to 10 mg lutein/2 mg zeaxanthin, 350 mg docosahexaenoic acid/650 mg eicosapentaenoic acid, combination, or placebo. Consenting AREDS2 participants were also randomly assigned to alternative AREDS formulations: original; no beta-carotene; 25 mg zinc instead of 80 mg; both.

MAIN OUTCOME MEASURES

(1) Change in GA proximity to central macula over time and (2) change in square root GA area over time, each measured from color fundus photographs at annual visits and analyzed by mixed-model regression according to randomized assignments.

RESULTS

In AREDS eyes with noncentral GA (n = 208), proximity-based progression toward the central macula was significantly slower with randomization to antioxidants versus none, at 50.7 μm/year (95% confidence interval [CI], 38.0-63.4 μm/year) versus 72.9 μm/year (95% CI, 61.3-84.5 μm/year; P = 0.012), respectively. In AREDS2 eyes with noncentral GA, in participants assigned to AREDS antioxidants without β-carotene (n = 325 eyes), proximity-based progression was significantly slower with randomization to lutein/zeaxanthin versus none, at 80.1 μm/year (95% CI, 60.9-99.3 μm/year) versus 114.4 μm/year (95% CI, 96.2-132.7 μm/year; P = 0.011), respectively. In AREDS eyes with any GA (n = 392), area-based progression was not significantly different with randomization to antioxidants versus none (P = 0.63). In AREDS2 eyes with any GA, in participants assigned to AREDS antioxidants without β-carotene (n = 505 eyes), area-based progression was not significantly different with randomization to lutein/zeaxanthin versus none (P = 0.64).

CONCLUSIONS

Oral micronutrient supplementation slowed GA progression toward the central macula, likely by augmenting the natural phenomenon of foveal sparing.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found after the references.

Association of Hyperautofluorescence Signals with Geographic Atrophy Progression in the METformin for the MINimization of Geographic Atrophy Progression Trial

Purpose

To investigate the association between rim area focal hyperautofluorescence (RAFH) signals and geographic atrophy (GA) growth rates, as well as the impact of oral metformin on the longitudinal change of RAFH.

Design

Secondary analysis of a randomized controlled trial.

Participants

Seventy-one eyes from 44 participants with GA and ≥6 months of follow-up in the METformin for the MINimization of geographic atrophy progression study.

Methods

Fundus autofluorescence images were captured using a 488 nm excitation wavelength. Two masked graders identified and measured RAFH lesions using proprietary semiautomatic segmentation software and ImageJ. We calculated RAFH by dividing the areas of hyperautofluorescence within a 450-μm rim circumscribing the GA by the total area enclosed within this rim.

Main Outcome Measures

Longitudinal changes in RAFH and GA area.

Results

Baseline RAFH was positively associated with the baseline square root of GA area 0.065/year (P < 0.001). In the entire study cohort, higher baseline RAFH was associated with a faster GA area growth rate in mm2/year (Spearman's ρ = 0.53; P < 0.001). The association became weaker in square root-transformed GA area growth (ρ = 0.19, P = 0.11) and perimeter-adjusted GA growth rate (ρ = 0.28, P = 0.02), achieving statistical significance only in the latter. When this analysis was stratified into 3 baseline GA tertiles, the first and second tertiles showed weak to moderate association with statistical significance in all 3 modes of GA growth rates. Rim area focal hyperautofluorescence increased slightly but significantly over time at 0.020/year (P < 0.01). Rim area focal hyperautofluorescence increased slightly but significantly over time at 0.020/year (P < 0.01). The use of oral metformin was not significantly associated with the change in RAFH over time compared with the observation group (0.023/year vs. 0.016/year; P = 0.29).

Conclusions

Increased baseline RAFH is associated with faster GA area progression. However, the effect size of this association may depend on the baseline GA lesion size such that small to medium-sized GA lesions display this relationship regardless of the mode of the calculation of GA growth rate.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Artificial intelligence for geographic atrophy: pearls and pitfalls

PURPOSE OF REVIEW

This review aims to address the recent advances of artificial intelligence (AI) in the context of clinical management of geographic atrophy (GA), a vision-impairing late-stage manifestation of age-related macular degeneration (AMD).

RECENT FINDINGS

Recent literature shows substantial advancements in the development of AI systems to segment GA lesions on multimodal retinal images, including color fundus photography (CFP), fundus autofluorescence (FAF) and optical coherence tomography (OCT), providing innovative solutions to screening and early diagnosis. Especially, the high resolution and 3D-nature of OCT has provided an optimal source of data for the training and validation of novel algorithms. The use of AI to measure progression in the context of newly approved GA therapies, has shown that AI methods may soon be indispensable for patient management. To date, while many AI models have been reported on, their implementation in the real-world has only just started. The aim is to make the benefits of AI-based personalized treatment accessible and far-reaching.

SUMMARY

The most recent advances (pearls) and challenges (pitfalls) associated with AI methods and their clinical implementation in the context of GA will be discussed.

Informing Endpoints for Clinical Trials of Geographic Atrophy

Geographic atrophy (GA), the non-neovascular advanced form of age-related macular degeneration, remains an important disease area in which treatment needs are currently unmet. Recent clinical trials using drugs that target the complement pathway have shown modest yet consistent reductions in GA expansion but without commensurate changes in measures of visual function. In this review, we summarize information from the wide range of studies describing the characteristics of GA morphology and enumerate the factors influencing the growth rates of lesions and the directionality of expansion. In addition, we review the relationship between GA growth and the various measures of vision that reflect changes in function. We consider the reasons for the discordance between the anatomical and functional endpoints in current use and discuss methods to align these key outcomes.

Measuring Geographic Atrophy Area Using Column-Based Machine Learning Software on Spectral-Domain Optical Coherence Tomography versus Fundus Auto Fluorescence

BACKGROUND

The purpose of this study was to compare geographic atrophy (GA) area semi-automatic measurement using fundus autofluorescence (FAF) versus optical coherence tomography (OCT) annotation with the cRORA (complete retinal pigment epithelium and outer retinal atrophy) criteria.

METHODS

GA findings on FAF and OCT were semi-automatically annotated at a single time point in 36 pairs of FAF and OCT scans obtained from 36 eyes in 24 patients with dry age-related macular degeneration (AMD). The GA area, focality, perimeter, circularity, minimum and maximum Feret diameter, and minimum distance from the center were compared between FAF and OCT annotations.

RESULTS

The total GA area measured on OCT was 4.74 ± 3.80 mm2. In contrast, the total GA measured on FAF was 13.47 ± 8.64 mm2 (p < 0.0001), with a mean difference of 8.72 ± 6.35 mm2. Multivariate regression analysis revealed a significant correlation between the difference in area between OCT and FAF and the total baseline lesion perimeter and maximal lesion diameter measured on OCT (adjusted r2: 0.52; p < 0.0001) and the total baseline lesion area measured on FAF (adjusted r2: 0.83; p < 0.0001).

CONCLUSIONS

We report that the GA area measured on FAF differs significantly from the GA area measured on OCT. Further research is warranted in order to determine the clinical relevance of these findings.

[Use of artificial intelligence in geographic atrophy in age-related macular degeneration]

The first regulatory approval of treatment for geographic atrophy (GA) secondary to age-related macular degeneration in the USA constitutes an important milestone; however, due to the nature of GA as a non-acute, insidiously progressing pathology, the ophthalmologist faces specific challenges concerning risk stratification, making treatment decisions, monitoring of treatment and patient education. Innovative retinal imaging modalities, such as fundus autofluorescence (FAF) and optical coherence tomography (OCT) have enabled identification of typical morphological alterations in relation to GA, which are also suitable for the quantitative characterization of GA. Solutions based on artificial intelligence (AI) enable automated detection and quantification of GA-specific biomarkers on retinal imaging data, also retrospectively and over time. Moreover, AI solutions can be used for the diagnosis and segmentation of GA as well as the prediction of structure and function without and under GA treatment, thereby making a valuable contribution to treatment monitoring and the identification of high-risk patients and patient education. The integration of AI solutions into existing clinical processes and software systems enables the broad implementation of informed and personalized treatment of GA secondary to AMD.

Combination of optical coherence tomography-derived shape and texture features are associated with development of sub-foveal geographic atrophy in dry AMD

Geographic atrophy (GA) is an advanced form of dry age-related macular degeneration (AMD) that leads to progressive and irreversible vision loss. Identifying patients with greatest risk of GA progression is important for targeted utilization of emerging therapies. This study aimed to comprehensively evaluate the role of shape-based fractal dimension features ( F fd ) of sub-retinal pigment epithelium (sub-RPE) compartment and texture-based radiomics features ( F t ) of Ellipsoid Zone (EZ)-RPE and sub-RPE compartments for risk stratification for subfoveal GA (sfGA) progression. This was a retrospective study of 137 dry AMD subjects with a 5-year follow-up. Based on sfGA status at year 5, eyes were categorized as Progressors and Non-progressors. A total of 15 shape-based F fd of sub-RPE surface and 494 F t from each of sub-RPE and EZ-RPE compartments were extracted from baseline spectral domain-optical coherence tomography scans. The top nine features were identified from F fd and F t feature pool separately using minimum Redundancy maximum Relevance feature selection and used to train a Random Forest (RF) classifier independently using three-fold cross validation on the training set ( S t , N = 90) to distinguish between sfGA Progressors and Non-progressors. Combined F fd and F t was also evaluated in predicting risk of sfGA progression. The RF classifier yielded AUC of 0.85, 0.79 and 0.89 on independent test set ( S v , N = 47) using F fd , F t , and their combination, respectively. Using combined F fd and F t , the improvement in AUC was statistically significant on S v with p-values of 0.032 and 0.04 compared to using only F fd and only F t , respectively. Combined F fd and F t appears to identify high-risk patients. Our results show that FD and texture features could be potentially used for predicting risk of sfGA progression and future therapeutic response.

Multimodal imaging and deep learning in geographic atrophy secondary to age-related macular degeneration

Geographic atrophy (GA) secondary to age-related macular degeneration is among the most common causes of irreversible vision loss in industrialized countries. Recently, two therapies have been approved by the US FDA. However, given the nature of their treatment effect, which primarily involves a relative decrease in disease progression, discerning the individual treatment response at the individual level may not be readily apparent. Thus, clinical decision-making may have to rely on the quantification of the slope of GA progression before and during treatment. A panel of imaging modalities and artificial intelligence (AI)-based algorithms are available for such quantifications. This article aims to provide a comprehensive overview of the fundamentals of GA imaging, the procedures for diagnosis and classification using these images, and the cutting-edge role of AI algorithms in automatically deriving diagnostic and prognostic insights from imaging data.

Novel Fractal-Based Sub-RPE Compartment OCT Radiomics Biomarkers Are Associated With Subfoveal Geographic Atrophy in Dry AMD

OBJECTIVE

The purpose of this study was to quantitatively characterize the shape of the sub-retinal pigment epithelium (sub-RPE, i.e., space bounded by RPE and Bruch's membrane) compartment on SD-OCT using fractal dimension (FD) features and evaluate their impact on risk of subfoveal geographic atrophy (sfGA) progression.

METHODS

This was an IRB-approved retrospective study of 137 subjects with dry age-related macular degeneration (AMD) with subfoveal GA. Based on sfGA status at year five, eyes were categorized as "Progressors" and "Non-progressors". FD analysis allows quantification of the degree of shape complexity and architectural disorder associated with a structure. To characterize the structural irregularities along the sub-RPE surface between the two groups of patients, a total of 15 shape descriptors of FD were extracted from the sub-RPE compartment of baseline OCT scans. The top four features were identified using minimum Redundancy maximum Relevance (mRmR) feature selection method and evaluated with Random Forest (RF) classifier using three-fold cross validation from the training set (N = 90). Classifier performance was subsequently validated on the independent test set (N = 47).

RESULTS

Using the top four FD features, a RF classifier yielded an AUC of 0.85 on the independent test set. Mean fractal entropy (p-value = 4.8e-05) was identified as the most significant biomarker; higher values of entropy being associated with greater shape disorder and risk for sfGA progression.

CONCLUSIONS

FD assessment holds promise for identifying high-risk eyes for GA progression.

SIGNIFICANCE

With further validation, FD features could be potentially used for clinical trial enrichment and assessments for therapeutic response in dry AMD patients.

Geographic Atrophy Segmentation Using Multimodal Deep Learning

Purpose

To examine deep learning (DL)-based methods for accurate segmentation of geographic atrophy (GA) lesions using fundus autofluorescence (FAF) and near-infrared (NIR) images.

Methods

This retrospective analysis utilized imaging data from study eyes of patients enrolled in Proxima A and B (NCT02479386; NCT02399072) natural history studies of GA. Two multimodal DL networks (UNet and YNet) were used to automatically segment GA lesions on FAF; segmentation accuracy was compared with annotations by experienced graders. The training data set comprised 940 image pairs (FAF and NIR) from 183 patients in Proxima B; the test data set comprised 497 image pairs from 154 patients in Proxima A. Dice coefficient scores, Bland-Altman plots, and Pearson correlation coefficient (r) were used to assess performance.

Results

On the test set, Dice scores for the DL network to grader comparison ranged from 0.89 to 0.92 for screening visit; Dice score between graders was 0.94. GA lesion area correlations (r) for YNet versus grader, UNet versus grader, and between graders were 0.981, 0.959, and 0.995, respectively. Longitudinal GA lesion area enlargement correlations (r) for screening to 12 months (n = 53) were lower (0.741, 0.622, and 0.890, respectively) compared with the cross-sectional results at screening. Longitudinal correlations (r) from screening to 6 months (n = 77) were even lower (0.294, 0.248, and 0.686, respectively).

Conclusions

Multimodal DL networks to segment GA lesions can produce accurate results comparable with expert graders.

Translational Relevance

DL-based tools may support efficient and individualized assessment of patients with GA in clinical research and practice.

Detection of macular atrophy in age-related macular degeneration aided by artificial intelligence

INTRODUCTION

Age-related macular degeneration (AMD) is a leading cause of irreversible visual impairment worldwide. The endpoint of AMD, both in its dry or wet form, is macular atrophy (MA) which is characterized by the permanent loss of the RPE and overlying photoreceptors either in dry AMD or in wet AMD. A recognized unmet need in AMD is the early detection of MA development.

AREAS COVERED

Artificial Intelligence (AI) has demonstrated great impact in detection of retinal diseases, especially with its robust ability to analyze big data afforded by ophthalmic imaging modalities, such as color fundus photography (CFP), fundus autofluorescence (FAF), near-infrared reflectance (NIR), and optical coherence tomography (OCT). Among these, OCT has been shown to have great promise in identifying early MA using the new criteria in 2018.

EXPERT OPINION

There are few studies in which AI-OCT methods have been used to identify MA; however, results are very promising when compared to other imaging modalities. In this paper, we review the development and advances of ophthalmic imaging modalities and their combination with AI technology to detect MA in AMD. In addition, we emphasize the application of AI-OCT as an objective, cost-effective tool for the early detection and monitoring of the progression of MA in AMD.

FUNDUS AUTOFLUORESCENCE IN EXTENSIVE MACULAR ATROPHY WITH PSEUDODRUSEN AND DIFFUSE TRICKLING GEOGRAPHIC ATROPHY

PURPOSE

To establish whether extensive macular atrophy with pseudodrusen (EMAP) can be distinguished from the diffuse-trickling phenotype of geographic atrophy (DTGA) secondary to age-related macular degeneration on the basis of its features on blue-light autofluorescence.

METHODS

The authors reviewed our prospectively maintained database to enroll patients with a diagnosis of EMAP, DTGA, and non-DTGA with a minimum follow-up of 1 year. Atrophic areas and growth rates were measured on blue-light autofluorescence images, using the Heidelberg Region Finder tool. Circularity and roundness were chosen as atrophy shape descriptors, extracted using ImageJ, and compared between disease groups.

RESULTS

A total of 28 EMAP, 27 DTGA, and 30 non-DTGA eyes were included in the analysis. The median follow-up time was around 3.5 years. Extensive macular atrophy with pseudodrusen was characterized by an irregular and elongated shape (low circularity and low roundness) and associated with a fast atrophy growth rate (3.6 mm 2 /year), compared with non-DTGA. However, these parameters were not significantly different between EMAP and DTGA.

CONCLUSION

Our study found that EMAP and DTGA cannot be effectively differentiated on fundus autofluorescence. In both diseases, the macular atrophic area has a major vertical axis, fringed borders, and fast progression.

Identifying geographic atrophy

PURPOSE OF REVIEW

Age-related macular degeneration (AMD) is one of the leading causes of blindness and can progress to geographic atrophy (GA) in late stages of disease. This review article highlights recent literature which assists in the accurate and timely identification of GA, and monitoring of GA progression.

RECENT FINDINGS

Technology for diagnosing and monitoring GA has made significant advances in recent years, particularly regarding the use of optical coherence tomography (OCT). Identification of imaging features which may herald the development of GA or its progression is critical. Deep learning applications for OCT in AMD have shown promising growth over the past several years, but more prospective studies are needed to demonstrate generalizability and clinical utility.

SUMMARY

Identification of GA and of risk factors for GA development or progression is essential when counseling AMD patients and discussing prognosis. With new therapies on the horizon for the treatment of GA, identification of risk factors for the development and progression of GA will become critical in determining the patients who would be appropriate candidates for new targeted therapies.

Deep Learning to Predict Geographic Atrophy Area and Growth Rate from Multimodal Imaging

OBJECTIVE

To develop deep learning models for annualized geographic atrophy (GA) growth rate prediction using fundus autofluorescence (FAF) images and spectral-domain OCT volumes from baseline visits, which can be used for prognostic covariate adjustment to increase power of clinical trials.

DESIGN

This retrospective analysis estimated GA growth rate as the slope of a linear fit on all available measurements of lesion area over a 2-year period. Three multitask deep learning models-FAF-only, OCT-only, and multimodal (FAF and OCT)-were developed to predict concurrent GA area and annualized growth rate.

PARTICIPANTS

Patients were from prospective and observational lampalizumab clinical trials.

METHODS

The 3 models were trained on the development data set, tested on the holdout set, and further evaluated on the independent test sets. Baseline FAF images and OCT volumes from study eyes of patients with bilateral GA (NCT02247479; NCT02247531; and NCT02479386) were split into development (1279 patients/eyes) and holdout (443 patients/eyes) sets. Baseline FAF images from study eyes of NCT01229215 (106 patients/eyes) and NCT02399072 (169 patients/eyes) were used as independent test sets.

MAIN OUTCOME MEASURES

Model performance was evaluated using squared Pearson correlation coefficient (r²) between observed and predicted lesion areas/growth rates. Confidence intervals were calculated by bootstrap resampling (B = 10 000).

RESULTS

On the holdout data set, r² (95% confidence interval) of the FAF-only, OCT-only, and multimodal models for GA lesion area prediction was 0.96 (0.95-0.97), 0.91 (0.87-0.95), and 0.94 (0.92-0.96), respectively, and for GA growth rate prediction was 0.48 (0.41-0.55), 0.36 (0.29-0.43), and 0.47 (0.40-0.54), respectively. On the 2 independent test sets, r² of the FAF-only model for GA lesion area was 0.98 (0.97-0.99) and 0.95 (0.93-0.96), and for GA growth rate was 0.65 (0.52-0.75) and 0.47 (0.34-0.60).

CONCLUSIONS

We show the feasibility of using baseline FAF images and OCT volumes to predict individual GA area and growth rates using a multitask deep learning approach. The deep learning-based growth rate predictions could be used for covariate adjustment to increase power of clinical trials.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found after the references.

Quantitative multimodal imaging of extensive macular atrophy with pseudodrusen and geographic atrophy with diffuse trickling pattern

To compare clinical and imaging characteristics of extensive macular atrophy with pseudodrusen-like appearance (EMAP) versus diffuse-trickling geographic atrophy (DTGA) and non-diffuse-trickling geographic atrophy (nDTGA) phenotypes of age-related macular degeneration. Prospective, observational study performed in the Ophthalmology Department of IRCCS San Raffaele Hospital between January 2015 and January 2021. Patients examination included fundus autofluorescence (FAF) and optical coherence tomography at baseline and follow-up visits. We measured subfoveal choroidal thickness (SCT), Sattler/choroid ratio (SCR), choroidal vascularity index and ellipsoid zone disruption distance on OCT scans. We calculated progression rates and circularity of the atrophic lesions on FAF images. These variables were compared between the three groups and correlations with progression rates and visual acuity were assessed. Sixty-three eyes from 63 patients were included: 18 with EMAP, 18 with DTGA and 27 with nDTGA. Mean follow-up was 3.73 ± 2.12 years. EMAP and DTGA shared a faster progression, lower circularity and SCR, and higher EZ disruption distance than nDTGA, while SCT and CVI were similar between the three groups. Baseline circularity and SCR correlated with progression rates. EMAP and DTGA show similar OCT and FAF characteristics, which differ from nDTGA.

Histologic Cell Shape Descriptors for the Retinal Pigment Epithelium in Age-Related Macular Degeneration: A Comparison to Unaffected Eyes

Purpose

Phenotype alterations of the retinal pigment epithelium (RPE) are a main characteristic of age-related macular degeneration (AMD). Individual RPE cell shape descriptors may help to delineate healthy from AMD-affected cells in early disease stages.

Methods

Twenty-two human RPE flatmounts (7 eyes with AMD [early, 3; geographic atrophy, 1; neovascular, 3); 15 unaffected eyes [8 aged ≤51 years; 7 aged >80 years)] were imaged at the fovea, perifovea, and near periphery (predefined sample locations) using a laser-scanning confocal fluorescence microscope. RPE cell boundaries were manually marked with computer assistance. For each cell, 11 shape descriptors were calculated and correlated with donor age, cell autofluorescence (AF) intensity, and retinal location. Statistical analysis was performed using an ensemble classifier based on logistic regression.

Results

In AMD, RPE was altered at all locations (most pronounced at the fovea), with area, solidity, and form factor being the most discriminatory descriptors. In the unaffected macula, aging had no significant effect on cell shape factors; however, with increasing distance to the fovea, area, solidity, and convexity increased while form factor decreased. Reduced AF in AMD was significantly associated with decreased roundness and solidity.

Conclusions

AMD results in an altered RPE with enlarged and deformed cells that could precede clinically visible lesions and thus serve as early biomarkers for AMD onset. Our data may also help guide the interpretation of RPE morphology in in vivo studies utilizing high-resolution single-cell imaging.

Translational Relevance

Our histologic RPE cell shape data have the ability to identify robust biomarkers for the early detection of AMD-affected cells, which also could serve as a basis for automated segmentation of RPE sheets.

Comparing Accuracies of Length-Type Geographic Atrophy Growth Rate Metrics Using Atrophy-Front Growth Modeling

Purpose

To compare the accuracies of the previously proposed square-root-transformed and perimeter-adjusted metrics for estimating length-type geographic atrophy (GA) growth rates.

Design

Cross-sectional and simulation-based study.

Participants

Thirty-eight eyes with GA from 27 patients.

Methods

We used a previously developed atrophy-front growth model to provide analytical and numerical evaluations of the square-root-transformed and perimeter-adjusted growth rate metrics on simulated and semisimulated GA growth data.

Main Outcome Measures

Comparison of the accuracies of the square-root-transformed and perimeter-adjusted metrics on simulated and semisimulated GA growth data.

Results

Analytical and numerical evaluations showed that the accuracy of the perimeter-adjusted metric is affected minimally by baseline lesion area, focality, and circularity over a wide range of GA growth rates. Average absolute errors of the perimeter-adjusted metric were approximately 20 times lower than those of the square-root-transformed metrics, per evaluation on a semisimulated dataset with growth rate characteristics matching clinically observed data.

Conclusions

Length-type growth rates have an intuitive, biophysical interpretation that is independent of lesion geometry, which supports their use in clinical trials of GA therapeutics. Taken in the context of prior studies, our analyses suggest that length-type GA growth rates should be measured using the perimeter-adjusted metric, rather than square-root-transformed metrics.

Beyond the neuron: Role of non-neuronal cells in stress disorders

Stress disorders are leading causes of disease burden in the U.S. and worldwide, yet available therapies are fully effective in less than half of all individuals with these disorders. Although to date, much of the focus has been on neuron-intrinsic mechanisms, emerging evidence suggests that chronic stress can affect a wide range of cell types in the brain and periphery, which are linked to maladaptive behavioral outcomes. Here, we synthesize emerging literature and discuss mechanisms of how non-neuronal cells in limbic regions of brain interface at synapses, the neurovascular unit, and other sites of intercellular communication to mediate the deleterious, or adaptive (i.e., pro-resilient), effects of chronic stress in rodent models and in human stress-related disorders. We believe that such an approach may one day allow us to adopt a holistic "whole body" approach to stress disorder research, which could lead to more precise diagnostic tests and personalized treatment strategies. Stress is a major risk factor for many psychiatric disorders. Cathomas et al. review new insight into how non-neuronal cells mediate the deleterious effects, as well as the adaptive, protective effects, of stress in rodent models and human stress-related disorders.

Progression of cRORA (Complete RPE and Outer Retinal Atrophy) in Dry Age-Related Macular Degeneration Measured Using SD-OCT

Purpose

The purpose of this study was to evaluate the long-term rate of progression and baseline predictors of geographic atrophy (GA) using complete retinal pigment epithelium and outer retinal atrophy (cRORA) annotation criteria.

Methods

This is a retrospective study. Columns of GA were manually annotated by two graders using a self-developed software on optical coherence tomography (OCT) B-scans and projected onto the infrared images. The primary outcomes were: (1) rate of area progression, (2) rate of square root area progression, and (3) rate of radial progression towards the fovea. The effects of 11 additional baseline predictors on the primary outcomes were analyzed: total area, focality (defined as the number of lesions whose area is >0.05 mm2), circularity, total lesion perimeter, minimum diameter, maximum diameter, minimum distance from the center, sex, age, presence/absence of hypertension, and lens status.

Results

GA was annotated in 33 pairs of baseline and follow-up OCT scans from 33 eyes of 18 patients with dry age-related macular degeneration (AMD) followed for at least 6 months. The mean rate of area progression was 1.49 ± 0.86 mm2/year (P < 0.0001 vs. baseline), and the mean rate of square root area progression was 0.33 ± 0.15 mm/year (P < 0.0001 vs. baseline). The mean rate of radial progression toward the fovea was 0.07 ± 0.11 mm/year. A multiple variable linear regression model (adjusted r2 = 0.522) revealed that baseline focality and female sex were significantly correlated with the rate of GA area progression.

Conclusions

GA area progression was quantified using OCT as an alternative to conventional measurements performed on fundus autofluorescence images. Baseline focality correlated with GA area progression rate and lesion's minimal distance from the center correlated with GA radial progression rate toward the center. These may be important markers for the assessment of GA activity.

Translational Relevance

Advanced method linking specific retinal micro-anatomy to GA area progression analysis.

Local Geographic Atrophy Growth Rates Not Influenced by Close Proximity to Non-Exudative Type 1 Macular Neovascularization

Purpose

The local growth rates of geographic atrophy (GA) adjacent to non-exudative type 1 macular neovascularization (MNV) were investigated to determine if MNV influenced GA growth.

Methods

Eyes with GA and non-exudative type 1 MNV were followed for at least 1 year. Both GA and the MNV were imaged and measured using swept-source optical coherence tomography angiography (SS-OCTA) scans. Pearson correlations were computed between local growth rates of GA, which were estimated using a biophysical GA growth model, and local distances-to-MNV. Corresponding P values for the null hypothesis of no Pearson correlation were computed using a Monte Carlo approach that adjusts for spatial autocorrelations.

Results

Nine eyes were included in this study. There were positive correlations (Pearson's r > 0) between distance-to-MNV and local GA growth in eight (89%) of the eyes; however, in all but one eye (11%), correlations were relatively weak and statistically nonsignificant after Bonferroni correction (corrected P > 0.05).

Conclusions

SS-OCTA imaging combined with GA growth modeling and spatial statistical analysis enabled quantitative assessment of correlations between local GA growth rates and local distances-to-MNV. Our results are not consistent with non-exudative type 1 MNV having a strong inhibitory effect on local GA growth rates.

Risk Classification for Progression to Subfoveal Geographic Atrophy in Dry Age-Related Macular Degeneration Using Machine Learning-Enabled Outer Retinal Feature Extraction

BACKGROUND AND OBJECTIVE

To evaluate the utility of spectral-domain optical coherence tomography biomarkers to predict the development of subfoveal geographic atrophy (sfGA).

PATIENTS AND METHODS

This was a retrospective cohort analysis including 137 individuals with dry age-related macular degeneration without sfGA with 5 years of follow-up. Multiple spectral-domain optical coherence tomography quantitative metrics were generated, including ellipsoid zone (EZ) integrity and subretinal pigment epithelium (sub-RPE) compartment features.

RESULTS

Reduced mean EZ-RPE central subfield thickness and increased sub-RPE compartment thickness were significantly different between sfGA convertors and nonconvertors at baseline in both 2-year and 5-year sfGA risk assessment. Longitudinal change assessment showed a significantly higher degradation of EZ integrity in sfGA convertors. The predictive performance of a machine learning classification model based on 5-year and 2-year risk conversion to sfGA demonstrated an area under the receiver operating characteristic curve of 0.92 ± 0.06 and 0.96 ± 0.04, respectively.

CONCLUSIONS

Quantitative outer retinal and sub-RPE feature assessment using a machine learning-enabled retinal segmentation platform provides multiple parameters that are associated with progression to sfGA. [Ophthalmic Surg Lasers Imaging. 2022;53:31-39.].

Association of Reading Performance in Geographic Atrophy Secondary to Age-Related Macular Degeneration With Visual Function and Structural Biomarkers

Importance

As a disabling and frequent disease, geographic atrophy secondary to age-related macular degeneration (AMD) constitutes an important study subject. Emerging clinical trials require suitable end points. The characterization and validation of reading performance as a functional outcome parameter is warranted.

Objective

To prospectively evaluate reading performance in geographic atrophy and to assess its association with established visual function assessments and structural biomarkers.

Design, Setting, and Participants

The noninterventional, prospective natural history Directional Spread in Geographic Atrophy study included patients with geographic atrophy secondary to AMD who were recruited at the University Hospital in Bonn, Germany. Participants were enrolled from June 2013 to June 2016. Analysis began December 2019 and ended January 2021.

Main Outcomes and Measures

Reading acuity and reading speed were assessed using Radner charts. Longitudinal fundus autofluorescence and infrared reflectance images were semiautomatically annotated for geographic atrophy, followed by extraction of shape-descriptive variables. Linear mixed-effects models were applied to investigate the association of those variables with reading performance.

Results

A total of 150 eyes of 85 participants were included in this study (median [IQR] age, 77.9 [72.4-82.1] years; 51 women [60%]; 34 men [40%]). Reading performance was impaired with a median (IQR) monocular reading acuity of 0.9 (0.4-1.3) logarithm of the reading acuity determination and a reading speed of 52.8 (0-123) words per minute. In the multivariable cross-sectional analysis, best-corrected visual acuity, area of geographic atrophy in the central Early Treatment Diabetic Retinopathy Study (ETDRS) subfield, classification of noncenter vs center-involving geographic atrophy, and area of geographic atrophy in the inner-right ETDRS subfield showed strongest associations with reading acuity (cross-validated R2for reading acuity = 0.69). Regarding reading speed, the most relevant variables were best-corrected visual acuity, low-luminance visual acuity, area of geographic atrophy in the central ETDRS subfield, in the inner-right ETDRS subfield, and in the inner-upper ETDRS subfield (R2 for reading speed = 0.67). In the longitudinal analysis, a similar prediction accuracy for reading performance was determined (R2 for reading acuity = 0.73; R2 for reading speed = 0.70). Prediction accuracy did not improve when follow-up time was added as an independent variable. Binocular reading performance did not differ from reading performance in the better-seeing eye.

Conclusions and Relevance

The association of reading acuity and speed with visual functional and structural biomarkers supports the validity of reading performance as a meaningful end point in clinical trials. These findings suggest that measures in clinical and low-vision care for patients with geographic atrophy should focus primarily on the better-seeing eye.

Local Progression Kinetics of Geographic Atrophy Depends Upon the Border Location

Purpose

To assess the influence of lesion morphology and location on geographic atrophy (GA) growth rate.

Methods

We manually delineated GA on color fundus photographs of 237 eyes in the Age-Related Eye Disease Study. We calculated local border expansion rate (BER) as the linear distance that a point on the GA border traveled over 1 year based on a Euclidean distance map. Eye-specific BER was defined as the mean local BER of all points on the GA border in an eye. The percentage area affected by GA was defined as the GA area divided by the total retinal area in the region.

Results

GA enlarged 1.51 ± 1.96 mm2 in area and 0.13 ± 0.11 mm in distance over 1 year. The GA area growth rate (mm2/y) was associated with the baseline GA area (P < 0.001), perimeter (P < 0.001), lesion number (P < 0.001), and circularity index (P < 0.001); in contrast, eye-specific BER (mm/y) was not significantly associated with any of these factors. As the retinal eccentricity increased from 0 to 3.5 mm, the local BER increased from 0.10 to 0.24 mm/y (P < 0.001); in contrast, the percentage of area affected by GA decreased from 49.3% to 2.3%.

Conclusions

Using distance-based measurements allows GA progression evaluation without significant confounding effects from baseline GA morphology. Local GA progression rates increased as a function of retinal eccentricity within the macula which is opposite of the trend for GA distribution, suggesting that GA initiation and enlargement may be mediated by different biological processes.

Growth Modeling for Quantitative, Spatially Resolved Geographic Atrophy Lesion Kinetics

Purpose

To demonstrate the applicability of a growth modeling framework for quantifying spatial variations in geographic atrophy (GA) lesion kinetics.

Methods

Thirty-eight eyes from 27 patients with GA secondary to age-related macular degeneration were imaged with a commercial swept source optical coherence tomography instrument at two visits separated by 1 year. Local GA growth rates were computed at 6-µm intervals along each lesion margin using a previously described growth model. Corresponding margin eccentricities, margin angles, and growth angles were also computed. The average GA growth rates conditioned on margin eccentricity, margin angle, growth angle, and fundus position were estimated via kernel regression.

Results

A total of 88,356 GA margin points were analyzed. The average GA growth rates exhibited a hill-shaped dependency on eccentricity, being highest in the 0.5 mm to 1.6 mm range and lower on either side of that range. Average growth rates were also found to be higher for growth trajectories oriented away from (smaller growth angle), rather than toward (larger growth angle), the foveal center. The dependency of average growth rate on margin angle was less pronounced, although lesion segments in the superior and nasal aspects tended to grow faster.

Conclusions

Our proposed growth modeling framework seems to be well-suited for generating accurate, spatially resolved GA growth rate atlases and should be confirmed on larger datasets.

Translational Relevance

Our proposed growth modeling framework may enable more accurate measurements of spatial variations in GA growth rates.

Model Structure Uncertainty in the Characterization and Growth of Geographic Atrophy

Purpose

To identify the most suitable model for assessing the rate of growth of total geographic atrophy (GA) by analysis of model structure uncertainty.

Methods

Model structure uncertainty refers to unexplained variability arising from the choice of mathematical model and represents an example of epistemic uncertainty. In this study, we quantified this uncertainty to help identify a model most representative of GA progression. Fundus autofluorescence (FAF) images and GA progression data (i.e., total GA area estimation at each presentation) were acquired using Spectralis HRA+OCT instrumentation and RegionFinder software. Six regression models were evaluated. Models were compared using various statistical tests, [i.e., coefficient of determination (r²), uncertainty metric (U), and test of significance for the correlation coefficient, r], as well as adherence to expected physical and clinical assumptions of GA growth.

Results

Analysis was carried out for 81 GA-affected eyes, 531 FAF images (range: 3–17 images per eye), over median of 57 months (IQR: 42, 74), with a mean baseline lesion size of 2.62 ± 4.49 mm² (range: 0.11–20.69 mm²). The linear model proved to be the most representative of total GA growth, with lowest average uncertainty (original scale: U = 0.025, square root scale: U = 0.014), high average r² (original scale: 0.92, square root scale: 0.93), and applicability of the model was supported by a high correlation coefficient, r, with statistical significance (P = 0.01).

Conclusions

Statistical analysis of uncertainty suggests that the linear model provides an effective and practical representation of the rate and progression of total GA growth based on data from patient presentations in clinical settings.

Translational Relevance

Identification of correct model structure to characterize rate of growth of total GA in the retina using FAF images provides an objective metric for comparing interventions and charting GA progression in clinical presentations.

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.

Geographic Atrophy Growth Is Strongly Related to Lesion Perimeter: Unifying Effects of Lesion Area, Number, and Circularity on Growth

PURPOSE

To investigate the underlying reason for the previously observed impact of baseline lesion size, number, and circularity on geographic atrophy (GA) growth rate.

DESIGN

Retrospective analysis of a multicenter, prospective, randomized controlled trial.

PARTICIPANTS

Age-Related Eye Disease Study participants with GA secondary to nonexudative age-related macular degeneration.

METHODS

We manually delineated atrophic lesions on color fundus photographs of 318 eyes with GA followed up over at least 2 visits (mean follow-up duration, 5.1 ± 3.0 years). We calculated GA area growth rate for each eye based on the first and last visit. GA perimeter-adjusted growth rate was defined as the ratio between GA area growth rate and mean GA perimeter between the first and last visit for each eye.

MAIN OUTCOME MEASURES

GA area growth rate, growth rate of the square root of GA area, and GA perimeter-adjusted growth rate.

RESULTS

GA area growth rate was correlated strongly with mean GA perimeter (r² = 0.66). GA area growth rate was associated with baseline GA area (r² = 0.39; P < 0.001), lesion number (r² = 0.10; P < 0.001), and circularity index (r² = 0.28; P < 0.001). The use of the square root of GA area reduced the influence of baseline GA area (but not lesion number or circularity) on GA growth rate. In comparison, GA perimeter-adjusted growth rate (0.098 ± 0.062 mm/year) was not correlated with baseline GA area (r² = 0.005; P = 0.20), lesion number (r² = 0.00009; P = 0.86), or circularity index (r² = 0.007; P = 0.14). GA perimeter-adjusted growth rate was 50.0% higher in eyes whose fellow eyes showed GA at any visit (0.102 ± 0.062 mm/year) than in eyes whose fellow eyes never demonstrated GA during follow-up (0.068 ± 0.049 mm/year).

CONCLUSIONS

The growth rate of GA area is associated strongly with lesion perimeter. This relationship explains the previously observed influences of baseline GA size, lesion number, and circularity on GA growth rate. GA perimeter-adjusted growth rate is uncorrelated with the 3 morphologic factors and may serve as a surrogate outcome measure to monitor GA progression in future studies.

PROGRESSION OF ABCA4-RELATED RETINOPATHY: Prognostic value of demographic, functional, genetic, and imaging parameters

PURPOSE

To investigate the prognostic value of demographic, functional, genetic, and imaging parameters on retinal pigment epithelium atrophy progression secondary to ABCA4-related retinopathy.

METHODS

Patients with retinal pigment epithelium atrophy secondary to ABCA4-related retinopathy were examined longitudinally with fundus autofluorescence imaging. Lesion area, perimeter, circularity, caliper diameters, and focality of areas with definitely decreased autofluorescence were determined. A model was used to predict the lesion enlargement rate based on baseline variables. Sample size calculations were performed to model the power in a simulated interventional study.

RESULTS

Sixty-eight eyes of 37 patients (age range, 14-78 years) with a follow-up time of 10 to 100 months were included. The mean annual progression of retinal pigment epithelium atrophy was 0.89 mm. The number of atrophic areas, the retina-wide functional impairment, and the age-of-onset category constituted significant predictors for future retinal pigment epithelium atrophy growth, explaining 25.7% of the variability. By extension of a simulated study length and/or specific patient preselection based on these baseline characteristics, the required sample size could significantly be reduced.

CONCLUSION

Trial design based on specific shape-descriptive factors and patients' baseline characteristics and the adaption of the trial duration may provide potential benefits in required cohort size and absolute number of visits.

[Artificial intelligence in ophthalmology : Guidelines for physicians for the critical evaluation of studies]

BACKGROUND

Empirical models have been an integral part of everyday clinical practice in ophthalmology since the introduction of the Sanders-Retzlaff-Kraff (SRK) formula. Recent developments in the field of statistical learning (artificial intelligence, AI) now enable an empirical approach to a wide range of ophthalmological questions with an unprecedented precision.

OBJECTIVE

Which criteria must be considered for the evaluation of AI-related studies in ophthalmology?

MATERIAL AND METHODS

Exemplary prediction of visual acuity (continuous outcome) and classification of healthy and diseased eyes (discrete outcome) using retrospectively compiled optical coherence tomography data (50 eyes of 50 patients, 50 healthy eyes of 50 subjects). The data were analyzed with nested cross-validation (for learning algorithm selection and hyperparameter optimization).

RESULTS

Based on nested cross-validation for training, visual acuity could be predicted in the separate test data-set with a mean absolute error (MAE, 95% confidence interval, CI of 0.142 LogMAR [0.077; 0.207]). Healthy versus diseased eyes could be classified in the test data-set with an agreement of 0.92 (Cohen's kappa). The exemplary incorrect learning algorithm and variable selection resulted in an MAE for visual acuity prediction of 0.229 LogMAR [0.150; 0.309] for the test data-set. The drastic overfitting became obvious on comparison of the MAE with the null model MAE (0.235 LogMAR [0.148; 0.322]).

CONCLUSION

Selection of an unsuitable measure of the goodness-of-fit, inadequate validation, or withholding of a null or reference model can obscure the actual goodness-of-fit of AI models. The illustrated pitfalls can help clinicians to identify such shortcomings.

Multimodal Imaging for the Assessment of Geographic Atrophy in Patients with "Foveal" and "No-Foveal" Sparing

INTRODUCTION

The aim of the study was to evaluate the applicability of optical coherence tomography (OCT) angiography (OCTA) for measuring geographic atrophy (GA) areas in age-related macular degeneration (AMD) patients with "foveal" and "no-foveal" sparing disease and compare it to other imaging modalities.

METHODS

A multimodal imaging protocol was applied, using infrared (IR) imaging, fundus autofluorescence (FAF), OCTA, and en-face OCT in 35 eyes of 23 AMD patients with GA. Patients were classified into 2 groups, with and without foveal sparing disease. GA area measurements for all imaging modalities were compared for each group separately.

RESULTS

The measured GA area was estimated to be 6.68 ± 3.18 mm2 using IR; 6.99 ± 3.09 mm2 using FAF; 6.56 ± 3.11 mm2 using OCTA, and 6.65 ± 3.14 mm2 using en-face OCT. There was no statistically significant difference in the GA area between different modalities (p = 0.977). When separate analysis was conducted for patients with "foveal" and "no-foveal" sparing disease, although GA measurements in FAF imaging displayed higher numerical values than the other modalities, especially in patients with foveal sparing, no statistically significant difference in the GA area was found between the different imaging modalities in either group (p = 0.816 for foveal sparing; p = 0.992 for no-foveal sparing group).

CONCLUSIONS

OCTA can be reliably used in the assessment of GA in AMD patients with and without foveal sparing disease. For both groups, measurements are comparable to IR, en-face OCT, and FAF, despite the fact that the latter recorded larger area of GA, mainly in the foveal sparing cases.

Artificial Intelligence Algorithms for Analysis of Geographic Atrophy: A Review and Evaluation

Purpose

The purpose of this study was to summarize and evaluate artificial intelligence (AI) algorithms used in geographic atrophy (GA) diagnostic processes (e.g. isolating lesions or disease progression).

Methods

The search strategy and selection of publications were both conducted in accordance with the Preferred of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. PubMed and Web of Science were used to extract literary data. The algorithms were summarized by objective, performance, and scope of coverage of GA diagnosis (e.g. lesion automation and GA progression).

Results

Twenty-seven studies were identified for this review. A total of 18 publications focused on lesion segmentation only, 2 were designed to detect and classify GA, 2 were designed to predict future overall GA progression, 3 focused on prediction of future spatial GA progression, and 2 focused on prediction of visual function in GA. GA-related algorithms reported sensitivities from 0.47 to 0.98, specificities from 0.73 to 0.99, accuracies from 0.42 to 0.995, and Dice coefficients from 0.66 to 0.89.

Conclusions

Current GA-AI publications have a predominant focus on lesion segmentation and a minor focus on classification and progression analysis. AI could be applied to other facets of GA diagnoses, such as understanding the role of hyperfluorescent areas in GA. Using AI for GA has several advantages, including improved diagnostic accuracy and faster processing speeds.

Translational Relevance

AI can be used to quantify GA lesions and therefore allows one to impute visual function and quality-of-life. However, there is a need for the development of reliable and objective models and software to predict the rate of GA progression and to quantify improvements due to interventions.

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.

Determinants of Quality of Life in Geographic Atrophy Secondary to Age-Related Macular Degeneration

Purpose

To longitudinally evaluate vision-related quality of life (VRQoL) in geographic atrophy (GA) secondary to age-related macular degeneration (AMD) and define its relation to visual function and structural biomarkers.

Methods

Patients with GA secondary to AMD were recruited in the context of the prospective, non-interventional, natural-history Directional Spread in Geographic-Atrophy study (NCT02051998). Fundus autofluorescence and infrared reflectance images were semi-automatically annotated for GA. Linear mixed-effects models were applied to investigate the association of putative determinants with the National Eye Institute Visual Function Questionnaire 25 (NEI VFQ-25) VRQoL.

Results

A total of 87 patients with a mean age ± SD of 77.07 ± 7.49 years were included in the analysis. At baseline, median (IQR) best-corrected visual acuity (BCVA) was 0.3 (0.51) for the better eye and 0.89 (0.76) for the worse eye; 46% of the patients showed binocular and 25.3% monocular non-central GA. The VRQoL composite score was impaired: 69.96 (24.03). Sixty-six patients with a median of 2 (2) follow-up visits after 1.08 (0.78) years were examined longitudinally.

Conclusions

Vision-related quality of life is significantly impaired in patients with GA secondary to AMD. The cross-sectional and longitudinal association of VRQoL with visual functional and structural biomarkers supports the validity of the NEI VFQ-25 VRQoL.

Progression of Unifocal versus Multifocal Geographic Atrophy in Age-Related Macular Degeneration: A Systematic Review and Meta-analysis

TOPIC

Determining the natural history of unifocal versus multifocal geographic atrophy (GA) secondary to nonexudative age-related macular degeneration.

CLINICAL RELEVANCE

The association between GA focality (i.e., unifocal vs. multifocal lesions) and enlargement rate is inconsistent in the literature. Some studies report a comparable growth rate between unifocal and multifocal GA, whereas others suggest the growth rate varies widely between the 2 groups.

METHODS

We searched 5 literature databases up to May 3, 2019, for studies that classified treatment-naïve GA patients based on lesion focality. We performed a random effects meta-analysis to determine the growth rates of GA. To account for different entry times among cohorts, we introduced a horizontal translation factor to the dataset of each cohort. Heterogeneity and study quality were assessed using the I2 statistic and Quality in Prognosis Studies tool, respectively. Publication bias was evaluated by funnel plots and the Egger test.

RESULTS

We included 12 studies with 3489 eyes from 3001 patients. After the introduction of translation factors, the effective radius of unifocal and multifocal GA enlarged linearly over approximately 7 years. The effective radius growth rate of multifocal GA (0.199±0.012 mm/year) was 46.3% higher than the growth rate of unifocal GA (0.136±0.008 mm/year; P < 0.001). Interestingly, unifocal and multifocal GA lesions with the same total baseline area grew at vastly different rates, with an estimated ratio of the growth rate as 1.46 (between 2 and 3). This difference disappeared after we accounted for different baseline total perimeters between unifocal and multifocal groups. The measured GA growth rate was consistent across studies using color fundus photography, fundus autofluorescence, or OCT (P = 0.35-0.99).

CONCLUSIONS

The effective radius of GA enlarges linearly and steadily over time in both unifocal and multifocal GA. The lesion focality is a significant prognostic factor for the GA effective radius growth rate. We propose that the growth rate of GA area is directly proportional to the total lesion perimeter (a measure of the number of retinal pigment epithelium cells exposed at the lesion border). Additional studies are needed to understand the cellular mechanisms underlying this relationship.

Optical Coherence Tomography-Angiography in Geographic Atrophy

Geographic atrophy (GA) represents the non-exudative late stage of age-related macular degeneration and constitutes a leading cause of legal blindness in the developed world. It is characterized by areas of loss of outer retinal layers including photoreceptors, degeneration of the retinal pigment epithelium, and rarefication of the choriocapillaris. As all three layers are functionally connected, the precise temporal sequence and relative contribution of these layers towards the development and progression of GA is unclear. The advent of optical coherence tomography angiography (OCT-A) has allowed for three-dimensional visualization of retinal blood flow. Using OCT-A, recent studies have demonstrated that choriocapillaris flow alterations are particularly associated with the development of GA, exceed atrophy boundaries spatially, and are a prognostic factor for future GA progression. Furthermore, OCT-A may be helpful to differentiate GA from mimicking diseases. Evidence for a potential protective effect of specific forms of choroidal neovascularization in the context of GA has been reported. This article aims to give a comprehensive review of the current literature concerning the application of OCT-A in GA, and summarizes the opportunities and limitations with regard to pathophysiologic considerations, differential diagnosis, study design, and patient assessment.

Factors Influencing Retinal Pigment Epithelium-Atrophy Progression Rate in Stargardt Disease

Purpose

To evaluate demographic, clinical, imaging, and genetic factors associated with retinal pigment epithelium enlargement in Stargardt disease (STGD1) and to measure the agreement between short-wavelength fundus autofluorescence (SW-FAF) and near-infrared fundus autofluorescence (NIR-FAF).

Methods

Retrospective cohort study of patients with STGD1 with ≥2 gradable SW-FAF images. RPE-atrophy areas were measured on SW-FAF and NIR-FAF at each visit and regressed against time to obtain the rate of RPE-atrophy enlargement. Agreement between SW-FAF and NIR-FAF with regards to baseline atrophic areas and rates of enlargement was evaluated. Baseline factors predictive of faster SW-FAF RPE-atrophy enlargement were investigated with linear mixed models.

Results

Fifty-four eyes of 28 patients (median age: 45 years; 13 males) were included. SW-FAF and NIR-FAF agreed well for slow rates of RPE-atrophy progression, but agreement decreased as the rate increased. Median (interquartile range [IQR]) rate of RPE-atrophy expansion was 0.18 (0.10–0.85) mm²/year on SW-FAF and 0.24 (0.08–0.33) mm²/year on NIR-FAF. Larger baseline RPE-atrophy area (estimate: 0.057 mm²/year, P < 0.001), worse visual acuity (0.305 mm²/year, P = 0.005), multifocal disease (0.401 mm²/year, P = 0.02), and SW-FAF pattern (0.534 mm²/year, P =0 .03) were associated with a faster rate of progression (predictive R²: 0.65).

Conclusions

SW-FAF and NIR-FAF are not interchangeable in the evaluation of RPE-atrophy enlargement, and both imaging modalities may be required for optimal detection of disease progression. A multivariable model based on baseline clinical and imaging information may identify patients at higher risk of fast disease progression.

Translational Relevance

The knowledge of the agreement of different FAF modalities, the estimated rates of RPE-atrophy enlargement, and factors predictive of faster anatomic decay in STGD1 may allow tailored clinical management and better clinical trials design.

Progression of Retinopathy Secondary to Maternally Inherited Diabetes and Deafness - Evaluation of Predicting Parameters

PURPOSE

To investigate the prognostic value of demographic, functional, and imaging parameters on retinal pigment epithelium (RPE) atrophy progression secondary to maternally inherited diabetes and deafness (MIDD) and to evaluate the application of these factors in clinical trial design.

DESIGN

Retrospective observational case series.

METHODS

Thirty-five eyes of 20 patients (age range, 24.9-75.9 years) with genetically proven MIDD and demarcated RPE atrophy on serial fundus autofluorescence (AF) images were included. Lesion size and shape-descriptive parameters were longitudinally determined by 2 independent readers. A linear mixed-effect model was used to predict the lesion enlargement rate based on baseline variables. Sample size calculations were performed to model the power in a simulated interventional study.

RESULTS

The mean follow-up time was 4.27 years. The mean progression rate of RPE atrophy was 2.33 mm²/year, revealing a dependence on baseline lesion size (+0.04 [0.02-0.07] mm²/year/mm², P < .001), which was absent after square root transformation. The fovea was preserved in the majority of patients during the observation time. In the case of foveal involvement, the loss of visual acuity lagged behind central RPE atrophy in AF images. Sex, age, and number of atrophic foci predicted future progression rates with a cross-validated mean absolute error of 0.13 mm/year and to reduce the required sample size for simulated interventional trials.

CONCLUSIONS

Progressive RPE atrophy could be traced in all eyes using AF imaging. Shape-descriptive factors and patients' baseline characteristics had significant prognostic value, guiding appropriate subject selection and sample size in future interventional trial design.

Prognostic value of intermediate age-related macular degeneration phenotypes for geographic atrophy progression

BACKGROUND

To characterise early stages of geographic atrophy (GA) development in age-related macular degeneration (AMD) and to determine the prognostic value of structural precursor lesions in eyes with intermediate (i) AMD on the subsequent GA progression.

METHODS

Structural precursor lesions for atrophic areas (lesion size at least 0.5 mm² in fundus autofluorescence images) were retrospectively identified based on multimodal imaging and evaluated for association with the subsequent GA enlargement rates (square-root transformed, sqrt). A linear mixed-effects model was used to account for the hierarchical nature of the data with a Tukey post hoc test to assess the impact of the local precursor on the subsequent GA progression rate.

RESULTS

A total of 39 eyes with GA of 34 patients with a mean age of 74.4±6.7 (±SD) years were included in this study. Five precursor lesions (phenotypes 1-5) preceding GA development were identified: large, sub-retinal pigment epithelial drusen (n=19), reticular pseudodrusen (RPD, n=10), refractile deposits (n=4), pigment epithelial detachment (n=4) and vitelliform lesions (n=2). Precursor lesions exhibited a significant association with the subsequent (sqrt) GA progression rates (p=0.0018) with RPD (phenotype 2) being associated with the fastest GA enlargement (2.29±0.52 (±SE) mm/year.

CONCLUSIONS

The results indicate the prognostic relevance of iAMD phenotyping for subsequent GA progression highlighting the role of structural AMD features across different AMD stages.

Relationship between proximity of choriocapillaris flow deficits and enlargement rate of geographic atrophy

PURPOSE

To correlate choriocapillaris (CC) flow deficits (FD) in eyes with geographic atrophy (GA) at various distances from the border of the GA lesion with yearly enlargement rate (yER) of GA.

METHODS

In this retrospective study, spectral domain optical coherence tomography (SD-OCT) and SD optical coherence tomography angiography (OCTA) images were collected from patients with GA, who were imaged at Doheny Eye Centers between 2016 and 2018, using the Cirrus HD-OCT (Carl Zeiss Meditec, Dublin, CA). All enrolled patients had one baseline 6 × 6 mm OCTA scan and two 6 × 6 mm SD-OCT cubes, one at baseline and one at a follow-up visit at least 12 months later. The border of the GA was manually outlined on the en face OCT fundus image and the yER was calculated after square root transformation. A grid composed of 100-μm-wide successive concentric rings was created around the GA lesion on the OCTA CC slab using ImageJ and the FD% was calculated from the binarized image. FD% from each ring was correlated with the yER of GA.

RESULTS

Thirty eyes of 22 patients were included in the study. The mean yER was 0.2 ± 0.15 mm. The FD% in the first five rings (from 0 to 500 μm from the border of GA) was significantly correlated with the yER. However, there was no statistically significant correlation between the yER and CC FD% beyond 500 μm from the GA lesion.

CONCLUSIONS

Only the choriocapillaris FD% in the 500-μm region immediately surrounding GA lesions appears to predict the rate of enlargement of these lesions.

Outer Retinal Thickness and Fundus Autofluorescence in Geographic Atrophy

PURPOSE

Most studies of fundus autofluorescence (FAF) in geographic atrophy (GA) have been nonquantitative, with inadequate registration of image modalities. Furthermore, as pointed out in the recent Consensus Definition for Atrophy Associated with Age-Related Macular Degeneration on OCT, it is unclear whether decreased FAF would be correlated exclusively with a single category of OCT-defined atrophy. We sought to determine how FAF intensity in eyes with GA correlates with structural changes of the outer retina and choroid as seen on co-registered spectral domain OCT (SD-OCT) images.

DESIGN

Retrospective cross-sectional.

PARTICIPANTS

Twenty eyes of 11 patients with GA secondary to non-neovascular age-related macular degeneration (AMD).

METHODS

Spectral domain OCT and FAF images for each eye were co-registered using MATLAB (MathWorks Inc, Natick, MA). On B-scans, the choroid, retinal pigment epithelium (RPE), photoreceptor (PR) layer, and outer nuclear layer (ONL) were segmented. Regions of interest (ROIs) including all atrophic and border regions were selected manually on the FAF scans. Regions of interest were subdivided into quartiles of FAF level to correlate with retinal thickness measurements taken along the B-scans. Mean choroid, RPE, PR, and ONL thicknesses were compared across quartiles using an analysis of variance factorial design testing for interaction effects, adjusted for repeated measures (on both eyes) with a within-subjects factor.

RESULTS

Seventeen eyes of 10 patients were selected for analysis. The mean choroidal thicknesses were not significantly different across FAF quartiles, but the overall differences in mean RPE, PR layer, and ONL thicknesses across quartiles were statistically significant (analysis of variance, P < 0.001, P < 0.001, and P = 0.015, respectively). Post hoc analysis demonstrated significant differences in thickness among quartiles 1, 2, and 3 for the RPE and PR layers (Tukey, P < 0.01 in each case). The FAF quartiles within GA did not correlate exclusively with single categories of Consensus Definition for Atrophy Associated with Age-Related Macular Degeneration-defined atrophy.

CONCLUSIONS

Not only RPE but also PR layer thickness on SD-OCT varies significantly with FAF levels in GA. This suggests that although the RPE cells are losing thickness and function, evidenced by decreased FAF from fluorophores, delicate PR cells also succumb early in the disease process. These relationships should be pursued as a possibly better-detailed mechanism in GA.

Computational modeling of retinal hypoxia and photoreceptor degeneration in patients with age-related macular degeneration

Although drusen have long been acknowledged as a primary hallmark of dry age-related macular degeneration (AMD) their role in the disease remains unclear. We hypothesize that drusen accumulation increases the barrier to metabolite transport ultimately resulting in photoreceptor cell death. To investigate this hypothesis, a computational model was developed to evaluate steady-state oxygen distribution in the retina. Optical coherence tomography images from fifteen AMD patients and six control subjects were segmented and translated into 3D in silico representations of retinal morphology. A finite element model was then used to determine the steady-state oxygen distribution throughout the retina for both generic and patient-specific retinal morphology. Oxygen levels were compared to the change in retinal thickness at a later time point to observe possible correlations. The generic finite element model of oxygen concentration in the retina agreed closely with both experimental measurements from literature and clinical observations, including the minimal pathological drusen size identified by AREDS (64 μm). Modeling oxygen distribution in the outer retina of AMD patients showed a substantially stronger correlation between hypoxia and future retinal thinning (Pearson correlation coefficient, r = 0.2162) than between drusen height and retinal thinning (r = 0.0303) indicating the potential value of this physiology-based approach. This study presents proof-of-concept for the potential utility of finite element modeling in evaluating retinal health and also suggests a potential link between transport and AMD pathogenesis. This strategy may prove useful as a prognostic tool for predicting the clinical risk of AMD progression.