INVESTIGATING A GROWTH PREDICTION MODEL IN ADVANCED AGE-RELATED MACULAR DEGENERATION WITH SOLITARY GEOGRAPHIC ATROPHY USING QUANTITATIVE AUTOFLUORESCENCE

A Novel Management Challenge in Age-Related Macular Degeneration: Artificial Intelligence and Expert Prediction of Geographic Atrophy

PURPOSE

The progression of geographic atrophy (GA) secondary to age-related macular degeneration is highly variable among individuals. Prediction of the progression is critical to identify patients who will benefit most from the first treatments currently approved. The aim of this study was to investigate the value and difference in predictive power between ophthalmologists and artificial intelligence (AI) in reliably assessing individual speed of GA progression.

DESIGN

Prospective, expert and AI comparison study.

PARTICIPANTS

Eyes with natural progression of GA from a prospective study (NCT02503332).

METHODS

Ophthalmologists predicted yearly growth speed of GA as well as selected the potentially faster-growing lesions from 2 eyes based on fundus autofluorescence (FAF), near-infrared reflectance (NIR), and OCT. A deep learning algorithm predicted progression solely on the baseline OCT (Spectralis, Heidelberg Engineering).

MAIN OUTCOME MEASURES

Accuracy, weighted κ, and concordance index (c-index) between the prediction made by ophthalmology specialists, ophthalmology residents, and the AI algorithm.

RESULTS

A total of 134 eyes of 134 patients from a phase II clinical trial were included; among them, 53 were from the sham arm, and 81 were from untreated fellow eyes. Four ophthalmologists performed 2880 gradings. Human experts reached an accuracy of 0.37, 0.43, and 0.41 and a κ of 0.06, 0.16, and 0.18 on FAF, NIR + OCT, and FAF + NIR + OCT, respectively. On a pairwise comparison task, human experts achieved a c-index of 0.62, 0.59, and 0.60. Automated AI-based analysis reached an accuracy of 0.48 and κ of 0.23 on the first task, and c-index of 0.69 on the second task solely utilizing OCT imaging.

CONCLUSIONS

Prediction of individual progression will become an important task for patient counseling, most importantly with the treatments becoming available. Human gradings improved with the availability of OCT. However, automated AI performed better than ophthalmologists in several comparisons. Artificial intelligence-supported decisions improve clinical precision, access to timely care for the community, and socioeconomic feasibility in the management of the leading cause of irreversible vision loss.

FINANCIAL DISCLOSURE(S)

The author(s) have no proprietary or commercial interest in any materials discussed in this article.

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.

Progression Rate of Macular Retinal Pigment Epithelium Atrophy in Geographic Atrophy and Selected Inherited Retinal Dystrophies. A Systematic Review and Meta-Analysis

PURPOSE

To compare the macular retinal pigment epithelium (RPE) atrophy progression rate of selected degenerative and macular inherited retinal diseases (IRD).

DESIGN

Systematic review and meta-analysis.

METHODS

The protocol was registered on the PROSPERO database. Medline, Embase, Web of Science, Cochrane Central Register of Controlled Trials, and Google Scholar were searched up to September 15, 2023 for articles reporting the RPE atrophy growth rate in treatment-naïve eyes with geographic atrophy (GA), Stargardt disease (STGD1), Best disease, pseudoxanthoma elasticum (PXE), central areolar choroidal dystrophy (CACD), or pattern dystrophies with no previous or current macular neovascularization and a minimum follow-up time of 12 months. Meta-analyses determined mean RPE atrophy growth rates per disease, imaging modality (fundus autofluorescence [FAF], optical coherence tomography [OCT], or color fundus photography [CFP]) and metric (mm2/y or mm/y). The Newcastle-Ottawa scale and the Cochrane Risk-of-Bias tool assessed the risk of bias, and funnel plots were used to evaluate small-study effects.

RESULTS

From 4354 publications, 85 were included for meta-analysis: 69 studies (7815 eyes) on GA, 15 (1367 eyes) on STGD1, and one on both. Two studies on PXE were only eligible for review. No studies for other diseases met our eligibility criteria. The overall mean RPE atrophy growth rate for GA using FAF was 1.65 mm2/y (95% confidence interval [CI], 1.49-1.81) and 0.35 mm/y (95% CI, 0.28-0.41); using OCT, it was 1.46 mm2/y (95% CI, 1.28-1.64) and 0.34 mm/y (95% CI, 0.28-0.40); and on CFP it was 1.76 mm2/y (95% CI, 1.56-1.97) and 0.30 mm/y (95% CI, 0.28-0.31). For STGD1, using FAF it was 1.0 mm2/y (95% CI, 0.77-1.23) and 0.20 mm/y (95% CI, 0.17-0.23); on OCT, it was 0.80 mm2/y (95% CI, 0.72-0.88). No studies on STGD1 reported the growth rate with other imaging modalities or metrics. Growth rates in GA were faster than in STGD1 (p < .05). A larger baseline area of atrophy was generally associated with faster growth rates.

CONCLUSIONS

The RPE atrophy growth rate in GA is faster than in STGD1 but with great variation between studies and imaging modalities. Limited information was available for other macular IRD, suggesting further research is needed.

AI in the clinical management of GA: A novel therapeutic universe requires novel tools

Regulatory approval of the first two therapeutic substances for the management of geographic atrophy (GA) secondary to age-related macular degeneration (AMD) is a major breakthrough following failure of numerous previous trials. However, in the absence of therapeutic standards, diagnostic tools are a key challenge as functional parameters in GA are hard to provide. The majority of anatomical biomarkers are subclinical, necessitating advanced and sensitive image analyses. In contrast to fundus autofluorescence (FAF), optical coherence tomography (OCT) provides high-resolution visualization of neurosensory layers, including photoreceptors, and other features that are beyond the scope of human expert assessment. Artificial intelligence (AI)-based methodology strongly enhances identification and quantification of clinically relevant GA-related sub-phenotypes. Introduction of OCT-based biomarker analysis provides novel insight into the pathomechanisms of disease progression and therapeutic, moving beyond the limitations of conventional descriptive assessment. Accordingly, the Food and Drug Administration (FDA) has provided a paradigm-shift in recognizing ellipsoid zone (EZ) attenuation as a primary outcome measure in GA clinical trials. In this review, the transition from previous to future GA classification and management is described. With the advent of AI tools, diagnostic and therapeutic concepts have changed substantially in monitoring and screening of GA disease. Novel technology combined with pathophysiological knowledge and understanding of the therapeutic response to GA treatments, is currently opening the path for an automated, efficient and individualized patient care with great potential to improve access to timely treatment and reduce health disparities.

Extensive macular atrophy with pseudodrusen-like appearance: comprehensive review of the literature

PURPOSE

This review focuses on extensive macular atrophy with pseudodrusen-like appearance (EMAP), a recently described maculopathy presenting with pseudodrusen-like lesions and chorioretinal atrophy more pronounced in the vertical axis.

METHODS

Narrative review of the literature published until May 2024.

RESULTS

The early onset age of EMAP (50-55 years) and its distinctive natural history, which includes night blindness followed by severe vision loss, differentiate it from atrophic age-related macular degeneration (AMD). A clear pathogenesis has not been determined, but risk factors include female gender and complement system abnormalities (altered levels of C3 and CH50). Moreover, lifelong exposure to pesticides has been suggested as risk factor for direct neuronal degeneration involving rods and cones. In the early phase of the disease, reticular pseudodrusen-like lesions appear in the superior perifovea and tend to coalescence horizontally into a flat, continuous, reflective material localized between the retinal pigmented epithelium and Bruch's membrane. Over time, EMAP causes profound RPE and outer retinal atrophy in the macular area, with a recent classification reporting a 3-stages evolution pattern. Blue autofluorescence showed rapidly evolving atrophy with either hyperautofluorescent or isoautofluorescent borders. Significant similarities between the diffuse-trickling phenotype of geographic atrophy and EMAP have been reported. Macular neovascularization is a possible complication.

CONCLUSION

EMAP is specific form of early-onset atrophic macular degeneration with rapid evolution and no treatment. Further studies are needed to assess the best management.

Quantitative Autofluorescence at AMD's Beginnings Highlights Retinal Topography and Grading System Differences: ALSTAR2 Baseline

INTRODUCTION

The aims of the study were to describe baseline quantitative (short-wavelength) autofluorescence (qAF) findings in a large pseudophakic cohort at age-related macular degeneration (AMD)'s beginnings and to assess qAF8 as an outcome measure and evaluate Age-Related Eye Disease Study (AREDS) and Beckman grading systems.

METHODS

In the ALSTAR2 baseline cohort (NCT04112667), 346 pseudophakic eyes of 188 persons (74.0 ± 5.5 years) were classified as normal (N = 160 by AREDS, 158 by Beckman), early AMD (eAMD) (N = 104, 66), and intermediate AMD (iAMD) (N = 82, 122). Groups were compared via mean qAF intensities in a 6°-8° annulus (qAF8) and maps of differences between observations and the overall mean, divided by standard deviation (Z-score).

RESULTS

qAF8 did not differ significantly among diagnostic groups by either stratification (p = 0.0869 AREDS; p = 0.0569 by Beckman). Notably, 45 eyes considered eAMD by AREDS became iAMD by Beckman. For AREDS-stratified eyes, Z-score maps showed higher centrally located qAF for normal, near the mean in eAMD, and lower values for iAMD. Maps deviated from this pattern for Beckman-stratified eyes.

CONCLUSIONS

In a large sample of pseudophakic eyes, qAF8 does not differ overall from normal aging to iAMD but also does not capture the earliest AMD activity in the macula lutea. AREDS classification gives results more consistent with a slow decline in histologic autofluorescence than Beckman classification.

Fundus autofluorescence of retinal atrophy progression between fundus flavimaculatus and extensive macular atrophy with pseudo-drusen

OBJECTIVE

To analyze the progression of macular atrophy in Fundus Flavimaculatus (FFM) versus Extensive Macular Atrophy with Pseudo-drusen (EMAP), using Spectralis® RegionFinder™ tool.

METHODS

Retrospective review of patients diagnosed with FFM and EMAP. Ophthalmic imaging features were reviewed by retina specialists for each patient in both eyes. The atrophic zones were measured on fundus autofluorescence acquisitions using the RegionFinder™ tool.

RESULTS

FFM group included 16 eyes of 8 patients, whose mean age was 61.42 ± 10.76 years, with a mean 4.54 ± 2.73 years of follow-up. EMAP group contained 16 eyes of 8 patients, whose mean age was 67.81 ± 3.03 years (p = 0.12), with a mean 3.62 ± 2.49 years of follow-up (P = 0.63). The atrophy progression rates were 3.73 ± 6.75 and 0.70 ± 0.98 mm2/year, for EMAP and FFM respectively. The yearly rate of progression of the atrophic areas in EMAP was 5.3 times higher than in FFM (mm2/year) (p = 0.03).

CONCLUSION

The progression of the atrophy in eyes with Extensive Macular Atrophy with Pseudo-drusen (EMAP) is significantly more rapid than in eyes with Fundus Flavimaculatus (FFM).

Learn Single-horizon Disease Evolution for Predictive Generation of Post-therapeutic Neovascular Age-related Macular Degeneration

BACKGROUND AND OBJECTIVE

Most of the existing disease prediction methods in the field of medical image processing fall into two classes, namely image-to-category predictions and image-to-parameter predictions.Few works have focused on image-to-image predictions. Different from multi-horizon predictions in other fields, ophthalmologists prefer to show more confidence in single-horizon predictions due to the low tolerance of predictive risk.

METHODS

We propose a single-horizon disease evolution network (SHENet) to predictively generate post-therapeutic SD-OCT images by inputting pre-therapeutic SD-OCT images with neovascular age-related macular degeneration (nAMD). In SHENet, a feature encoder converts the input SD-OCT images to deep features, then a graph evolution module predicts the process of disease evolution in high-dimensional latent space and outputs the predicted deep features, and lastly, feature decoder recovers the predicted deep features to SD-OCT images. We further propose an evolution reinforcement module to ensure the effectiveness of disease evolution learning and obtain realistic SD-OCT images by adversarial training.

RESULTS

SHENet is validated on 383 SD-OCT cubes of 22 nAMD patients based on three well-designed schemes (P-0, P-1 and P-M) based on the quantitative and qualitative evaluations. Three metrics (PSNR, SSIM, 1-LPIPS) are used here for quantitative evaluations. Compared with other generative methods, the generative SD-OCT images of SHENet have the highest image quality (P-0: 23.659, P-1: 23.875, P-M: 24.198) by PSNR. Besides, SHENet achieves the best structure protection (P-0: 0.326, P-1: 0.337, P-M: 0.349) by SSIM and content prediction (P-0: 0.609, P-1: 0.626, P-M: 0.642) by 1-LPIPS. Qualitative evaluations also demonstrate that SHENet has a better visual effect than other methods.

CONCLUSIONS

SHENet can generate post-therapeutic SD-OCT images with both high prediction performance and good image quality, which has great potential to help ophthalmologists forecast the therapeutic effect of nAMD.

Predicting Topographic Disease Progression and Treatment Response of Pegcetacoplan in Geographic Atrophy Quantified by Deep Learning

PURPOSE

To identify disease activity and effects of intravitreal pegcetacoplan treatment on the topographic progression of geographic atrophy (GA) secondary to age-related macular degeneration quantified in spectral-domain OCT (SD-OCT) by automated deep learning assessment.

DESIGN

Retrospective analysis of a phase II clinical trial study evaluating pegcetacoplan in GA patients (FILLY, NCT02503332).

SUBJECTS

SD-OCT scans of 57 eyes with monthly treatment, 46 eyes with every-other-month (EOM) treatment, and 53 eyes with sham injection from baseline and 12-month follow-ups were included, in a total of 312 scans.

METHODS

Retinal pigment epithelium loss, photoreceptor (PR) integrity, and hyperreflective foci (HRF) were automatically segmented using validated deep learning algorithms. Local progression rate (LPR) was determined from a growth model measuring the local expansion of GA margins between baseline and 1 year. For each individual margin point, the eccentricity to the foveal center, the progression direction, mean PR thickness, and HRF concentration in the junctional zone were computed. Mean LPR in disease activity and treatment effect conditioned on these properties were estimated by spatial generalized additive mixed-effect models.

MAIN OUTCOME MEASURES

LPR of GA, PR thickness, and HRF concentration in μm.

RESULTS

A total of 31,527 local GA margin locations were analyzed. LPR was higher for areas with low eccentricity to the fovea, thinner PR layer thickness, or higher HRF concentration in the GA junctional zone. When controlling for topographic and structural risk factors, we report on average a significantly lower LPR by -28.0% (95% confidence interval [CI], -42.8 to -9.4; P = 0.0051) and -23.9% (95% CI, -40.2 to -3.0; P = 0.027) for monthly and EOM-treated eyes, respectively, compared with sham.

CONCLUSIONS

Assessing GA progression on a topographic level is essential to capture the pathognomonic heterogeneity in individual lesion growth and therapeutic response. Pegcetacoplan-treated eyes showed a significantly slower GA lesion progression rate compared with sham, and an even slower growth rate toward the fovea. This study may help to identify patient cohorts with faster progressing lesions, in which pegcetacoplan treatment would be particularly beneficial. Automated artificial intelligence-based tools will provide reliable guidance for the management of GA in clinical practice.

Fundus autofluorescence and optical coherence tomography biomarkers associated with the progression of geographic atrophy secondary to age-related macular degeneration

OBJECTIVES

To investigate the impact of qualitatively graded and deep learning quantified imaging biomarkers on growth of geographic atrophy (GA) secondary to age-related macular degeneration.

METHODS

This prospective study included 1062 visits of 181 eyes of 100 patients with GA. Spectral-domain optical coherence tomography (SD-OCT) and fundus autofluorescence (FAF) images were acquired at each visit. Hyperreflective foci (HRF) were quantitatively assessed in SD-OCT volumes using a validated deep learning algorithm. FAF images were graded for FAF patterns, subretinal drusenoid deposits (SDD), GA lesion configuration and atrophy enlargement. Linear mixed models were calculated to investigate associations between all parameters and GA progression.

RESULTS

FAF patterns were significantly associated with GA progression (p < 0.001). SDD was associated with faster GA growth (p = 0.005). Eyes with higher HRF concentrations showed a trend towards faster GA progression (p = 0.072) and revealed a significant impact on GA enlargement in interaction with FAF patterns (p = 0.01). The fellow eye status had no significant effect on lesion enlargement (p > 0.05). The diffuse-trickling FAF pattern exhibited significantly higher HRF concentrations than any other pattern (p < 0.001).

CONCLUSION

Among a wide range of investigated biomarkers, SDD and FAF patterns, particularly in interaction with HRF, significantly impact GA progression. Fully automated quantification of retinal imaging biomarkers such as HRF is both reliable and merited as HRF are indicators of retinal pigment epithelium dysmorphia, a central pathogenetic mechanism in GA. Identifying disease markers using the combination of FAF and SD-OCT is of high prognostic value and facilitates individualized patient management in a clinical setting.

Influence of lens opacities and cataract severity on quantitative fundus autofluorescence as a secondary outcome of a randomized clinical trial

The aim of this study is to investigate the impact of age-related lens opacities and advanced cataract, quantified by LOCS III grading, on quantitative autofluorescence (qAF) measurements in patients before and after cataract surgery. Images from a randomized controlled trial evaluating the impact of femtosecond-laser assisted cataract surgery (FLACS) on retinal thickness were analyzed post-hoc. One-hundred and twenty eyes from 60 consecutive patients with age-related cataract were included and assessed with qAF and optical coherence tomography (OCT) before, 1, 3 and 6 weeks after cataract surgery (randomized 1:1 to FLACS or phacoemulsification). LOCS III grading was performed before surgery. Pre- to post-surgical qAF values, as well as the impact of LOCS III gradings, surgery technique, gender, axial length and age on post-surgery qAF values was investigated using generalized linear mixed models. For this analysis, 106 eyes from 53 patients were usable. No difference in qAF was found between FLACS and phacoemulsification (p > 0.05) and results were pooled for the total cohort. Mean pre-surgical qAF was 89.45 ± 44.9 qAF units, with a significant mean increase of 178.4–191.6% after surgery (p < 0.001). No significant difference was found between the three follow-up visits after surgery (p > 0.05). Higher LOCS III cortical opacity quantifications were associated with a significantly greater increase in qAF after surgery (estimate: 98.56, p = 0.006) and nuclear opacities showed a trend toward an increased change (estimate: 48.8, p = 0.095). Considerable interactions were identified between baseline qAF and cortical opacities, nuclear opacities and posterior subcapsular opacities, as well as nuclear opacities and cortical opacities (p = 0.012, p = 0.064 and p = 0.069, respectively). Quantitative autofluorescence signals are significantly reconstituted after cataract surgery and LOCS III gradings are well associated with post-surgical qAF values. Careful consideration of age-related lens opacities is vital for the correct interpretation of qAF, especially in retinal diseases affecting the elderly.

ClinicalTrials.gov Identifier: NCT03465124.

LONGITUDINAL CHANGES IN QUANTITATIVE AUTOFLUORESCENCE DURING PROGRESSION FROM INTERMEDIATE TO LATE AGE-RELATED MACULAR DEGENERATION

PURPOSE

To prospectively investigate the development of quantitative autofluorescence (qAF) during progression from intermediate to late age-related macular degeneration (AMD).

METHODS

Quantitative autofluorescence images from patients with intermediate AMD were acquired every three months with a Spectralis HRA + OCT (Heidelberg Engineering, Heidelberg, Germany) using a built-in autofluorescence reference. The association between changes in longitudinal qAF and progression toward late AMD was assessed using Cox regression models with time-dependent covariates.

RESULTS

One hundred and twenty-one eyes of 71 patients were included, and 653 qAF images were acquired. Twenty-one eyes of 17 patients converted to late AMD (median follow-up: 21 months; 12 eyes: atrophic AMD; nine eyes: neovascular AMD). The converting patients' mean age was 74.6 ± 4.4 years. Eleven eyes in the converting group (52.4%) were pseudophakic. The presence of an intraocular lens did not affect the qAF regression slopes (P > 0.05). The median change for atrophic AMD was -2.34 qAF units/3 months and 0.78 qAF units/3 months for neovascular AMD. A stronger decline in qAF was significantly associated with an increased risk of developing atrophic AMD (hazard ratio = 1.022, P < 0.001). This association, however, was not present in the group progressing toward neovascular AMD (hazard ratio = 1.001, P = 0.875).

CONCLUSION

The qAF signal declines with progression to atrophy, contrary to developing neovascularization. Quantitative autofluorescence may allow identification of patients at risk of progressing to late AMD and benefits individualized patient care in intermediate AMD.

Progression of Atrophy and Visual Outcomes in Extensive Macular Atrophy with Pseudodrusen-like Appearance

Purpose

Design

Participants

Methods

Main Outcome Measures

Results

Conclusions

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.

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.

The In Vivo Correlation between Retinal Pigment Epithelium Thickness and Quantitative Fundus Autofluorescence in a White Population

PURPOSE

To investigate the influence of age on the thickness of the retinal pigment epithelium (RPE)/Bruch's membrane (BM) complex and the quantitative autofluorescence (qAF) and to study the possible correlation existing between these 2 parameters in a healthy White population.

DESIGN

Cross-sectional, observational study.

PARTICIPANTS

Healthy White volunteers aged 18 to 65 years.

METHODS

All subjects underwent spectral domain OCT (SD-OCT) and qAF imaging with the Heidelberg HRA-Spectralis (Heidelberg Engineering, Heidelberg, Germany). Spectral domain OCT images were analyzed using the in-built graph-based automatic segmentation algorithm for single retinal layer identification to assess RPE/BM complex thickness in vivo. The thickness values of both inner and outer rings of the Early Treatment Diabetic Retinopathy Study (ETDRS) grid, generated by the software using the "RPE" segmentation, were averaged to obtain a single RPE/BM complex thickness value in each eye. Quantitative autofluorescence images were also evaluated using a dedicated software. The qAF values of 8 subfields forming a ring centered onto the fovea were collected and averaged to obtain a single qAF value (qAF₈) in each eye. The correlation among the RPE/BM complex thickness, the qAF value, and the age of the subjects was investigated.

MAIN OUTCOME MEASURES

The in vivo correlation between RPE/BM complex thickness and qAF.

RESULTS

A total of 105 eyes from 105 subjects (mean age, 42.1 ± 13.9 years; range, 18-65) were included in the analysis. The mean RPE/BM complex thickness significantly increased with age (r = 0.33, P = 0.0006). The values of qAF also positively increased with age (P < 0.0001). A significant correlation was found between qAF and RPE/BM complex thickness (r = 0.27, P = 0.004). After adjusting for age, iris color, and gender, the correlation remained significant only for subjects aged less than 40 years (P = 0.009).

CONCLUSIONS

BM complex thickness was significantly co/BM complex thickness increased with age in a healthy White population. A similar increase was found for qAF values. After adjusting for age and iris color, qAF and RPE/BM complex thickness were still correlated in subjects aged less than 40 years. The RPE/BM complex thickness could reflect the lipofuscin/melanolipofuscin accumulation in normal subjects, adding great interest in RPE cell biology.

Quantitative Fundus Autofluorescence: Advanced Analysis Tools

Purpose

To use multimodal retinal images (including quantitative fundus autofluorescence [QAF]) for spectral-domain optical coherence tomography (SD-OCT)-based image registration and alignment. For each age decade of healthy adults, normative fine-grained QAF retinal maps are generated and advanced methods for QAF image analysis are applied.

Methods

Multimodal retinal images were obtained from 103 healthy subjects (age 19–77 years; unremarkable retina/macula, age-appropriate clear optic media). Custom written FIJI plugins enabled: (1) determination of the fovea in SD-OCT and the edge of the optic disc in infrared (IR) images; (2) alignment and superimposition of multimodal retinal images based on foveal and optic disc position; (3) plotting of normative QAF retinal maps for each decade; and (4) comparison of individual retinas with normative retinas of different decades using newly introduced analysis patterns (QAF97, freehand tool).

Results

SD-OCT based image registration enables easy image registration, alignment, and analysis of different modalities (QAF, IR, and SD-OCT here reported). In QAF, intensities significantly increase with age with two major inclines between the third/fourth and seventh/eighth decades. With aging, the parafoveal area of maximum QAF intensity slightly shifts from temporal-superior to temporal. Compared with standard QAF analysis, refined QAF analysis patterns reveal a more detailed analysis of QAF, especially in the diseased retina.

Conclusions

Age-related QAF normative retinal maps can be used to directly compare and classify individual's QAF intensities. Advanced QAF analysis tools will further help to interpret autofluorescence changes in normal aging and in the diseased retina in a multimodal imaging setting.

Translational Relevance

Advanced methods for QAF analysis link basic findings with clinical observations in normal aging and in the diseased macula.