CLASSIFICATION AND QUANTITATIVE ANALYSIS OF GEOGRAPHIC ATROPHY JUNCTIONAL ZONE USING SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY

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.

Deep Learning Approaches to Predict Geographic Atrophy Progression Using Three-Dimensional OCT Imaging

Purpose

To evaluate the performance of various approaches of processing three-dimensional (3D) optical coherence tomography (OCT) images for deep learning models in predicting area and future growth rate of geographic atrophy (GA) lesions caused by age-related macular degeneration (AMD).

Methods

The study used OCT volumes of GA patients/eyes from the lampalizumab clinical trials (NCT02247479, NCT02247531, NCT02479386); 1219 and 442 study eyes for model development and holdout performance evaluation, respectively. Four approaches were evaluated: (1) en-face intensity maps; (2) SLIVER-net; (3) a 3D convolutional neural network (CNN); and (4) en-face layer thickness and between-layer intensity maps from a segmentation model. The processed OCT images and maps served as input for CNN models to predict baseline GA lesion area size and annualized growth rate.

Results

For the holdout dataset, the Pearson correlation coefficient squared (r2) in the GA growth rate prediction was comparable for all the evaluated approaches (0.33∼0.35). In baseline lesion size prediction, prediction performance was comparable (0.9∼0.91) except for the SLIVER-net (0.83). Prediction performance with only the thickness map of the ellipsoid zone (EZ) or retinal pigment epithelium (RPE) layer individually was inferior to using both. Addition of other layer thickness or intensity maps did not improve the prediction performance.

Conclusions

All explored approaches had comparable performance, which might have reached a plateau to predict GA growth rate. EZ and RPE layers appear to contain the majority of information related to the prediction.

Translational Relevance

Our study provides important insights on the utility of 3D OCT images for GA disease progression predictions.

Photoreceptor assessment in age-related macular degeneration

Clinical trials investigating drugs for various stages of age-related macular degeneration (AMD) are actively underway and there is a strong interest in outcomes that demonstrate a structure-function-correlation. The ellipsoid zone (EZ), a crucial anatomical feature affected in this disease, has emerged as a strong contender. There is significant interest in evaluating EZ metrics on Optical Coherence Tomography (OCT), such as integrity and reflectivity, as disruption of this photoreceptor-rich layer may indicate disease progression. Loss of photoreceptor integrity in the junctional zone of geographic atrophy (GA) has been shown to exceed the areas of retinal pigment epithelial (RPE) atrophy, thus predicting future GA expansion. Furthermore, reduced visual acuity and retinal sensitivity have been correlated with loss of EZ integrity, underscoring a structure-function relationship. Photoreceptor integrity has also recently been acknowledged by the Food and Drug Administration (FDA), supporting its use as a primary endpoint in clinical trials investigating treatments for GA. However, the segmentation of this EZ still poses challenges. Continuous enhancements in OCT resolution and advancements in automated segmentation algorithms contribute to improved assessment of the EZ, strengthening its potential as an imaging biomarker for assessing photoreceptor function. It remains to be seen whether the EZ will serve as a surrogate marker for intermediate AMD. This article aims to provide an overview of the current understanding and knowledge of the EZ, while addressing ongoing challenges encountered in its assessment and interpretation.

Histologic and Immunohistochemical Characterization of GA-Like Pathology in the Rat Subretinal Sodium Iodate Model

Purpose

Geographic atrophy (GA) is an advanced form of dry age-related macular degeneration with multifactorial etiology and no well-established treatment. A model recapitulating the hallmarks would serve as a key to understanding the underlying pathologic mechanisms better. In this report, we further characterized our previously reported subretinal sodium iodate model of GA.

Methods

Retinal degeneration was induced in rats (6-8 weeks old) by subretinal injections of NaIO3 as described previously. Animals were sacrificed at 3, 8 and 12 weeks after injection and eyes were fixed or cryopreserved. Some choroids were processed as flatmounts while other eyes were cryopreserved, sectioned, and immunolabeled with a panel of antibodies. Finally, some eyes were prepared for transmission electron microscopic (TEM) analysis.

Results

NaIO3 subretinal injection resulted in a well-defined focal area of retinal pigment epithelium (RPE) degeneration surrounded by viable RPE. These atrophic lesions expanded over time. RPE morphologic changes at the border consisted of hypertrophy, multilayering, and the possible development of a migrating phenotype. Immunostaining of retinal sections demonstrated external limiting membrane descent, outer retinal tubulation (ORT), and extension of Müller cells toward RPE forming a glial membrane in the subretinal space of the atrophic area. TEM findings demonstrated RPE autophagy, cellular constituents of ORT, glial membranes, basal laminar deposits, and defects in Bruch's membrane.

Conclusions

In this study, we showed pathologic features of a rodent model resembling human GA in a temporal order through histology, immunofluorescence, and TEM analysis and gained insights into the cellular and subcellular levels of the GA-like phenotypes.

Translational Relevance

Despite its acute nature, the expansion of atrophy and the GA-like border in this rat model makes it ideal for studying disease progression and provides a treatment window to test potential therapeutics for GA.

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.

Comparison of Fundus Autofluorescence Versus Optical Coherence Tomography-based Evaluation of the Therapeutic Response to Pegcetacoplan in Geographic Atrophy

PURPOSE

To perform an optical coherence tomography (OCT)-based analysis of geographic atrophy (GA) progression in patients treated with pegcetacoplan.

DESIGN

Post hoc analysis of a phase 2 multicenter, randomized, sham-controlled trial.

METHODS

Manual annotation of retinal pigment epithelium (RPE), ellipsoid zone (EZ), and external limiting membrane (ELM) loss was performed on OCT volumes from baseline and month 12 from the phase 2 FILLY trial of intravitreal pegcetacoplan for the treatment of GA secondary to age-related macular degeneration.

MAIN OUTCOME MEASURES

Correlation of GA areas measured on fundus autofluorescence and OCT. Difference in square root transformed growth rates of RPE, EZ, and ELM loss between treatment groups (monthly injection [AM], injection every other month [AEOM], and sham [SM]).

RESULTS

OCT volumes from 113 eyes of 113 patients (38 AM, 36 AEOM, and 39 SM) were included, resulting in 11 074 B-scans. The median growth of RPE loss was significantly slower in the AM group (0.158 [0.057-0.296]) than the SM group (0.255 [0.188-0.359], P = .014). Importantly, the growth of EZ loss was also significantly slower in the AM group (0.127 [0.041-0.247]) than the SM group (0.232 [0.130-0.349], P = .017). There was no significant difference in the growth of ELM loss between the treatment groups (P = .114).

CONCLUSIONS

OCT imaging provided consistent results for GA growth compared with fundus autofluorescence. In addition to slower RPE atrophy progression in patients treated with pegcetacoplan, a significant reduction in EZ impairment was also identified by OCT, suggesting the use of OCT as a potentially more sensitive monitoring tool in GA therapy.

The effect of pegcetacoplan treatment on photoreceptor maintenance in geographic atrophy monitored by AI-based OCT analysis

PURPOSE

To investigate the therapeutic effect of intravitreal pegcetacoplan on the inhibition of photoreceptor (PR) loss and thinning in geographic atrophy (GA) on conventional spectral domain-optical coherence tomography (SD-OCT) imaging by deep learning-based automated PR quantification.

DESIGN

Post-hoc analysis of a prospective, multicenter, randomized, sham-controlled, masked phase II trial investigating the safety and efficacy of pegcetacoplan for the treatment of GA due to age-related macular degeneration.

PARTICIPANTS

Study eyes of 246 patients, randomized 1:1:1 to monthly (AM), bimonthly (AEOM) and sham (SM) treatment.

METHODS

We performed fully automated, deep learning-based segmentation of retinal pigment epithelium (RPE) loss and PR thickness on SD-OCT volumes acquired at baseline, month 2, 6 and 12. The difference in the change of PR loss area was compared between treatment arms. Change in PR thickness adjacent to the GA borders and in the whole 20 degrees scanning area was compared between treatment arms.

MAIN OUTCOME MEASURES

Square root transformed PR loss area in μm or mm, PR thickness in μm, PR loss/RPE loss ratio.

RESULTS

A total of 31,556 B-Scans of 644 SD-OCT volumes of 161 study eyes (AM: 52, AEOM: 54, SM: 56) were evaluated from baseline to month 12. Comparison of mean change in PR loss area revealed statistically significantly less growth in the AM group at month 2, 6 and 12 compared to SM (-41μm ± 219 vs. 77μm ± 126, p=0.0004; -5μm ± 221 vs. 156μm ± 139, p<0.0001; 106μm ± 400 vs. 283μm ± 226 p=0.0014). PR thinning was significantly reduced under monthly treatment compared to sham within the GA junctional zone as well as throughout the 20 degrees area. A trend towards greater inhibition of PR loss compared to RPE loss was observed under therapy.

CONCLUSIONS

Distinct and reliable quantification of PR loss using deep learning-based algorithms offers an essential tool to evaluate therapeutic efficacy in slowing disease progression. PR loss and thinning are reduced by intravitreal complement C3 inhibition. Automated quantification of PR loss/maintenance based on OCT images is an ideal approach to reliably monitor disease activity and therapeutic efficacy in GA management in clinical routine and regulatory trials.

Correlation between Fundus Autofluorescence and En Face Optical Coherence Tomography Measurements of Geographic Atrophy

PURPOSE

To evaluate the correlation between fundus autofluorescence (FAF) and en face spectral-domain optical coherence tomography (SDOCT) measurements of geographic atrophy (GA) associated with age-related macular degeneration (AMD).

DESIGN

Retrospective, cross-sectional study.

PARTICIPANTS

270 eyes from 172 subjects with GA associated with AMD.

METHODS

Subjects with atrophic AMD with both fundus autofluorescence (FAF; Heidelberg HRA + Spectralis) and dense volume (128 B-scans over 6x6mm) spectral domain optical coherence tomography (SDOCT; Cirrus OCT) imaging were included in this retrospective analysis. The borders of all areas of definite decreased autofluorescence (DDAF) corresponding to GA were manually outlined on FAF images by certified graders at the Doheny Image Reading Center (DIRC) using validated planimetric grading tools. GA was also delineated automatically from en face OCT (at the level of the choroid) using instrument software (Cirrus v.6.2), and segmentation errors were manually corrected prior to computation of GA area. FAF and SDOCT derived measurements were correlated.

MAIN OUTCOME MEASURES

Correlation between SD-OCT and FAF measurements of GA area.

RESULTS

The mean GA area measured from FAF images was 8.1 ± 5.04 mm², compared with an automated, uncorrected SDOCT GA area of 6.82 ± 3.84 mm². Despite the presence of apparent OCT segmentation errors, there was a significant correlation between FAF and uncorrected SDOCT measurements (r = 0.80; P < 0.001). Following manual correction of SDOCT GA segmentation errors, the measured GA area increased to 7.29 ± 4.18 mm², and the correlation with the FAF-determined GA area significantly improved (r = 0.98; P < 0.001).

CONCLUSIONS

SDOCT-derived measurements of GA correlate well with areas of DDAF obtained from FAF images. Manual correction of SDOCT segmentation errors can further improve this correlation. These observations may support the use of SDOCT-based measurements of GA in clinical research and clinical trials.

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

PURPOSE

To investigate geographic atrophy (GA) progression using quantitative autofluorescence (qAF) in eyes with solitary GA.

METHODS

Forty-three eyes of 26 patients (age 79.7 ± 7.2 years; 28 women; 16 pseudophakic) underwent spectral-domain optical coherence tomography and qAF imaging at baseline and after 12 months. The junctional zone (AJZ) and a nonaffected 300-µm-wide control area (AC) were delineated on spectral-domain optical coherence tomography scans and transferred to the qAF image. Linear mixed models were calculated to investigate the association between GA progression and qAF, age, and baseline GA area. Mixed model analyses of variance were used to investigate differences in qAF between areas.

RESULTS

Quantitative autofluorescence of the three inferior sections of both the AJZ (P = 0.028; P = 0.014 and P = 0.032) and the AC (P = 0.043; P = 0.02 and P = 0.028) were significantly associated with GA progression after 12 months. However, qAF measurements were not associated with GA progression in the overall model (P > 0.05). Mean qAF was significantly lower in the AJZ and growth area (AG12) than in the AC (both P ≤ 0.001).

CONCLUSION

The authors report a statistically significant association between GA growth area and qAF measurements at specific retinal locations and a significant difference in qAF between the GA border and unaffected areas outside the lesion. Quantitative autofluorescence measurements may be limitedly useful for predicting GA progression.

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.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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