Development of AITC-induced dermal blood flow as a translational in vivo biomarker of TRPA1 activity in human and rodent skin.

BACKGROUND AND PURPOSE: Develop a translational assay of Transient Receptor Potential Ankyrin 1 (TRPA1) activity for use as a preclinical and clinical biomarker. EXPERIMENTAL APPROACH: Allyl isothiocyanate (AITC), capsaicin or citric acid were applied to ears of wildtype and Trpa1-knock out (Trpa1 KO) rats, and changes in dermal blood flow (DBF) were measured by laser speckle contrast imaging. In humans, the DBF, pain and itch responses to 5-20% AITC applied to the forearm were measured and safety was evaluated. Reproducibility of the DBF, pain and itch responses to topically applied 10% and 15% AITC were assessed at two visits separated by 13-15 days. DBF changes were summarized at 5-minute intervals as areas under the curve (AUC) and maxima. Intraclass correlation coefficient (ICC) was calculated to assess arm-arm and period-period reproducibility. KEY RESULTS: AITC- and citric acid-induced DBF were significantly reduced in Trpa1 KO rats compared to wildtype (90 ± 2% and 65 ± 11% reduction, respectively), whereas capsaicin response did not differ. In humans, each AITC concentration significantly increased DBF compared to vehicle with the maximal increase occurring 5 minutes post application. Ten percent and 15% AITC were selected as safe and effective stimuli. AUC from 0 to 5 minutes was the most reproducible metric of AITC-induced DBF across arms (ICC = 0.92) and periods (ICC = 0.85). Subject-reported pain was more reproducible than itch across visits (ICC = 0.76 vs 0.17, respectively). CONCLUSION AND IMPLICATIONS: AITC-induced DBF is a suitable target engagement biomarker of TRPA1 activity for preclinical and clinical studies of TRPA1 antagonists.

Conversion from Intermediate Age-Related Macular Degeneration to Geographic Atrophy in a Proxima B Subcohort Using a Multimodal Approach.

INTRODUCTION: This retrospective analysis assessed geographic atrophy (GA) progression in fellow eyes from the Proxima B trial intermediate age-related macular degeneration (iAMD) subcohort using high-resolution multimodal imaging anchored on optical coherence tomography (OCT). METHODS: Thirty-two patients from the Proxima B iAMD subcohort were assessed; all had GA with no macular neovascularization (MNV) in the contralateral eye. Imaging data, including color fundus photography, fluorescein angiography, near-infrared reflectance, fundus autofluorescence (FAF), and spectral-domain OCT, were obtained. Features preceding progression/conversion to advanced AMD (drusen, reticular pseudodrusen [RPD], MNV, incomplete/complete retinal pigment epithelium and outer retinal atrophy [iRORA/cRORA]) were assessed. RESULTS: Of 30 fellow eyes with available follow-up images, 12 converted to GA (FAF), 2 converted to MNV, and 16 were nonconverters during the review period (median: 17.8 months). iRORA/cRORA features (present in all converters at baseline) were identified on OCT in eyes that progressed to GA. Median time interval from iRORA to cRORA and from cRORA to GA was 7 months each. GA development/progression was either drusen- or RPD-associated (n = 6 each). Eyes with baseline RPD showed faster GA progression versus eyes with drusen (1.49 vs. 0.38 mm2/year). CONCLUSIONS: RPD presence was associated with rapid GA lesion enlargement and may provide an early indication of faster GA progression.

Quantitative optical coherence tomography angiography of vascular abnormalities in the living human eye.

Retinal vascular diseases are important causes of vision loss. A detailed evaluation of the vascular abnormalities facilitates diagnosis and treatment in these diseases. Optical coherence tomography (OCT) angiography using the highly efficient split-spectrum amplitude decorrelation angiography algorithm offers an alternative to conventional dye-based retinal angiography. OCT angiography has several advantages, including 3D visualization of retinal and choroidal circulations (including the choriocapillaris) and avoidance of dye injection-related complications. Results from six illustrative cases are reported. In diabetic retinopathy, OCT angiography can detect neovascularization and quantify ischemia. In age-related macular degeneration, choroidal neovascularization can be observed without the obscuration of details caused by dye leakage in conventional angiography. Choriocapillaris dysfunction can be detected in the nonneovascular form of the disease, furthering our understanding of pathogenesis. In choroideremia, OCT's ability to show choroidal and retinal vascular dysfunction separately may be valuable in predicting progression and assessing treatment response. OCT angiography shows promise as a noninvasive alternative to dye-based angiography for highly detailed, in vivo, 3D, quantitative evaluation of retinal vascular abnormalities.

Projection-Resolved Optical Coherence Tomography Angiography of Macular Retinal Circulation in Glaucoma.

PURPOSE: To detect macular perfusion defects in glaucoma using projection-resolved optical coherence tomography (OCT) angiography. DESIGN: Prospective observation study. PARTICIPANTS: A total of 30 perimetric glaucoma and 30 age-matched normal participants were included. METHODS: One eye of each participant was imaged using 6×6-mm macular OCT angiography (OCTA) scan pattern by 70-kHz 840-nm spectral-domain OCT. Flow signal was calculated by the split-spectrum amplitude-decorrelation angiography algorithm. A projection-resolved OCTA (PR-OCTA) algorithm was used to remove flow projection artifacts. Four en face OCTA slabs were analyzed: the superficial vascular complex (SVC), intermediate capillary plexus (ICP), deep capillary plexus (DCP), and all-plexus retina (SVC + ICP + DCP). The vessel density (VD), defined as the percentage area occupied by flow pixels, was calculated from en face OCTA. A novel algorithm was used to adjust the vessel density to compensate for local variations in OCT signal strength. MAIN OUTCOME MEASURES: Macular retinal VD, ganglion cell complex (GCC) thickness, and visual field (VF) sensitivity. RESULTS: Focal capillary dropout could be visualized in the SVC, but not the ICP and DVP, in glaucomatous eyes. In the glaucoma group, the SVC and all-plexus retinal VD (mean ± standard deviation: 47.2%±7.1% and 73.5%±6.6%) were lower than in the normal group (60.5%±4.0% and 83.2%±4.2%, both P < 0.001, t test). The ICP and DCP VD were not significantly lower in the glaucoma group. Among the overall macular VD parameters, the SVC VD had the best diagnostic accuracy as measured by the area under the receiver operating characteristic curve (AROC). The accuracy was even better when the worse hemisphere (inferior or superior) was used, achieving an AROC of 0.983 and a sensitivity of 96.7% at a specificity of 95%. Among the glaucoma participants, the hemispheric SVC VD values were highly correlated with the corresponding GCC thickness and VF sensitivity (P < 0.003). The reflectance compensation step in VD calculation significantly improved repeatability, normal population variation, and correlation with VF and GCC thickness. CONCLUSIONS: On the basis of PR-OCTA, glaucoma preferentially affects perfusion in the SVC in the macula more than the deeper plexuses. Reflectance-compensated SVC VD measurement by PR-OCTA detected glaucoma with high accuracy and could be useful in the clinical evaluation of glaucoma.

The candidate splicing factor Sfswap regulates growth and patterning of inner ear sensory organs.

The Notch signaling pathway is thought to regulate multiple stages of inner ear development. Mutations in the Notch signaling pathway cause disruptions in the number and arrangement of hair cells and supporting cells in sensory regions of the ear. In this study we identify an insertional mutation in the mouse Sfswap gene, a putative splicing factor, that results in mice with vestibular and cochlear defects that are consistent with disrupted Notch signaling. Homozygous Sfswap mutants display hyperactivity and circling behavior consistent with vestibular defects, and significantly impaired hearing. The cochlea of newborn Sfswap mutant mice shows a significant reduction in outer hair cells and supporting cells and ectopic inner hair cells. This phenotype most closely resembles that seen in hypomorphic alleles of the Notch ligand Jagged1 (Jag1). We show that Jag1; Sfswap compound mutants have inner ear defects that are more severe than expected from simple additive effects of the single mutants, indicating a genetic interaction between Sfswap and Jag1. In addition, expression of genes involved in Notch signaling in the inner ear are reduced in Sfswap mutants. There is increased interest in how splicing affects inner ear development and function. Our work is one of the first studies to suggest that a putative splicing factor has specific effects on Notch signaling pathway members and inner ear development.

Characterization of Chorioretinopathy Associated with Mitochondrial Trifunctional Protein Disorders: Long-Term Follow-up of 21 Cases.

PURPOSE: To assess long-term effects of genotype on chorioretinopathy severity in patients with mitochondrial trifunctional protein (MTP) disorders. DESIGN: Retrospective case series. PARTICIPANTS: Consecutive patients with MTP disorders evaluated at a single center from 1994 through 2015, including 18 patients with long-chain 3-hydroxyacyl-CoA dehydrogenase deficiency (LCHADD) and 3 patients with trifunctional protein deficiency (TFPD). METHODS: Local records from all visits were reviewed. Every participant underwent a complete ophthalmic examination and was evaluated by a metabolic physician and dietitian. Nine patients underwent ancillary funduscopic imaging including optical coherence tomography (OCT) and OCT angiography. MAIN OUTCOME MEASURES: The primary outcome measure was best-corrected visual acuity at the final visit. Secondary outcome measures included spherical equivalent refraction, visual fields, electroretinography B-wave amplitudes, and qualitative imaging findings. RESULTS: Participants were followed up for a median of 5.6 years (range 0.3-20.2 years). The median age of LCHADD participants at initial and final visits was 2.3 and 11.9 years, whereas that for TFPD participants at initial and final visits was 4.7 and 15.5 years, respectively. Four long-term survivors older than 16 years were included (3 with LCHADD and 1 with TFPD). The LCHADD participants demonstrated a steady decline in visual acuity from an average of 0.23 logarithm of the minimum angle of resolution (logMAR; Snellen equivalent, 20/34) at baseline to 0.42 logMAR (Snellen equivalent, 20/53) at the final visit, whereas TFPD patients maintained excellent acuity throughout follow-up. Participants with LCHADD, but not TFPD, showed an increasing myopia with a mean decrease in spherical equivalent refraction of 0.24 diopters per year. Visual fields showed sensitivity losses centrally associated with defects on OCT. Multimodal imaging demonstrated progressive atrophy of the outer retina in LCHADD, often preceded by the formation of outer retinal tubulations and choriocapillaris dropout. Electroretinography findings support the more severe clinical profile of LCHADD patients compared with TFPD patients; the function of both rods and cones are attenuated diffusely in LCHADD patients, but are within normal limits for TFPD patients. CONCLUSIONS: Despite improved survival with early diagnosis, medical management, and dietary treatment, participants with the LCHADD subtype of MTP disorder continue to demonstrate visually disabling chorioretinopathy. Multimodal imaging is most consistent with choriocapillaris loss exceeding photoreceptor loss.

Optimization of the split-spectrum amplitude-decorrelation angiography algorithm on a spectral optical coherence tomography system: erratum.

An erratum is presented to include conflict of interest disclosures that were unintentionally left out of our recent Letter [Opt. Lett.40, 2305 (2015)10.1364/OL.40.002305OPLEDP0146-9592].

OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY OF CHOROIDAL NEOVASCULARIZATION IN FOUR INHERITED RETINAL DYSTROPHIES.

PURPOSE: To demonstrate the clinical utility of optical coherence tomography (OCT) angiography (OCT-A) in inherited retinal dystrophies complicated by choroidal neovascularization (CNV). METHODS: Optical coherence tomography angiography and structural OCT were performed using a 70-kHz spectral domain OCT system using the split-spectrum amplitude-decorrelation angiography algorithm. Semiautomated image processing software was used to segment and measure the CNV. RESULTS: Four participants were enrolled to study the following inherited retinal dystrophies complicated by CNV: choroideremia, EFEMP1-related retinopathy, Best vitelliform dystrophy, and adult-onset vitelliform dystrophy. Interpretation of fluorescein angiography was difficult because of abnormal retinal architecture but suggested the presence of CNV. Structural OCT revealed subretinal or subretinal pigment epithelium fibrovascular tissue, within which flow signal was observed on OCT-A. The CNV morphology varied from dense capillary networks in active lesions to asymptomatic large caliber loops. Baseline CNV vessel areas ranged from 0.07 mm to 0.98 mm. After treatment with intravitreal bevacizumab, the CNV in choroideremia decreased in the vessel area then rebounded, whereas the one in EFEMP1-related retinopathy remained largely unchanged. CONCLUSION: Optical coherence tomography angiography enables morphologic characterization and quantification of CNV in patients with retinal dystrophies despite distorted retinal architecture, can assess response to treatment, and may facilitate differentiation between active and regressed lesions.

Postprocessing algorithms to minimize fixed-pattern artifact and reduce trigger jitter in swept source optical coherence tomography.

We propose methods to align interferograms affected by trigger jitter to a reference interferogram based on the information (amplitude/phase) at a fixed-pattern noise location to reduce residual fixed-pattern noise and improve the phase stability of swept source optical coherence tomography (SS-OCT) systems. One proposed method achieved this by introducing a wavenumber shift (k-shift) in the interferograms of interest and searching for the k-shift that minimized the fixed-pattern noise amplitude. The other method calculated the relative k-shift using the phase information at the residual fixed-pattern noise location. Repeating this wavenumber alignment procedure for all A-lines of interest produced fixed-pattern noise free and phase stable OCT images. A system incorporating these correction routines was used for human retina OCT and Doppler OCT imaging. The results from the two methods were compared, and it was found that the intensity-based method provided better results.

Spectral fractionation detection of gold nanorod contrast agents using optical coherence tomography.

We demonstrate the proof of concept of a novel Fourier-domain optical coherence tomography contrast mechanism using gold nanorod contrast agents and a spectral fractionation processing technique. The methodology detects the spectral shift of the backscattered light from the nanorods by comparing the ratio between the short and long wavelength halves of the optical coherence tomography signal intensity. Spectral fractionation further divides the halves into sub-bands to improve spectral contrast and suppress speckle noise. Herein, we show that this technique can detect gold nanorods in intralipid tissue phantoms. Furthermore, cellular labeling by gold nanorods was demonstrated using retinal pigment epithelial cells in vitro.

Optimization of the split-spectrum amplitude-decorrelation angiography algorithm on a spectral optical coherence tomography system.

The split-spectrum amplitude-decorrelation angiography algorithm was optimized on a spectral optical coherence tomography system using a flow phantom. The number of times the spectrum was split and the bandwidth of each split were adjusted to maximize the flow phantom decorrelation signal-to-noise ratio. The improvement in flow detection was then demonstrated with en face retinal angiograms. The optimized algorithm increased the detectable retinal microvascular flow and decreased the variability of the quantified vessel density in OCT retinal angiograms of healthy human subjects.

OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY FEATURES OF DIABETIC RETINOPATHY.

PURPOSE: To describe the optical coherence tomography angiography features of diabetic retinopathy. METHODS: Using a 70 kHz optical coherence tomography and the split-spectrum amplitude decorrelation angiography algorithm, 6 mm × 6 mm 3-dimensional angiograms of the macula of 4 patients with diabetic retinopathy were obtained and compared with fluorescein angiography for features cataloged by the Early Treatment of Diabetic Retinopathy Study. RESULTS: Optical coherence tomography angiography detected enlargement and distortion of the foveal avascular zone, retinal capillary dropout, and pruning of arteriolar branches. Areas of capillary loss obscured by fluorescein leakage on fluorescein angiography were more clearly defined on optical coherence tomography angiography. Some areas of focal leakage on fluorescein angiography that were thought to be microaneurysms were found to be small tufts of neovascularization that extended above the inner limiting membrane. CONCLUSION: Optical coherence tomography angiography does not show leakage but can better delineate areas of capillary dropout and detect early retinal neovascularization. This new noninvasive angiography technology may be useful for routine surveillance of proliferative and ischemic changes in diabetic retinopathy.

DETECTION OF NONEXUDATIVE CHOROIDAL NEOVASCULARIZATION IN AGE-RELATED MACULAR DEGENERATION WITH OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY.

PURPOSE: To evaluate eyes with age-related macular degeneration and high-risk characteristics for choroidal neovascularization (CNV) with optical coherence tomographic (OCT) angiography to determine whether earlier detection of CNV is possible. METHODS: Eyes with drusen, pigmentary changes, and with CNV in the fellow eye were scanned with a 70-kHz spectral domain OCT system (Optovue RTVue-XR Avanti). The split-spectrum amplitude-decorrelation angiography (SSADA) algorithm was used to distinguish blood flow from static tissue. Two masked graders reviewed scans for CNV, defined as flow in the outer retinal/sub-RPE slab. Choroidal neovascularization flow area repeatability and between-grader reproducibility were calculated. RESULTS: Of 32 eyes, 2 (6%) were found to have Type 1 CNV with OCT angiography. The lesions were not associated with leakage on fluorescein angiography or fluid on OCT. One case was followed for 8 months without treatment, and the CNV flow area enlarged slightly without fluid buildup on OCT or vision loss. Between-grader reproducibility of the CNV flow area was 9.4% (coefficient of variation) and within-visit repeatability was 5.2% (pooled coefficient of variation). CONCLUSION: Optical coherence tomographic angiography can detect the presence of nonexudative CNV, lesions difficult to identify with fluorescein angiography and OCT. Further study is needed to understand the significance and natural history of these lesions.

Vibration of the organ of Corti within the cochlear apex in mice.

The tonotopic map of the mammalian cochlea is commonly thought to be determined by the passive mechanical properties of the basilar membrane. The other tissues and cells that make up the organ of Corti also have passive mechanical properties; however, their roles are less well understood. In addition, active forces produced by outer hair cells (OHCs) enhance the vibration of the basilar membrane, termed cochlear amplification. Here, we studied how these biomechanical components interact using optical coherence tomography, which permits vibratory measurements within tissue. We measured not only classical basilar membrane tuning curves, but also vibratory responses from the rest of the organ of Corti within the mouse cochlear apex in vivo. As expected, basilar membrane tuning was sharp in live mice and broad in dead mice. Interestingly, the vibratory response of the region lateral to the OHCs, the "lateral compartment," demonstrated frequency-dependent phase differences relative to the basilar membrane. This was sharply tuned in both live and dead mice. We then measured basilar membrane and lateral compartment vibration in transgenic mice with targeted alterations in cochlear mechanics. Prestin(499/499), Prestin(-/-), and Tecta(C1509G/C1509G) mice demonstrated no cochlear amplification but maintained the lateral compartment phase difference. In contrast, Sfswap(Tg/Tg) mice maintained cochlear amplification but did not demonstrate the lateral compartment phase difference. These data indicate that the organ of Corti has complex micromechanical vibratory characteristics, with passive, yet sharply tuned, vibratory characteristics associated with the supporting cells. These characteristics may tune OHC force generation to produce the sharp frequency selectivity of mammalian hearing.

Topographic Clinical Insights From Deep Learning-Based Geographic Atrophy Progression Prediction.

Purpose: To explore the contributions of fundus autofluorescence (FAF) topographic imaging features to the performance of convolutional neural network-based deep learning (DL) algorithms in predicting geographic atrophy (GA) growth rate. Methods: Retrospective study with data from study eyes from three clinical trials (NCT02247479, NCT02247531, NCT02479386) in GA. The algorithm was initially trained with full FAF images, and its performance was considered benchmark. Ablation experiments investigated the contribution of imaging features to the performance of the algorithms. Three FAF image regions were defined relative to GA: Lesion, Rim, and Background. For No Lesion, No Rim, and No Background datasets, a single region of interest was removed at a time. For Lesion, Rim, and Background Shuffled datasets, individual region pixels were randomly shuffled. For Lesion, Rim, and Background Mask datasets, masks of the regions were used. A Convex Hull dataset was generated to evaluate the importance of lesion size. Squared Pearson correlation (r2) was used to compare the predictive performance of ablated datasets relative to the benchmark. Results: The Rim region influenced r2 more than the other two regions in all experiments, indicating the most relevant contribution of this region to the performance of the algorithms. In addition, similar performance was observed for all regions when pixels were shuffled or only a mask was used, indicating intensity information was not independently informative without textural context. Conclusions: These ablation experiments enabled topographic clinical insights on FAF images from a DL-based GA progression prediction algorithm. Translational Relevance: Results from this study may lead to new insights on GA progression prediction.

Deep Learning Approaches for Detecting of Nascent Geographic Atrophy in Age-Related Macular Degeneration.

Purpose: Nascent geographic atrophy (nGA) refers to specific features seen on OCT B-scans, which are strongly associated with the future development of geographic atrophy (GA). This study sought to develop a deep learning model to screen OCT B-scans for nGA that warrant further manual review (an artificial intelligence [AI]-assisted approach), and to determine the extent of reduction in OCT B-scan load requiring manual review while maintaining near-perfect nGA detection performance. Design: Development and evaluation of a deep learning model. Participants: One thousand eight hundred and eighty four OCT volume scans (49 B-scans per volume) without neovascular age-related macular degeneration from 280 eyes of 140 participants with bilateral large drusen at baseline, seen at 6-monthly intervals up to a 36-month period (from which 40 eyes developed nGA). Methods: OCT volume and B-scans were labeled for the presence of nGA. Their presence at the volume scan level provided the ground truth for training a deep learning model to identify OCT B-scans that potentially showed nGA requiring manual review. Using a threshold that provided a sensitivity of 0.99, the B-scans identified were assigned the ground truth label with the AI-assisted approach. The performance of this approach for detecting nGA across all visits, or at the visit of nGA onset, was evaluated using fivefold cross-validation. Main Outcome Measures: Sensitivity for detecting nGA, and proportion of OCT B-scans requiring manual review. Results: The AI-assisted approach (utilizing outputs from the deep learning model to guide manual review) had a sensitivity of 0.97 (95% confidence interval [CI] = 0.93-1.00) and 0.95 (95% CI = 0.87-1.00) for detecting nGA across all visits and at the visit of nGA onset, respectively, when requiring manual review of only 2.7% and 1.9% of selected OCT B-scans, respectively. Conclusions: A deep learning model could be used to enable near-perfect detection of nGA onset while reducing the number of OCT B-scans requiring manual review by over 50-fold. This AI-assisted approach shows promise for substantially reducing the current burden of manual review of OCT B-scans to detect this crucial feature that portends future development of GA. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Rare CIDEC coding variants enriched in age-related macular degeneration patients with small low-luminance deficit cause lipid droplet and fat storage defects.

BACKGROUND: The basis of Age-related macular degeneration (AMD) genetic risk has been well documented; however, few studies have looked at genetic biomarkers of disease progression or treatment response within advanced AMD patients. Here we report the first genome-wide analysis of genetic determinants of low-luminance vision deficit (LLD), which is seen as predictive of visual acuity loss and anti-VEGF treatment response in neovascular AMD patients. METHODS: AMD patients were separated into small- and large-LLD groups for comparison and whole genome sequencing was performed. Genetic determinants of LLD were assessed by common and rare variant genetic analysis. Follow-up functional analysis of rare coding variants identified by the burden test was then performed in vitro. RESULTS: We identified four coding variants in the CIDEC gene. These rare variants were only present in patients with a small LLD, which has been previously shown to indicate better prognosis and better anti-VEGF treatment response. Our in vitro functional characterization of these CIDEC alleles revealed that all decrease the binding affinity between CIDEC and the lipid droplet fusion effectors PLIN1, RAB8A and AS160. The rare CIDEC alleles all cause a hypomorphic defect in lipid droplet fusion and enlargement, resulting in a decreased fat storage capability in adipocytes. CONCLUSIONS: As we did not detect CIDEC expression in the ocular tissue affected by AMD, our results suggest that the CIDEC variants do not play a direct role in the eye and influence low-luminance vision deficit via an indirect and systemic effect related to fat storage capacity.

Interreader Agreement and Longitudinal Progression of Incomplete/Complete Retinal Pigment Epithelium and Outer Retinal Atrophy in Age-Related Macular Degeneration.

OBJECTIVE: To analyze the ability to evaluate changes over time of individual lesions of incomplete or complete retinal pigment epithelium (RPE) and outer retinal atrophy (iRORA and cRORA, respectively) in patients with intermediate age-related macular degeneration (iAMD). DESIGN: OCT images from patients enrolled in Proxima B clinical trial (NCT02399072) were utilized. PARTICIPANTS: Patients enrolled in the Proxima B clinical trial, from the cohort with geographic atrophy (GA) in 1 eye and iAMD in the other eye at baseline, were included. METHODS: Junior and senior readers analyzed OCT images for the qualitative presence of 9 distinct early atrophic features (presence of zone of choroidal hypertransmission, attenuation and/or disruption of RPE, disruption of ellipsoid zone [EZ] and external limiting membrane [ELM], outer nuclear layer [ONL] thinning, outer plexiform layer [OPL]/inner nuclear layer [INL] subsidence, and hyporeflective wedge-shaped band). If deemed "present," 7 features were quantified with a predefined tolerance level of 50 µm (diameter for the zone of choroidal hypertransmission, zone of attenuation and/or disruption of the RPE, outer retinal thickness left/right vertical diameter, outer retinal thickness thinnest vertical diameter, annotation of EZ, and ELM disruption). MAIN OUTCOME MEASURES: Interreader agreements for qualitative assessments (κ-type statistics) and quantitative measurements (Bland-Altman statistics) were assessed. Progression of the lesion features over time was described. RESULTS: Moderate agreement was found for presence of choroidal hypertransmission (κ = 0.54), followed by ELM disruption (κ = 0.58), OPL/INL subsidence (κ = 0.46), and a hyporeflective wedge-shaped band (κ = 0.47). Quantification measurements showed that choroidal hypertransmission had the highest agreement, whereas RPE attenuation/disruption had the lowest agreement. Longitudinal adjudicated changes for quantitative measurements of lesion progression showed that choroidal hypertransmission and ELM disruption showed significant progression, whereas EZ disruption and RPE attenuation/disruption did not. CONCLUSIONS: The ability to evaluate changes over time for specific features of iRORA and cRORA was explored. The most robust biomarker was found to be choroidal hypertransmission, followed by ELM disruption and the qualitative markers of OPL/INL subsidence, as well as a wedge-shaped band. Disease progression over time could be assessed by some, but not all, spectral-domain OCT features that were explored. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

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.

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.