Spatially Resolved Association of Structural Biomarkers on Retinal Function in Non-Exudative Age-Related Macular Degeneration Over 4 Years.

Purpose: To longitudinally assess the impact of high-risk structural biomarkers for natural disease progression in non-exudative age-related macular degeneration (AMD) on spatially resolved mesopic and scotopic fundus-controlled perimetry testing. Methods: Multimodal retinal imaging data and fundus-controlled perimetry stimuli points were semiautomatically registered according to landmark correspondences at each annual visit over a period of up to 4 years. The presence of sub-RPE drusen, subretinal drusenoid deposits, pigment epithelium detachments (PEDs), hyper-reflective foci (HRF), vitelliform lesions, refractile deposits, and incomplete RPE and outer retinal atrophy (iRORA) and complete RPE and outer retinal atrophy (cRORA) were graded at each stimulus position and visit. Localized retinal layer thicknesses were extracted. Mixed-effect models were used for structure-function correlation. Results: Fifty-four eyes of 49 patients with non-exudative AMD (mean age, 70.7 ± 9.1 years) and 27 eyes of 27 healthy controls (mean age, 63.4 ± 8.9 years) were included. During study course, presence of PED had the highest functional impact with a mean estimated loss of -1.30 dB (P < 0.001) for mesopic and -1.23 dB (P < 0.001) for scotopic testing, followed by HRF with -0.89 dB (mesopic, P = 0.001) and -0.87 dB (scotopic, P = 0.005). Subretinal drusenoid deposits were associated with a stronger visual impairment (mesopic, -0.38 dB; P = 0.128; scotopic, -0.37 dB; P = 0.172) compared with sub-RPE drusen (-0.22 dB, P = 0.0004; -0.18 dB, P = 0.006). With development of c-RORA, scotopic retinal sensitivity further significantly decreased (-2.15 dB; P = 0.02). Thickening of the RPE-drusen-complex and thinning of the outer nuclear layer negatively impacted spatially resolved retinal sensitivity. Conclusions: The presence of PED and HRF had the greatest prognostic impact on progressive point-wise sensitivity losses. Higher predominant rod than cone-mediated localized retinal sensitivity losses with early signs of retinal atrophy development indicate photoreceptor preservation as a potential therapeutic target for future interventional AMD trials.

Impact of lens autofluorescence and opacification on retinal imaging.

BACKGROUND: Retinal imaging, including fundus autofluorescence (FAF), strongly depends on the clearness of the optical media. Lens status is crucial since the ageing lens has both light-blocking and autofluorescence (AF) properties that distort image analysis. Here, we report both lens opacification and AF metrics and the effect on automated image quality assessment. METHODS: 227 subjects (range: 19-89 years old) received quantitative AF of the lens (LQAF), Scheimpflug, anterior chamber optical coherence tomography as well as blue/green FAF (BAF/GAF), and infrared (IR) imaging. LQAF values, the Pentacam Nucleus Staging score and the relative lens reflectivity were extracted to estimate lens opacification. Mean opinion scores of FAF and IR image quality were compiled by medical readers. A regression model for predicting image quality was developed using a convolutional neural network (CNN). Correlation analysis was conducted to assess the association of lens scores, with retinal image quality derived from human or CNN annotations. RESULTS: Retinal image quality was generally high across all imaging modalities (IR (8.25±1.99) >GAF >BAF (6.6±3.13)). CNN image quality prediction was excellent (average mean absolute error (MAE) 0.9). Predictions were comparable to human grading. Overall, LQAF showed the highest correlation with image quality grading criteria for all imaging modalities (eg, Pearson correlation±CI -0.35 (-0.50 to 0.18) for BAF/LQAF). BAF image quality was most vulnerable to an increase in lenticular metrics, while IR (-0.19 (-0.38 to 0.01)) demonstrated the highest resilience. CONCLUSION: The use of CNN-based retinal image quality assessment achieved excellent results. The study highlights the vulnerability of BAF to lenticular remodelling. These results can aid in the development of cut-off values for clinical studies, ensuring reliable data collection for the monitoring of retinal diseases.

Personalized Lens Correction Improves Quantitative Fundus Autofluorescence Analysis.

Purpose: Quantitative fundus autofluorescence (QAF) currently deploys an age-based score to correct for lens opacification. However, in elderly people, lens opacification varies strongly between individuals of similar age, and innate lens autofluorescence is not included in the current correction formula. Our goal was to develop and compare an individualized formula. Methods: One hundred thirty participants were examined cross-sectionally, and a subset of 30 participants received additional multimodal imaging 2-week post-cataract-surgery. Imaging included the Scheimpflug principle, anterior chamber optical coherence tomography (AC-OCT), lens quantitative autofluorescence (LQAF), and retinal QAF imaging. Among the subset, least absolute shrinkage and selection operator regression and backward selection was implemented to determine which lens score best predicts the QAF value after lens extraction. Subsequently, a spline mixed model was applied to the whole cohort to quantify the influence of LQAF and Scheimpflug on QAF. Results: Age and LQAF measurements were found to be the most relevant variables, whereas AC-OCT measurements and Scheimpflug were eliminated by backward selection. Both an increase in Scheimpflug and LQAF values were associated with a decrease in QAF. The prediction error of the spline model (mean absolute error [MAE] ± standard deviation) of 32.2 ± 23.4 (QAF a.u.) was markedly lower compared to the current age-based formula MAE of 96.1 ± 93.5. Both smooth terms, LQAF (P < 0.01) and Scheimpflug (P < 0.001), were significant for the spline mixed model. Conclusions: LQAF imaging proved to be the most predictive for the impact of the natural lens on QAF imaging. The application of lens scores in the clinic could improve the accuracy of QAF imaging interpretation and might allow including aged patients in future QAF studies.

Spectral Analysis of Human Retinal Pigment Epithelium Cells in Healthy and AMD Eyes.

Purpose: Retinal pigment epithelium (RPE) cells show strong autofluorescence (AF). Here, we characterize the AF spectra of individual RPE cells in healthy eyes and those affected by age-related macular degeneration (AMD) and investigate associations between AF spectral response and the number of intracellular AF granules per cell. Methods: RPE-Bruch's membrane flatmounts of 22 human donor eyes, including seven AMD-affected eyes (early AMD, three; geographic atrophy, one; neovascular, three) and 15 unaffected macula (<51 years, eight; >80 years, seven), were imaged at the fovea, perifovea, and near-periphery using confocal AF microscopy (excitation 488 nm), and emission spectra were recorded (500-710 nm). RPE cells were manually segmented with computer assistance and stratified by disease status, and emission spectra were analyzed using cubic spline transforms. Intracellular granules were manually counted and classified. Linear mixed models were used to investigate associations between spectra and the number of intracellular granules. Results: Spectra of 5549 RPE cells were recorded. The spectra of RPE cells in healthy eyes showed similar emission curves that peaked at 580 nm for fovea and perifovea and at 575 and 580 nm for near-periphery. RPE spectral curves in AMD eyes differed significantly, being blue shifted by 10 nm toward shorter wavelengths. No significant association coefficients were found between wavelengths and granule counts. Conclusions: This large series of RPE cell emission spectra at precisely predefined retinal locations showed a hypsochromic spectral shift in AMD. Combining different microscopy techniques, our work has identified cellular RPE spectral AF and subcellular granule properties that will inform future in vivo investigations using single-cell imaging.

QUANTITATIVE AUTOFLUORESCENCE IN CENTRAL SEROUS CHORIORETINOPATHY.

BACKGROUND/PURPOSE: Central serous chorioretinopathy (CSC) is associated with pachychoroid and dysfunctional retinal pigment epithelium. Autofluorescence (AF) is typically altered. The authors performed this study to quantify these alterations using quantitative AF (qAF) in patients with CSC and in their fellow eye in comparison with a healthy control group. METHODS: Patients with CSC and healthy controls were recruited prospectively. All patients received a full clinical examination including best-corrected visual acuity, enhanced depth imaging-optical coherence tomography, and qAF. Quantitative autofluorescence images were taken with a confocal scanning laser ophthalmoscope (Heidelberg Engineering). Quantitative autofluorescence values were assessed in specified regions of the inner eight and the middle ring of the Delori grid. RESULTS: In total, 141 eyes of 77 patients with CSC were included. Ninety eyes had a manifest CSC (group 1) while 51 fellow eyes (group 2) did not show signs of CSC. There were no significant differences of qAF values between these two groups: mean qAF values were 241.3 (inner eight) and 212.8 (middle ring) in group 1 and 235.9 (inner eight) and 210.0 (middle ring) in group 2 ( P = 1.0 and 1.0). We compared these eyes with healthy controls comprising 39 eyes. Quantitative autofluorescence signals (inner eight: 164.7; middle ring: 148.9) differed significantly compared with both CSC manifest ( P < 0.001) and fellow eyes ( P < 0.001). CONCLUSION: Our results show that patients with CSC have increased qAF values in both eyes with manifest CSC and asymptomatic, clinically unremarkable fellow eyes in comparison with healthy controls. This finding suggests that qAF alterations are present even before clinical signs can be observed.

Retest variability and patient reliability indices of quantitative fundus autofluorescence in age-related macular degeneration: a MACUSTAR study report.

This study aimed to determine the retest variability of quantitative fundus autofluorescence (QAF) in patients with and without age-related macular degeneration (AMD) and evaluate the predictive value of patient reliability indices on retest reliability. A total of 132 eyes from 68 patients were examined, including healthy individuals and those with various stages of AMD. Duplicate QAF imaging was conducted at baseline and 2 weeks later across six study sites. Intraclass correlation (ICC) analysis was used to evaluate the consistency of imaging, and mean opinion scores (MOS) of image quality were generated by two researchers. The contribution of MOS and other factors to retest variation was assessed using mixed-effect linear models. Additionally, a Random Forest Regressor was trained to evaluate the extent to which manual image grading of image quality could be replaced by automated assessment (inferred MOS). The results showed that ICC values were high for all QAF images, with slightly lower values in AMD-affected eyes. The average inter-day ICC was found to be 0.77 for QAF segments within the QAF8 ring and 0.74 for peripheral segments. Image quality was predicted with a mean absolute error of 0.27 on a 5-point scale, and of all evaluated reliability indices, MOS/inferred MOS proved most important. The findings suggest that QAF allows for reliable testing of autofluorescence levels at the posterior pole in patients with AMD in a multicenter, multioperator setting. Patient reliability indices could serve as eligibility criteria for clinical trials, helping identify patients with adequate retest reliability.

A Workflow to Quantitatively Determine Age-Related Macular Degeneration Lesion-Specific Variations in Fundus Autofluorescence.

Fundus autofluorescence (FAF) imaging allows the noninvasive mapping of intrinsic fluorophores of the ocular fundus, particularly the retinal pigment epithelium (RPE), now quantifiable with the advent of confocal scanning laser ophthalmoscopy-based quantitative autofluorescence (QAF). QAF has been shown to be generally decreased at the posterior pole in age-related macular degeneration (AMD). The relationship between QAF and various AMD lesions (drusen, subretinal drusenoid deposits) is still unclear. This paper describes a workflow to determine lesion-specific QAF in AMD. A multimodal in vivo imaging approach is used, including but not limited to spectral domain optical coherence tomography (SD-OCT) macular volume scanning and QAF. Using customized FIJI plug-ins, the corresponding QAF image is aligned with the near-infrared image from the SD-OCT scan (characteristic landmarks; i.e., vessel bifurcations). The foveola and the edge of the optic nerve head are marked in the OCT images (and transferred to the registered QAF image) for accurate positioning of the analysis grids. AMD-specific lesions can then be marked on individual OCT BScans or the QAF image itself. Normative QAF maps are created to account for the varying mean and standard deviation of QAF values throughout the fundus (QAF images from a representative AMD group were averaged to build normative standard retinal QAF AMD maps). The plug-ins record the X and Y coordinates, z-score (a numerical measurement that describes the QAF value in relation to the mean of AF maps in terms of standard deviation from the mean), mean intensity value, standard deviation, and number of pixels marked. The tools also determine z-scores from the border zone of marked lesions. This workflow and the analysis tools will improve the understanding of the pathophysiology and clinical AF image interpretation in AMD.

Reliability of Retinal Layer Annotation with a Novel, High-Resolution Optical Coherence Tomography Device: A Comparative Study.

Optical coherence tomography (OCT) enables in vivo diagnostics of individual retinal layers in the living human eye. However, improved imaging resolution could aid diagnosis and monitoring of retinal diseases and identify potential new imaging biomarkers. The investigational high-resolution OCT platform (High-Res OCT; 853 nm central wavelength, 3 µm axial-resolution) has an improved axial resolution by shifting the central wavelength and increasing the light source bandwidth compared to a conventional OCT device (880 nm central wavelength, 7 µm axial-resolution). To assess the possible benefit of a higher resolution, we compared the retest reliability of retinal layer annotation from conventional and High-Res OCT, evaluated the use of High-Res OCT in patients with age-related macular degeneration (AMD), and assessed differences of both devices on subjective image quality. Thirty eyes of 30 patients with early/intermediate AMD (iAMD; mean age 75 ± 8 years) and 30 eyes of 30 age-similar subjects without macular changes (62 ± 17 years) underwent identical OCT imaging on both devices. Inter- and intra-reader reliability were analyzed for manual retinal layer annotation using EyeLab. Central OCT B-scans were graded for image quality by two graders and a mean-opinion-score (MOS) was formed and evaluated. Inter- and intra-reader reliability were higher for High-Res OCT (greatest benefit for inter-reader reliability: ganglion cell layer; for intra-reader reliability: retinal nerve fiber layer). High-Res OCT was significantly associated with an improved MOS (MOS 9/8, Z-value = 5.4, p < 0.01) mainly due to improved subjective resolution (9/7, Z-Value 6.2, p < 0.01). The retinal pigment epithelium drusen complex showed a trend towards improved retest reliability in High-Res OCT in iAMD eyes but without statistical significance. Improved axial resolution of the High-Res OCT benefits retest reliability of retinal layer annotation and improves perceived image quality and resolution. Automated image analysis algorithms could also benefit from the increased image resolution.

Hyper-Reflective Foci in Intermediate Age-Related Macular Degeneration: Spatial Abundance and Impact on Retinal Morphology.

Purpose: The purpose of this study was to analyze spatially resolved structural changes at retinal locations in presence (+) or absence (-) of hyper-reflective foci (HRF) in eyes with subretinal pigment epithelium (RPE) drusen in intermediate age-related macular degeneration (iAMD). Methods: Patients with IAMD (n = 40; mean age = 69.7 ± 9.2 [SD] years) and healthy controls (n = 27; 64.2 ± 9.0) underwent spectral-domain optical-coherence-tomography imaging and fundus-controlled perimetry testing. After reviewing retinal layer segmentation, presence of HRF was annotated and retinal layer thicknesses (RLTs) extracted using ImageJ. Localized RLTs were compared between +HRF and -HRF positions. Univariate mixed linear models were used to investigate associations among RLT, HRF presence, and HRF size. Results: In iAMD eyes, a mean of 11.1 ± 12.5 HRF were detected with a peak abundance at 0.5 to 1.5 mm eccentricity to the fovea. At +HRF positions, outer nuclear layer (ONL; P = 0.0013, average difference = -12.4 µm) and retinal pigment epithelium drusen complex (RPEDC; P < 0.0001, +45.6 µm) thicknesses differed significantly compared to -HRF positions, even after correcting for accompanying drusen-related RPEDC layer thickening (P = 0.01). Mixed linear models revealed a significant association between increasing HRF area and decreasing ONL (association score = -0.17, P < 0.0001; 95% confidence interval [CI] = -0.22 to -0.11), and inner photoreceptor segments (IS) layer thicknesses (-0.08, P = 0.005; 95% CI = -0.14 to -0.03). Spearman rank correlation analysis yielded a significant correlation between total HRF area and mesopic (P = 0.015), but not scotopic (P = 0.305) retinal sensitivity losses. Conclusions: Descriptive analysis of this study demonstrated a predominant distribution of HRF at a foveal eccentricity of 0.5 to 1.5 mm, whereas further refined topographic analysis revealed a significant ONL layer thinning in presence of HRF even after correction for sub-RPE drusen presence compared to lesions in absence of HRF. Longitudinal studies are further needed to analyze the prognostic impact as well as the role of HRF presence in the context of iAMD.

Blue-light fundus autofluorescence imaging of pigment epithelial detachments.

BACKGROUND: Pigment epithelial detachments (PEDs) occur in association with various chorioretinal diseases. With respect to the broad clinical spectrum of PEDs we describe fundus autofluorescence (FAF) characteristics of PEDs. METHODS: Ninety-three eyes of 66 patients (mean age 71.9 ± 11.1) with uni- or bilateral PED ( ≥ 350 µm) were included in a retrospective cross-sectional study. PEDs were secondary to age-related macular degeneration (n = 79), central serous chorioretinopathy (n = 7), polypoidal choroidal vasculopathy (n = 2), pattern dystrophy (n = 3) or idiopathic PED (n = 2). FAF images were recorded using confocal scanning laser ophthalmoscopy (488 nm excitation wavelength, detection of emission >500 nm). Diagnosis of PED was confirmed using spectral-domain optical coherence tomography. A qualitative FAF grading system was established, and grading was performed by two independent readers. RESULTS: PEDs showed highly variable characteristics on FAF imaging. FAF within the area of PED was found to be irregular/granular (n = 59, 63.4%), increased (n = 28, 30.1%), decreased (n = 3, 3.2 %), or normal (n = 3, 3.2%). Accompanying FAF changes included condensation of macular pigment (n = 67, 72.0%), focally increased FAF at the PED apex (n = 14, 15.1%) or elsewhere (n = 52, 55.9%), focally decreased FAF (n = 23, 24.7%), a cartwheel-like pattern (n = 10, 10.8%), a doughnut sign (n = 6, 6.5%), and a halo of decreased FAF encircling the PED (completely n = 20, 21.5% or incompletely n = 20, 21.5%). CONCLUSIONS: PEDs show a variety of abnormal patterns on FAF imaging. These changes in FAF signals may be secondary to morphological and metabolic alterations within corresponding retinal layers and do not necessarily correspond with the underlying PED subtype or a specific pathology.

Effect of a flipped classroom course to foster medical students' AI literacy with a focus on medical imaging: a single group pre-and post-test study.

BACKGROUND: The use of artificial intelligence applications in medicine is becoming increasingly common. At the same time, however, there are few initiatives to teach this important and timely topic to medical students. One reason for this is the predetermined medical curriculum, which leaves very little room for new topics that were not included before. We present a flipped classroom course designed to give undergraduate medical students an elaborated first impression of AI and to increase their "AI readiness". METHODS: The course was tested and evaluated at Bonn Medical School in Germany with medical students in semester three or higher and consisted of a mixture of online self-study units and online classroom lessons. While the online content provided the theoretical underpinnings and demonstrated different perspectives on AI in medical imaging, the classroom sessions offered deeper insight into how "human" diagnostic decision-making differs from AI diagnoses. This was achieved through interactive exercises in which students first diagnosed medical image data themselves and then compared their results with the AI diagnoses. We adapted the "Medical Artificial Intelligence Scale for Medical Students" to evaluate differences in "AI readiness" before and after taking part in the course. These differences were measured by calculating the so called "comparative self-assessment gain" (CSA gain) which enables a valid and reliable representation of changes in behaviour, attitudes, or knowledge. RESULTS: We found a statistically significant increase in perceived AI readiness. While values of CSA gain were different across items and factors, the overall CSA gain regarding AI readiness was satisfactory. CONCLUSION: Attending a course developed to increase knowledge about AI in medical imaging can increase self-perceived AI readiness in medical students.

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.

Autofluorescent Organelles Within the Retinal Pigment Epithelium in Human Donor Eyes With and Without Age-Related Macular Degeneration.

Purpose: Human retinal pigment epithelium (RPE) cells contain lipofuscin, melanolipofuscin, and melanosome organelles that impact clinical autofluorescence (AF) imaging. Here, we quantified the effect of age-related macular degeneration (AMD) on granule count and histologic AF of RPE cell bodies. Methods: Seven AMD-affected human RPE-Bruch's membrane flatmounts (early and intermediate = 3, late dry = 1, and neovascular = 3) were imaged at fovea, perifovea, and near periphery using structured illumination and confocal AF microscopy (excitation 488 nm) and compared to RPE-flatmounts with unremarkable macula (n = 7, >80 years). Subsequently, granules were marked with computer assistance, and classified by their AF properties. The AF/cell was calculated from confocal images. The total number of granules and AF/cell was analyzed implementing a mixed effect analysis of covariance (ANCOVA). Results: A total of 152 AMD-affected RPE cells were analyzed (fovea = 22, perifovea = 60, and near-periphery = 70). AMD-affected RPE cells showed increased variability in size and a significantly increased granule load independent of the retinal location (fovea: P = 0.02, perifovea: P = 0.04, and near periphery: P < 0.01). The lipofuscin fraction of total organelles decreased and the melanolipofuscin fraction increased in AMD, at all locations (especially the fovea). AF was significantly lower in AMD-affected cells (fovea: <0.01, perifovea: <0.01, and near periphery: 0.02). Conclusions: In AMD RPE, lipofuscin was proportionately lowest in the fovea, a location also known to be affected by accumulation of soft drusen and preservation of cone-mediated visual acuity. Enlarged RPE cell bodies displayed increased net granule count but diminished total AF. Future studies should also assess the impact on AF imaging of RPE apical processes containing melanosomes.

AI-based structure-function correlation in age-related macular degeneration.

Sensitive and robust outcome measures of retinal function are pivotal for clinical trials in age-related macular degeneration (AMD). A recent development is the implementation of artificial intelligence (AI) to infer results of psychophysical examinations based on findings derived from multimodal imaging. We conducted a review of the current literature referenced in PubMed and Web of Science among others with the keywords 'artificial intelligence' and 'machine learning' in combination with 'perimetry', 'best-corrected visual acuity (BCVA)', 'retinal function' and 'age-related macular degeneration'. So far AI-based structure-function correlations have been applied to infer conventional visual field, fundus-controlled perimetry, and electroretinography data, as well as BCVA, and patient-reported outcome measures (PROM). In neovascular AMD, inference of BCVA (hereafter termed inferred BCVA) can estimate BCVA results with a root mean squared error of ~7-11 letters, which is comparable to the accuracy of actual visual acuity assessment. Further, AI-based structure-function correlation can successfully infer fundus-controlled perimetry (FCP) results both for mesopic as well as dark-adapted (DA) cyan and red testing (hereafter termed inferred sensitivity). Accuracy of inferred sensitivity can be augmented by adding short FCP examinations and reach mean absolute errors (MAE) of ~3-5 dB for mesopic, DA cyan and DA red testing. Inferred BCVA, and inferred retinal sensitivity, based on multimodal imaging, may be considered as a quasi-functional surrogate endpoint for future interventional clinical trials in the future.

NATURAL HISTORY OF QUANTITATIVE AUTOFLUORESCENCE IN INTERMEDIATE AGE-RELATED MACULAR DEGENERATION.

PURPOSE: To investigate differences in quantitative autofluorescence (qAF) imaging measurements between eyes with and without large drusen, and whether qAF measurements change over time in the eyes with large drusen. METHODS: Eighty-five eyes from participants with bilateral large drusen and 51 eyes from healthy participants underwent qAF imaging at least once, and the age-related macular degeneration participants were reviewed 6-monthly. Normalized grey values at 9° to 11° eccentricity from the fovea were averaged to provide a summary measure of qAF values (termed qAF8). RESULTS: In a multivariable model, qAF8 measurements were not significantly different between age-related macular degeneration eyes with large drusen and healthy eyes (P = 0.130), and qAF8 measurements showed a decline over time in the age-related macular degeneration eyes (P = 0.013). CONCLUSION: These findings add to the body of evidence that qAF levels are not increased in eyes with large drusen compared with healthy eyes, and qAF levels show a significant decline over time in the age-related macular degeneration eyes. These findings highlight how the relationship between qAF levels and retinal pigment epithelium health does not seem to be straightforward. Further investigation is required to better understand this relationship, especially if qAF levels are to be used as an outcome measure in intervention trials.

Mesopic and Scotopic Light Sensitivity and Its Microstructural Correlates in Pseudoxanthoma Elasticum.

Importance: Correlates for Bruch membrane alterations are needed for interventional trials targeting the Bruch membrane in pseudoxanthoma elasticum (PXE). Objectives: To quantify mesopic and scotopic light sensitivity and identify its microstructural correlates associated with a diseased Bruch membrane in patients with PXE. Design, Setting, and Participants: A prospective, single-center, cross-sectional case-control study was conducted at a tertiary referral center from January 31, 2018, to February 20, 2020. Twenty-two eyes of 22 patients with PXE and 40 eyes of 40 healthy individuals were included. Data analysis was completed March 15, 2020. Exposures: Mesopic and dark-adapted 2-color fundus-controlled perimetry (microperimetry) and multimodal retinal imaging including spectral-domain optical coherence tomography (SD-OCT) and OCT angiography were performed. Perimetry thresholds were analyzed using mixed models, and structure-function correlation with SD-OCT data was performed using machine learning. Main Outcomes and Measures: Observed dark-adapted cyan sensitivity loss as measure of rod photoreceptor dysfunction, as well as mean absolute error between predicted and observed retinal sensitivity to assess the accuracy of structure-function correlation. Results: Of the 22 patients with PXE included in this study, 15 were women (68%); median age was 56.5 years (interquartile range, 50.4-61.2). These patients exhibited mesopic (estimate, 5.13 dB; 95% CI, 2.89-7.38 dB), dark-adapted cyan (estimate, 9.08 dB; 95% CI, 6.34-11.82 dB), and dark-adapted red (estimate, 7.05 dB; 95% CI, 4.83-9.27 dB) sensitivity losses. This sensitivity loss was also evident in 9 eyes with nonneovascular PXE (mesopic: estimate, 3.21 dB; 95% CI, 1.28-5.14 dB; dark-adapted cyan: 5.93 dB; 95% CI, 3.59-8.27 dB; and dark-adapted red testing: 4.84 dB; 95% CI, 2.88-6.80 dB), showing a distinct centrifugal pattern of sensitivity loss with preserved function toward the periphery. Retinal function could be predicted from microstructure with high accuracy (mean absolute errors, of 4.91 dB for mesopic, 5.44 dB for dark-adapted cyan, and 4.99 dB for dark-adapted red). The machine learning-based analysis highlighted an association of a thinned inner retina and putative separation of the pigment-epithelium-photoreceptor complex with sensitivity loss. Conclusions and Relevance: In this study, among 22 patients with PXE, those with and without choroidal neovascularization exhibited reductions of retinal sensitivity being most pronounced in dark-adapted cyan testing. This finding suggests that pathologic characteristics of this Bruch membrane disease may be dominated by rod photoreceptor degeneration and/or dysfunction. A putative pigment-epithelium-photoreceptor separation may further impair rod function, while inner retinal abnormalities appear to be correlated with overall dysfunction.

[Artificial intelligence in ophthalmology : Guidelines for physicians for the critical evaluation of studies]. / Künstliche Intelligenz in der Augenheilkunde : Leitfaden für Ärzte zur kritischen Bewertung von Studien.

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.

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 Cone and Rod Functions in Geographic Atrophy: AI-Based Structure-Function Correlation.

PURPOSE: To investigate the association between retinal microstructure and cone and rod function in geographic atrophy (GA) secondary to age-related macular degeneration (AMD) by using artificial intelligence (AI) algorithms. DESIGN: Prospective, observational case series. METHODS: A total of 41 eyes of 41 patients (75.8 ± 8.4 years old; 22 females) from a tertiary referral hospital were included. Mesopic, dark-adapted (DA) cyan and red sensitivities were assessed by using fundus-controlled perimetry ("microperimetry"); and retinal microstructure was assessed by using spectral-domain optical-coherence-tomography (SD-OCT), fundus autofluorescence (FAF), and near-infrared-reflectance (IR) imaging. Layer thicknesses and intensities and FAF and IR intensities were extracted for each test point. The cross-validated mean absolute error (MAE) was evaluated for random forest-based predictions of retinal sensitivity with and without patient-specific training data and percentage of increased mean-squared error (%IncMSE) as measurement of feature importance. RESULTS: Retinal sensitivity was predicted with a MAE of 4.64 dB for mesopic, 4.89 dB for DA cyan, and 4.40 dB for DA red testing in the absence of patient-specific data. Partial addition of patient-specific sensitivity data to the training sets decreased the MAE to 2.89 dB, 2.86 dB, and 2.77 dB. For all 3 types of testing, the outer nuclear layer thickness constituted the most important predictive feature (35.0, 42.22, and 53.74 %IncMSE). Spatially resolved mapping of "inferred sensitivity" revealed regions with differential degrees of mesopic and DA cyan sensitivity loss outside of the GA lesions. CONCLUSIONS: "Inferred sensitivity" accurately reflected retinal function in patients with GA. Mapping of "inferred sensitivity" could facilitate monitoring of disease progression and serve as "quasi functional" surrogate outcome in clinical trials, especially in consideration of retinal regions beyond areas of GA.

MESOPIC AND DARK-ADAPTED TWO-COLOR FUNDUS-CONTROLLED PERIMETRY IN GEOGRAPHIC ATROPHY SECONDARY TO AGE-RELATED MACULAR DEGENERATION.

PURPOSE: To investigate retinal sensitivity in the junctional zone of geographic atrophy (GA) secondary to age-related macular degeneration using patient-tailored perimetry grids for mesopic and dark-adapted two-color fundus-controlled perimetry. METHODS: Twenty-five eyes with GA of 25 patients (prospective, natural-history Directional Spread in Geographic Atrophy study [DSGA; NCT02051998]) and 40 eyes of 40 normal subjects were included. Patient-tailored perimetry grids were generated using annotated fundus autofluorescence data. Customized software positioned test-points along iso-hulls surrounding the GA boundary at distances of 0.43°, 0.86°, 1.29°, 2.15°, and 3.01°. The grids were used for duplicate mesopic and dark-adapted two-color (cyan and red) fundus-controlled perimetry. Age-adjusted reference-data were obtained through regression analysis of normative data followed by spatial interpolation. RESULTS: The mean sensitivity loss for mesopic testing decreased with the distance to GA (-10.3 dB [0.43°], -8.2 dB [0.86°], -7.1 dB [1.29°], -6.8 dB [2.15°], and -6.6 dB [3.01°]; P < 0.01). Dark-adapted cyan sensitivity loss exceeded dark-adapted red sensitivity loss for all iso-hulls (-14.8 vs. -11.7 dB, -13.5 vs. -10.1 dB, -12.8 vs. -9.1 dB, -11.6 vs. -8.2 dB, -10.7 vs. -8.0 dB; P < 0.01). CONCLUSION: Patient-tailored fundus-controlled perimetry grids allowed for testing of retinal function in the junctional zone of GA with high spatial resolution. A distinct decrease in mesopic sensitivity loss between 0.43° (125 µm) and 1.29° (375 µm) was observed that leveled off at more distant test-points. In proximity to the GA boundary, the results indicate that rod exceeded cone dysfunction.