Fundus-controlled perimetry (microperimetry): Application as outcome measure in clinical trials

Age-related macular degeneration

Age-related macular degeneration (AMD) is the leading cause of legal blindness in the industrialized world. AMD is characterized by accumulation of extracellular deposits, namely drusen, along with progressive degeneration of photoreceptors and adjacent tissues. AMD is a multifactorial disease encompassing a complex interplay between ageing, environmental risk factors and genetic susceptibility. Chronic inflammation, lipid deposition, oxidative stress and impaired extracellular matrix maintenance are strongly implicated in AMD pathogenesis. However, the exact interactions of pathophysiological events that culminate in drusen formation and the associated degeneration processes remain to be elucidated. Despite tremendous advances in clinical care and in unravelling pathophysiological mechanisms, the unmet medical need related to AMD remains substantial. Although there have been major breakthroughs in the treatment of exudative AMD, no efficacious treatment is yet available to prevent progressive irreversible photoreceptor degeneration, which leads to central vision loss. Compelling progress in high-resolution retinal imaging has enabled refined phenotyping of AMD in vivo. These insights, in combination with clinicopathological and genetic correlations, have underscored the heterogeneity of AMD. Hence, our current understanding promotes the view that AMD represents a disease spectrum comprising distinct phenotypes with different mechanisms of pathogenesis. Hence, tailoring therapeutics to specific phenotypes and stages may, in the future, be the key to preventing irreversible vision loss.

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.

Evidence for Structural and Functional Damage of the Inner Retina in Diabetes With No Diabetic Retinopathy

Purpose

To provide structural and functional evidence of inner retinal loss in diabetes prior to vascular changes and interpret the structure-function relationship in the context of an established neural model.

Methods

Data from one eye of 505 participants (134 with diabetes and no clinically evident vascular alterations of the retina) were included in this analysis. The data were collected as part of a large population-based study. Functional tests included best-corrected visual acuity, Pelli-Robson contrast sensitivity, mesopic microperimetry, and frequency doubling technology perimetry (FDT). Macular optical coherence tomography volume scans were collected for all participants. To interpret the structure-function relationship in the context of a neural model, ganglion cell layer (GCL) thickness was converted to local ganglion cell (GC) counts.

Results

The GCL and inner plexiform layer were significantly thinner in participants with diabetes (P < 0.05), with no significant differences in the macular retinal nerve fiber layer or the outer retina. All functional tests except microperimetry showed a significant loss in diabetic patients (P < 0.05). Both FDT and microperimetry showed a significant relationship with the GC count (P < 0.05), consistent with predictions from a neural model for partial summation conditions. However, the FDT captured additional significant damage (P = 0.03) unexplained by the structural loss.

Conclusions

Functional and structural measurements support early neuronal loss in diabetes. The structure-function relationship follows the predictions from an established neural model. Functional tests could be improved to operate in total summation conditions in the macula, becoming more sensitive to early loss.

Inferred retinal sensitivity in recessive Stargardt disease using machine learning

Spatially-resolved retinal function can be measured by psychophysical testing like fundus-controlled perimetry (FCP or 'microperimetry'). It may serve as a performance outcome measure in emerging interventional clinical trials for macular diseases as requested by regulatory agencies. As FCP constitute laborious examinations, we have evaluated a machine-learning-based approach to predict spatially-resolved retinal function ('inferred sensitivity') based on microstructural imaging (obtained by spectral domain optical coherence tomography) and patient data in recessive Stargardt disease. Using nested cross-validation, prediction accuracies of (mean absolute error, MAE [95% CI]) 4.74 dB [4.48-4.99] were achieved. After additional inclusion of limited FCP data, the latter reached 3.89 dB [3.67-4.10] comparable to the test-retest MAE estimate of 3.51 dB [3.11-3.91]. Analysis of the permutation importance revealed, that the IS&OS and RPE thickness were the most important features for the prediction of retinal sensitivity. 'Inferred sensitivity', herein, enables to accurately estimate differential effects of retinal microstructure on spatially-resolved function in Stargardt disease, and might be used as quasi-functional surrogate marker for a refined and time-efficient investigation of possible functionally relevant treatment effects or disease progression.