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

Abstract

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.

Fig. 1. Inferred sensitivity mapping.

Based on the fundus autofluorescence (FAF), infrared reflection (IR, not shown) and spectral-domain optical coherence tomography (SD-OCT), mesopic as well as dark-adapted (DA) cyan and DA red sensitivity may be reliably inferred and topographically mapped. The arrows in the FAF image indicate the position of the SD-OCT B-scans. Multiple lines of evidence further support the accuracy of the inference. For all three types of testing, angioscotoma are adequately predicted. Further, the central rod-free zone is also correctly inferred as indicated by the marked cyan-red sensitivity difference at the fovea (eccentricity of 0°, middle B-scan). Regions exhibiting increased FAF and absence of photoreceptor outer and inner-segments (upper and lower SD-OCT scan) show reduced function for all three types of testing. Yet globally the degree of DA cyan dysfunction appears to exceed the degree of DA red dysfunction. Please note, that the inferred cyan-red sensitivity difference in the region of severe cone dysfunction (delimited by the dashed line) is an underestimation of the true cyan-red sensitivity difference due to the floor effects of the perimetry device used in this study that are inevitable reflected by the models. (Reprinted from von der Emde et. al: Artificial intelligence for morphology-based function prediction in neovascular age-related macular degeneration; Scientific reports 9:1132; published [2019] Springer Nature).

Fig. 2. Inferred sensitivity.

Possible quasi-functional surrogate endpoint in future clinical trial.