Multimodal Fusion of Circular Functional Data on High-resolution Neuroretinal Phenotypes

Abstract

Progressive optic neuropathies, particularly glaucoma, represent a significant global health challenge, and the need for precise understanding of heterogeneous neurodegenerative phenotypes cannot be overstated. Here, we brought together two complementary sources of unstructured yet clinically relevant information about neuroretinal rim (NRR) thinning, a common clinical marker of such decay. These are based on a new dataset of fundus digital images and a corresponding dataset of optical coherence tomography, both collected from a large clinical cohort of healthy eyes. First, we represented them using a common data structure that imposed a high-resolution scale of 180 equally spaced and registered measurements on a 360{degrees} circular axis. We modeled the NRR measurements of each eye as circular curves and aligned these multimodal curves to obtain a fused NRR curve for each eye. Unsupervised clustering of these fused curves identified four clusters of eyes with structural heterogeneity, which were also found to have distinctive clinical covariates. Computation of functional derivatives revealed troughs in the curves of each cluster. Using circular statistics, we estimated the directional distributions of these troughs as potentially clinically relevant regions of NRR degeneration. A comparative study using landmark registration based on functional canonical correlation analysis demonstrated that our curve-alignment-based multimodal fusion is superior. Moreover, it improves the robustness of baseline NRR data obtained from fundus imaging.