Extraction of Nystagmus Patterns from Eye-Tracker Data with Convolutional Sparse Coding

TL;DR

This paper introduces a convolutional dictionary learning method to automatically extract Nystagmus waveforms from eye-tracking data, effectively separating pathological signals from natural eye movements and artifacts, aiding clinical diagnosis.

Contribution

The paper presents a novel convolutional sparse coding approach for isolating Nystagmus patterns, improving pattern recovery in eye-tracking data with artifacts.

Findings

Enhanced pattern recovery rate on simulated signals

Effective separation of natural eye movements from pathological signals

Clinical examples demonstrating algorithm performance

Abstract

The analysis of the Nystagmus waveforms from eye-tracking records is crucial for the clinicial interpretation of this pathological movement. A major issue to automatize this analysis is the presence of natural eye movements and eye blink artefacts that are mixed with the signal of interest. We propose a method based on Convolutional Dictionary Learning that is able to automaticcaly highlight the Nystagmus waveforms, separating the natural motion from the pathological movements. We show on simulated signals that our method can indeed improve the pattern recovery rate and provide clinical examples to illustrate how this algorithm performs.