Extraction of Nystagmus Patterns from Eye-Tracker Data with Convolutional Sparse Coding
This work provides an automated method for clinicians to more accurately analyze nystagmus waveforms, which is important for the clinical interpretation of this pathological eye movement.
This paper addresses the challenge of automatically extracting nystagmus patterns from eye-tracker data, which is complicated by the presence of natural eye movements and blink artifacts. The authors propose a method based on Convolutional Dictionary Learning that successfully separates pathological nystagmus waveforms from natural motion, demonstrating improved pattern recovery rates on simulated signals.
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.