Baseline wander estimation methods applied to smooth pursuit eye movements from parkinsonian patient
By M. Bejani, E. Luque-Buzo, A. Burlaka-Petrash, J. A. Gómez-García, J. D. Arias-Londoño, F. Grandas-Pérez, J. I. Godino-Llorente.
This paper has been submitted for publication in 'IEEE Acsses' journal.
Repository of VOG-SPEM recordings of Patients with and with-out Parkinson Disease with a Ground Truth and Baseline Wander delimitation.
Prior studies aiming to parametrize the sequences obtained from the Smooth Pursuit Eye Movements (SPEM) of patients with Parkinson's disease are based on manual extraction of the required information. This is because methods to automatically extract the relevant information are complex to implement and are constrained, in part, by the appearance of a baseline wander (BW). Thus, new methods are required for preprocessing the SPEM sequences to make the potential parameterization procedures much more robust. In this regard, new methods are required to remove the aforementioned BW. The present study investigates and compares different BW removal methods applied to SPEM sequences based on a set of several objective evaluation metrics. At the same time, it proposes a set of guidelines to estimate the ground truth that is used for comparison purposes.
Data were collected using a video-based eye tracking device. 52 patients and 60 controls (48 age-matched to the patients and 12 young participants) were enrolled in the study. The ground truth required to compare different techniques of BW estimation was manually delineated according to a predefined protocol. Seven methods were developed to estimate the BW, and four objective metrics were used to evaluate the results.
According to the metrics used, a method based on the Empirical Wavelet Transform provided the best performance for removing the BW. Also, a method based on the Empirical Mode Decomposition provided very satisfactory results1. Furthermore, the objective and subjective results show that potential asymmetries between left and right eyes movements due to calibration issues are solved by removing the BW of the SPEM.
Regardless of the techniques used, BW removal in SPEM is revealed to be a crucial step for any autonomous SPEM processing tool.
All source code used to generate the results and figures in the paper are in
the DEMO
folder.
The data used in this study is provided in data
and the sources for the
manuscript text and figures are in manuscript
.
Results generated by the code are saved in results
.
See the README.md
files in each directory for a full description.
You can download a copy of all the files in this repository by cloning the git repository:
git clone https://github.com/orgs/BYO-UPM/repositories.git
or download a zip archive.
A copy of the repository is also archived at 'DOI'
You'll need a working Matlab environment to run the code. The recommended way to set up your environment is through MATLAB and Statistics Toolbox Release R2021a, The MathWorks, Inc., Natick, Massachusetts, United States. The software is implemented using Graphical User Interface (GUI).
To run the GUI: 1- Open the Baseline_Wander_estimation.fig file using GUIDE and press the run button there (F5). 2- Open the Baseline_Wander_estimation.m file and press the run button there. 3- Type "Baseline_Wander_estimation" in the command window and press Enter button.
More Infromation can be found at the 'README' file inside the 'DEMO' directory.
All source code is made available under a 'MIT' license. You can freely use and modify the code, without warranty, so long as you provide attribution to the authors.
The manuscript text is not open source. The authors reserve the rights to the article content, which is currently submitted for publication in the journal 'IEEE Acsses'.