Approach to Quantify Abnormal Gaze for pre-clinical/clinical Posterior Cerebral Artery Stroke Diagnosis
Investigating the need for calibrating a commercial eye tracker to acquire clinically relevant gaze information
Developing a method to acquire clinically relevant non-calibrated gaze information from RGB-camera
Developing a Machine Learning framework to perform classification on Posterior Cerebral Artery Stroke patients
Automated eye-tracking technology could enhance diagnosis for many neurological diseases, including stroke. Current literature focuses on gaze estimation through a form of calibration. However, patients with neuro-ocular abnormalities may have difficulty completing a calibration procedure due to inattention or other neurological deficits. We investigated 1) the need for calibration to measure eye movement symmetry in healthy controls and 2) the potential of eye movement symmetry to distinguish between healthy controls and patients. We analyzed fixations, smooth pursuits, saccades, and conjugacy measured by a Spearman correlation coefficient and utilized a linear mixed-effects model to estimate the effect of calibration. We found that (1) calibration is not required while measuring conjugacy of eye movement, (2) automated eye tracking can be deployed without calibration to measure between normal and abnormal eye movement symmetry. Link
We report a novel eye-movement assessment method using a digital camera to measure eye conjugacy in healthy individuals while performing a neurological examination. This is clinically significant because this approach overcomes the limitations of complex and expensive setups (e.g., infrared cameras) that often make it impractical to scale up and translate to clinical use. Moreover, this approach removes the need for a calibration procedure which has caused prior studies to exclude participants, potentially introducing selection bias and limiting generalizability. Our study suggests that this technology could be deployed for clinical use in the clinic or pre-hospital setting, including telemedicine or emergency medical services (EMS), encounters to detect neurological injury or diseases that cause neuro-ocular deficits, like stroke.
Code Digital Adaptation of Neurological Examination (Neuro Eye): https://github.com/Hfactor008/NeuroEye
Data & Code NeuroEye Pupil Center Dataset: https://www.kaggle.com/datasets/mahassan8/neuroeye
M. A. Hassan, et al.,A Digital Camera-based Eye Movement Assessment Method for NeuroEye Examination, IEEE JBHI., 2023
M. A. Hassan, et al., Approach to Quantify Eye Movements to Augment Stroke Diagnosis With a Non-Calibrated Eye-Tracker, IEEE T. Bio. Eng., 2022
..., M. A. Hassan, System, Method and Computer Readable Medium for Video-Based Facial Weakness Analysis for Detecting Neurological Deficits, US Patent, 2022
M. A. Hassan, et al., A Pilot Study on Video-based Eye Movement Assessment of the NeuroEye Examination, EMBS-BHI 2021
M. A. Hassan, et al., Comparison of Calibration vs Non-Calibration Techniques in the Automated Capture of Eye Movement Data: Initial Validation of the Roadie Device for Detecting PCS, STROKE, 2021
..., M. A. Hassan, et al.,Comparison of Calibration vs Non-calibration Techniques in the Automated Capture Of Eye Movement Data: Initial Validation of the ROADIE Device, Neurology, 2021
..., M. A. Hassan, et al.,Video-Based Facial Weakness Analysis, IEEE T. Bio. Eng., 2021
