EEG Source Imaging Enhances the Decoding of Complex Right-Hand Motor Imagery Tasks

Abstract

Goal Sensorimotor-based brain-computer interfaces (BCIs) have achieved successful control of real and virtual devices in up to three dimensions; however, the traditional sensor-based paradigm limits the intuitive use of these systems. Many control signals for state-of-the-art BCIs involve imagining the movement of body parts that have little to do with the output command, revealing a cognitive disconnection between the user’s intent and the action of the end effector. Therefore, there is a need to develop techniques which can identify with high spatial resolution the self-modulated neural activity reflective of the actions of a helpful output device. Methods We extend previous EEG source imaging (ESI) work to decoding natural hand/wrist manipulations by applying a novel technique to classifying four complex motor imaginations of the right hand: flexion, extension, supination and pronation. Results We report an increase of up to 18.6% for individual task classification and 12.7% for overall classification using the proposed ESI approach over the traditional sensor-based method. Conclusion ESI is able to enhance BCI performance of decoding complex right hand motor imagery tasks. Significance The present work may lead to the development of BCI systems with naturalistic and intuitive motor imaginations, thus facilitating broad use of non-invasive BCIs.

SOPHIA: Soft Orthotic Physiotherapy Hand Interactive Aid

“…An electroencephalogram (EEG) can record sensorimotor rhythm activities (Yuan and He, 2014;Edelman et al, 2016) and show clear functional specificity during planned, actual, or imagined movements. These imagined movements of extremities cause specific EEG patterns, such as a desynchronization of mu and central beta rhythms at the contralateral sensorimotor area (Pfurtscheller et al, 2006).…”

Channel Selection with EEG Source Imaging

“…The source analysis methods, which are used to analysis brain signals in source spaces and translate noninvasively recorded scalp signals into physical regions, are potential methods for us to explore the inner workings of the brain [11]. Taking advantage of source analysis methods such as equivalent dipole model and cortical imaging technique are thought to be potential methods for classifying MI tasks in BCI systems.…”

“…Pascual-Marqui came up with another method named standard low-resolution electromagnetic tomography (sLORETA) [13] with zero location error. Brad Edelman [11] used weighted minimum norm estimate (WMNE) to search out the optimal source distribution; the results showed that four-class classification of right hand tasks by using EEG source imaging approach were able to improve nearly 10% compared with traditional technology. Xu et al proposed NEtwork based SOurce Imaging (NESOI) method [14].…”

Data-driven forward model inference for EEG brain imaging

“…However, the macroscopic EEG signal is generally believed to originate from well-localized gray matter sources [8,9], and therefore makes full 3D spatial reconstruction of the dipole source distribution a valuable imaging modality. The source reconstruction process has been shown to reduce non-brain artifact signal components [10]; it allows incorporation of spatial a priori information from functional activation databases [11]; and it generally leads to improved interpretability [12,13] by reducing the blurring effects of volume conduction.…”