Online transcranial Doppler ultrasonographic control of an onscreen keyboard

• Published in: Frontiers in human neuroscience Vol. 8; p. 199
• Main Authors: Lu, Jie, Mamun, Khondaker A, Chau, Tom
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 22.04.2014; Frontiers Media S.A
• Subjects: Accuracy; Bayesian analysis; BCI; Blood flow; Brain; Brain research; Cerebral blood flow; Classification; Communication; Computer applications; Doppler effect; Electroencephalography; Flow velocity; Handedness; hemodynamic response; Hemodynamics; Implants; Internet; Keyboards; lateralization; Middle Cerebral Artery; Neuroscience; Rehabilitation; Scanning; Spectrum analysis; Studies; TCD; Ultrasonic imaging; Ultrasonic transducers; Ultrasonography; Ultrasound; Young adults; Canada; lateralization; BCI; hemodynamic response; TCD; communication; middle cerebral artery
• ISSN: 1662-5161; 1662-5161
• DOI: 10.3389/fnhum.2014.00199

Brain-computer interface (BCI) systems exploit brain activity for generating a control command and may be used by individuals with severe motor disabilities as an alternative means of communication. An emerging brain monitoring modality for BCI development is transcranial Doppler ultrasonography (TCD), which facilitates the tracking of cerebral blood flow velocities associated with mental tasks. However, TCD-BCI studies to date have exclusively been offline. The feasibility of a TCD-based BCI system hinges on its online performance. In this paper, an online TCD-BCI system was implemented, bilaterally tracking blood flow velocities in the middle cerebral arteries for system-paced control of a scanning keyboard. Target letters or words were selected by repetitively rehearsing the spelling while imagining the writing of the intended word, a left-lateralized task. Undesired letters or words were bypassed by performing visual tracking, a non-lateralized task. The keyboard scanning period was 15 s. With 10 able-bodied right-handed young adults, the two mental tasks were differentiated online using a Naïve Bayes classification algorithm and a set of time-domain, user-dependent features. The system achieved an average specificity and sensitivity of 81.44 ± 8.35 and 82.30 ± 7.39%, respectively. The level of agreement between the intended and machine-predicted selections was moderate (κ = 0.60). The average information transfer rate was 0.87 bits/min with an average throughput of 0.31 ± 0.12 character/min. These findings suggest that an online TCD-BCI can achieve reasonable accuracies with an intuitive language task, but with modest throughput. Future interface and signal classification enhancements are required to improve communication rate.