Towards increased data transmission rate for a three-class metabolic brain–computer interface based on transcranial Doppler ultrasound

doi:10.1016/j.neulet.2012.09.030

Neuroscience Letters

Volume 528, Issue 2, 24 October 2012, Pages 99-103

https://doi.org/10.1016/j.neulet.2012.09.030 Get rights and content

Abstract

In this study, we conducted an offline analysis of transcranial Doppler (TCD) ultrasound recordings to investigate potential methods for increasing data transmission rate in a TCD-based brain–computer interface. Cerebral blood flow velocity was recorded within the left and right middle cerebral arteries while nine able-bodied participants alternated between rest and two different mental activities (word generation and mental rotation). We differentiated these three states using a three-class linear discriminant analysis classifier while the duration of each state was varied between 5 and 30 s. Maximum classification accuracies exceeded 70%, and data transmission rate was maximized at 1.2 bits per minute, representing a four-fold increase in data transmission rate over previous two-class analysis of TCD recordings.

Highlights

► We investigated the future viability of a three-class ultrasound-based BCI. ► We differentiated three mental states offline based on changes in blood flow. ► We determined the time window that maximized data transmission rate. ► Data transmission rate peaked when mental task length was 20 s. ► Classification accuracies exceeded 70% using time-domain features and LDA.

Introduction

Brain–computer interfaces (BCIs) allow users to generate control signals for external devices using only their thoughts [7]. Due to their ability to bypass typical output channels such as movement and speech, BCIs are of interest within the field of rehabilitation engineering [29]. Specifically, BCIs can be used as an alternative means of communication in individuals with severe physical disabilities resulting from conditions such as stroke and amyotrophic lateral sclerosis (ALS). In extreme cases, these disabilities can result in total immobility and inability to communicate while retaining full consciousness. This condition is referred to as “locked-in syndrome” (LIS) [26]. The provision of a means of communication for individuals with LIS continues to be an important goal of BCI research [8].

Previous non-invasive BCI research has focused on a small number of measurement modalities, of which the foremost has been electroencephalography (EEG) [3], [14]. Recent research has also investigated alternative measurement modalities such as functional magnetic resonance imaging (fMRI) and near-infrared spectroscopy (NIRS) [25], [32]. While EEG directly measures neuronal activity, fMRI and NIRS measure changes in blood hemoglobin concentrations [15]. Consequently, BCIs using the latter modalities are often referred to as hemodynamic or metabolic BCIs [19]. These BCIs do not generally possess the same temporal resolution as EEG BCIs, but have still attracted attention due to their intuitive training methods and robustness against electrical artifacts [10]. Recent research in this area has produced a number of real-time fMRI and NIRS-based BCIs [1], [4], [6], [11], [18]. These BCIs, many of which rely upon detection of motor imagery (e.g. imagined hand movement or finger tapping), suggest that metabolic BCIs are worthy of further study.

Another metabolic signal that may be suitable for BCI development is transcranial Doppler ultrasound (TCD) [20]. TCD measures cerebral blood flow velocity (CBFV) within the circle of Willis (the network of arteries that supply the brain) [30]. Cognitive activation produces increases in CBFV within these arteries that can be detected using TCD [28]. These changes have been observed for a wide variety of different mental tasks [31], suggesting the potential to automatically detect mental activity on the basis of changes in CBFV. This possibility was investigated by Myrden et al. in [20], where it was shown that two different mental activities (word generation and mental rotation) can be differentiated from rest with greater than 80% accuracy. However, these results were achieved using very long durations for each activity (45 s), yielding a very low data transmission rate. This limits the practicality of such a BCI. Consequently, improvement of the data transmission rate is necessary in order to demonstrate the practical viability of a TCD-based BCI.

In BCIs, data transmission rate depends on three parameters – the number of potential classes (N), the classification accuracy (P), and the state duration – the length of time for which a mental activity is performed before it is classified. The first two variables determine the data transmission rate in bits per trial (B), which can be expressed as [22], [33]:

$B = {log}_{2} (N) + P {log}_{2} (P) + (1 - P) {log}_{2} (\frac{1 - P}{N - 1})$

Using the state duration, data transmission rate can be converted to bits per second or bits per minute. It is clear that data transmission rate can be augmented by increasing either N or P, or by decreasing the state duration. The effects of each parameter on data transmission rate (in bits per minute) are shown in Fig. 1.

Increasing the number of classes and reducing state durations is likely to decrease classification accuracy. This limits the maximum achievable data transmission rate. In this paper, we investigate the net gain in data transmission rate that can be attained by varying these parameters for a TCD-based BCI. We have expanded the classification problem introduced in [20] to a three-class problem by attempting to differentiate word generation, mental rotation, and rest from each other. Furthermore, state durations have been limited to a range of durations between 5 and 30 s. If state durations can be substantially reduced without greatly decreasing classification accuracy, data transmission rate will be improved.

Section snippets

Participants

Nine able-bodied participants (6 female, mean age 25.6 ± 2.4 years) were recruited from the Bloorview Research Institute. All participants were right-handed, as quantified by the Edinburgh Handedness Inventory [21], with a mean score of 79.4 ± 16.3. Participants had no history of migraine and no known neurological, cardiopulmonary, or respiratory conditions. All participants gave informed written consent. This study was approved by the Research Ethics Boards of both Holland Bloorview Kids

Results

The mean classification accuracy across all participants using two and three-dimensional feature sets is displayed in Fig. 2 for state durations ranging from 5 to 30 s. Mean classification accuracy ranged between 40% and 69% for two-dimensional feature sets, and between 37% and 74% for three-dimensional feature sets. For both sets, classification accuracy increased with increasing state duration, but tended to stabilize as state duration exceeded 20 s. In Fig. 3, these curves have been converted

Discussion

In this study, we have shown that mean classification accuracies exceeding 70% can be achieved for a three-class problem within 20 s of the onset of cognitive activity using bilateral TCD measurements, time-domain features, and a linear classifier. This corresponds to a maximum data transmission rate of 1.2 bits per minute, compared to a maximum rate of 0.3 bits per minute previously reported for a TCD-based BCI [20]. This significant improvement highlights the advantages of a three-class BCI

Acknowledgments

This work was supported by the Canada Research Chairs program, the Natural Sciences and Engineering Research Council, Holland Bloorview Kids Rehabilitation Hospital, and Barbara and Frank Milligan.

References (33)

A.F. Abdelnour et al.
Real-time imaging of human brain function by near-infrared spectroscopy using an adaptive general linear model
NeuroImage
(2009)
B.D. Berman et al.
Self-modulation of primary motor cortex activity with motor and motor imagery tasks using real-time fMRI-based neurofeedback
NeuroImage
(2012)
N. Birbaumer et al.
Neurofeedback and brain–computer interface: clinical applications
International Review of Neurobiology
(2009)
J.J. Daly et al.
Brain–computer interfaces in neurological rehabilitation
Lancet Neurology
(2008)
L.A. Farwell et al.
Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials
Electroencephalography and Clinical Neurophysiology
(1988)
S.M. Laconte
Decoding fMRI brain states in real-time
NeuroImage
(2011)
R.C. Oldfield
The assessment and analysis of handedness: the Edinburgh inventory
Neuropsychologia
(1971)
R. Sitaram et al.
Temporal classification of multichannel near-infrared spectroscopy signals of motor imagery for developing a brain–computer interface
NeuroImage
(2007)
A. Alexandrov et al.
Practice standards for transcranial Doppler ultrasound: Part I – test performance
Journal of Neuroimaging
(2007)
B.Z. Allison et al.
Brain–computer interface systems: progress and prospects
Expert Review of Medical Devices
(2007)

H. Ayaz et al.

Assessment of cognitive neural correlates for a function near infrared-based brain computer interface system

Found Augmented Cognition. Neuroergonomics and Operational Neuroscience

(2009)

G. Bauernfeind et al.

Single-trial classification of antagonistic oxyhemoglobin responses during mental arithmetic

Medical & Biological Engineering & Computing

(2011)

N. Birbaumer

Breaking the silence: brain–computer interfaces (BCI) for communication and motor control

Psychophysiology

(2006)

N. Birbaumer et al.

Brain–computer interface in paralysis

Current Opinion in Neurology

(2008)

S. Coyle et al.

On the suitability of near-infrared (NIR) systems for next-generation brain–computer interfaces

Physiological Measurement

(2004)

S.M. Coyle et al.

Brain–computer interface using a simplified near-infrared spectroscopy system

Journal of Neural Engineering

(2007)

Cited by (13)

A brain-computer interface based on functional transcranial doppler ultrasound using wavelet transform and support vector machines
2018, Journal of Neuroscience Methods
Citation Excerpt :
The studies suggested in (Goyal et al., 2016), (Myrden et al., 2012) reported accuracies of 62.40% within 15 s (Goyal et al., 2016) and 40% within 5 s (Myrden et al., 2012) of the onset of the cognitive task. Moreover, the maximum classification accuracy over the whole observation period obtained by our approach was 72.91% achieved in 11.27 s compared to the previously reported 73.11% obtained in 24.90 s (Myrden et al., 2012). A maximum bit rate of 3.83 and 3.09 bits per minute were achieved for the binary and the 3-class problems respectively using the moving window method, while the incremental window achieved maximum bit rates of 3.95 and 2.28 bits per minute.
Functional transcranial Doppler (fTCD) is an ultrasound based neuroimaging technique used to assess neural activation that occurs during a cognitive task through measuring velocity of cerebral blood flow.
The objective of this paper is to investigate the feasibility of a 2-class and 3-class real-time BCI based on blood flow velocity in left and right middle cerebral arteries in response to mental rotation and word generation tasks. Statistical features based on a five-level wavelet decomposition were extracted from the fTCD signals. The Wilcoxon test and support vector machines (SVM), with a linear kernel, were employed for feature reduction and classification.
The experimental results showed that within approximately 3 s of the onset of the cognitive task average accuracies of 80.29%, and 82.35% were obtained for the mental rotation versus resting state and the word generation versus resting state respectively. The mental rotation task versus word generation task achieved an average accuracy of 79.72% within 2.24 s from the onset of the cognitive task. Furthermore, an average accuracy of 65.27% was obtained for the 3-class problem within 4.68 s.
The results presented here provide significant improvement compared to the relevant fTCD-based systems presented in literature in terms of accuracy and speed. Specifically, the reported speed in this manuscript is at least 12 and 2.5 times faster than any existing binary and 3-class fTCD-based BCIs, respectively.
These results show fTCD as a promising and viable candidate to be used towards developing a real-time BCI.
An online three-class Transcranial Doppler ultrasound brain computer interface
2016, Neuroscience Research
Citation Excerpt :
However, lengthy task durations were required, limiting the data transmission rate. In a follow-up study using a three-class LDA, Myrden et al. (2012) varied the amount of time needed for the tasks, reporting that accuracies in excess of 70% could be attained with approximately 18 s task durations. Subsequently, Aleem and Chau (2013) proposed a user-independent TCD BCI.
Brain computer interfaces (BCI) can provide communication opportunities for individuals with severe motor disabilities. Transcranial Doppler ultrasound (TCD) measures cerebral blood flow velocities and can be used to develop a BCI. A previously implemented TCD BCI system used verbal and spatial tasks as control signals; however, the spatial task involved a visual cue that awkwardly diverted the user's attention away from the communication interface. Therefore, vision-independent right-lateralized tasks were investigated. Using a bilateral TCD BCI, ten participants controlled online, an on-screen keyboard using a left-lateralized task (verbal fluency), a right-lateralized task (fist motor imagery or 3D-shape tracing), and unconstrained rest. 3D-shape tracing was generally more discernible from other tasks than was fist motor imagery. Verbal fluency, 3D-shape tracing and unconstrained rest were distinguished from each other using a linear discriminant classifier, achieving a mean agreement of κ = 0.43 ± 0.17. These rates are comparable to the best offline three-class TCD BCI accuracies reported thus far. The online communication system achieved a mean information transfer rate (ITR) of 1.08 ± 0.69 bits/min with values reaching up to 2.46 bits/min, thereby exceeding the ITR of previous online TCD BCIs. These findings demonstrate the potential of a three-class online TCD BCI that does not require visual task cues.
Pattern classification to optimize the performance of Transcranial Doppler Ultrasonography-based brain machine interface
2015, Pattern Recognition Letters
Citation Excerpt :
This offline result exceeds the chance level and compares favorably to findings of previous studies, while considering the shortest data collection window to date and a combination of computationally efficient features and classifier. In fact, the present finding supports the methodological choices in [23] though SVM may be a viable classifier for TCD–BCI when used with WSFS in future online studies. Past TCD studies have shown that verbal fluency tasks tend to induce a left-lateralized increase in MCA CBFV in right-handed individuals [10].
Transcranial Doppler Ultrasonography (TCD) is an emerging brain–computer interface (BCI) modality. Previous offline studies have demonstrated algorithmic differentiation between two mental tasks with accuracies in excess of chance, but have used computationally sophisticated features and classifiers. A preferred approach for eventual online implementation has not yet been identified. In this study, we conducted an offline analysis of TCD recordings to investigate the potential for increasing accuracy in a TCD-based BCI while adhering to features and classifiers computationally conducive to online implementation. We re-examined blood flow velocities from Lu et al. (2014), recorded from the left and right middle cerebral arteries of 10 able-bodied participants during the performance of two different mental activities (mental spelling and visual tracking). Invoking a signal processing and pattern classification method from previous offline TCD studies, we obtained an average accuracy of 73.32 ± 4.09%. We subsequently compared systematic feature selection approaches (Fisher criterion, sequential forward selection, weighted sequential forward selection) and three classifiers, namely, linear discriminant analysis (LDA), Naïve Bayes (NB), and support vector machine (SVM). With the combination of weighted sequential forward selection (WSFS), which yielded less than a handful of time domain features, and a SVM classifier, a maximum accuracy of 87.60 ± 3. 27% was attained. Similar results were achieved with sequential forward selection and a SVM classifier. Our findings support the development of highly accurate online TCD–BCIs with computationally simple features.
Sequential hypothesis testing for automatic detection of task-related changes in cerebral perfusion in a brain-computer interface
2015, Neuroscience Research
Citation Excerpt :
The data transmission rate (DTR) incorporates the effects of both classification accuracy and decision time. It can be expressed in bits per trial as (Myrden et al., 2012): Classification accuracies, decision times, and data transmission rates for each participant are presented in Table 2.
Evidence suggests that the cerebral blood flow patterns accompanying cognitive activity are retained in many locked-in patients. These patterns can be monitored using transcranial Doppler ultrasound (TCD), a medical imaging technique that measures bilateral cerebral blood flow velocities. Recently, TCD has been proposed as an alternative imaging modality for brain–computer interfaces (BCIs). However, most previous TCD-BCI studies have performed offline analyses with impractically lengthy tasks. In this study, we designed a BCI that automatically differentiates between counting and verbal fluency tasks using sequential hypothesis testing to make decisions as quickly as possible. Ten able-bodied participants silently alternated between counting and verbal fluency tasks within the paradigm of a simulated on-screen keyboard. During this experiment, blood flow velocities were recorded within the left and right middle cerebral arteries using bilateral TCD. Twelve features were used to characterize TCD signals. In a simulated online analysis, sequential hypothesis testing was used to update estimates of class probability every 250 ms as TCD data were processed. Classification was terminated once a threshold level of certainty was reached. Mean classification accuracy across all participants was 72% after an average of 23 s, compared to an offline analysis which obtained a classification accuracy of 80% after 45 s. This represents a substantial gain in data transmission rate, while maintaining classification accuracies exceeding 70%. Furthermore, a range of decision times between 19 and 28 s was observed, suggesting that the ability of sequential hypothesis testing to adapt the task duration for each individual participant is critical to achieving consistent performance across participants. These results indicate that sequential hypothesis testing is a promising alternative for online TCD-BCIs.
An analysis of cerebral blood flow from middle cerebral arteries during cognitive tasks via functional transcranial Doppler recordings
2014, Neuroscience Research
Functional transcranial Doppler (fTCD) is a useful medical imaging technique to monitor cerebral blood flow velocity (CBFV) in major cerebral arteries. In this paper, CBFV changes in the right and left middle cerebral arteries (MCA) caused by cognitive tasks, such as word generation tasks and mental rotation tasks, were examined using fTCD. CBFV recordings were collected from 20 healthy subjects (10 females, 10 males). We obtained both the raw CBFV signal and the envelope CBFV signal, which is the maximal velocity to gain more information about the changes and hemisphere lateralization in cognitive tasks compared to the resting state. Time, frequency, time–frequency, and information-theoretic features were calculated and compared. Sex effects were also taken into consideration. The results of our analysis demonstrated that the raw CBFV signal contained more descriptive information than the envelope signals. Furthermore, both types of cognitive tasks produced higher values in most signal features. Geometric tasks were more distinguished from the rest-state than verbal tasks and the lateralization was exhibited in right MCA during geometric tasks. Our results show that the raw CBFV signals provided valuable information when studying the effects of cognitive tasks and lateralization in the MCA.
Assessment of Resting-State Blood Flow Through Anterior Cerebral Arteries Using Trans-cranial Doppler Recordings
2013, Ultrasound in Medicine and Biology
Trans-cranial Doppler (TCD) recordings are used to monitor cerebral blood flow in the main cerebral arteries. The resting state is usually characterized by the mean velocity or the maximum Doppler shift frequency (an envelope signal) by insonating the middle cerebral arteries. In this study, we characterized cerebral blood flow in the anterior cerebral arteries. We analyzed both envelope signals and raw signals obtained from bilateral insonation. We recruited 20 healthy patients and conducted the data acquisition for 15 min. Features were extracted from the time domain, the frequency domain and the time-frequency domain. The results indicate that a gender-based statistical difference exists in the frequency and time-frequency domains. However, no handedness effect was found. In the time domain, information-theoretic features indicated that mutual dependence is higher in raw signals than in envelope signals. Finally, we concluded that insonation of the anterior cerebral arteries serves as a complement to middle cerebral artery studies. Additionally, investigation of the raw signals provided us with additional information that is not otherwise available from envelope signals. Use of direct trans-cranial Doppler raw data is therefore validated as a valuable method for characterizing the resting state.

View all citing articles on Scopus

View full text

Towards increased data transmission rate for a three-class metabolic brain–computer interface based on transcranial Doppler ultrasound

Abstract

Highlights

Introduction

Section snippets

Participants

Results

Discussion

Acknowledgments

NeuroImage

NeuroImage

International Review of Neurobiology

Lancet Neurology

Electroencephalography and Clinical Neurophysiology

NeuroImage

Neuropsychologia

NeuroImage

Practice standards for transcranial Doppler ultrasound: Part I – test performance

Journal of Neuroimaging

Brain–computer interface systems: progress and prospects

Expert Review of Medical Devices

Assessment of cognitive neural correlates for a function near infrared-based brain computer interface system

Found Augmented Cognition. Neuroergonomics and Operational Neuroscience

Single-trial classification of antagonistic oxyhemoglobin responses during mental arithmetic

Medical & Biological Engineering & Computing

Breaking the silence: brain–computer interfaces (BCI) for communication and motor control

Psychophysiology

Brain–computer interface in paralysis

Current Opinion in Neurology

On the suitability of near-infrared (NIR) systems for next-generation brain–computer interfaces

Physiological Measurement

Brain–computer interface using a simplified near-infrared spectroscopy system

Journal of Neural Engineering