Decoding human brain states using Transcranial Doppler Ultrasonography

Transcranial Doppler Ultrasonography (TCD) has emerged as a Brain-computer Interface (BCI) modality with great promise and potential. TCD is a non-invasive ultrasound technology that detects the changes in cerebral blood flow velocity (CBFV) which has recently been used as a functional brain imaging tool to examine the effects of mental tasks on the blood flow velocities, particularly focusing on the middle cerebral arteries (MCAs). Individuals, having cognitive awareness but severe neuro-motor disabilities like muscular dystrophy or spinal cord injuries, face difficulties to communicate with their surroundings. Changes in blood flow velocity in the MCAs are an indication of mental activation in human brain which could lead us to identifying various brain states. Blood flow lateralization elicited by mental tasks, such as verbal fluency and visualization tasks, has been detected using TCD in a number of recent studies. In this study, CBFV was measured simultaneously within the left and right middle cerebral arteries for alternated mental activation and relaxation tasks from ten able-bodied participants. Signal features were extracted and then selected using the Fisher Criterion and Sequential Forward Search (SFS) approach. Two classification methods, Linear Discriminant Analysis and a Naïve Bayes Classifier were employed to decode mental activation and relaxation tasks. Preliminary results show an average accuracy, sensitivity (activation) and specificity (relaxation) of 79.13 ± 3.85%, 78.88 ± 6.44% and 79.38 ± 5.57% respectively. The results are very much encouraging and indicate that TCD could be a viable alternative BCI modality and demands for further exploration for improvement and potential real world applications.