Millions of people worldwide suffer motor or sensory impairment due to stroke, spinal cord injury, multiple sclerosis, traumatic brain injury, diabetes, and motor neuron diseases such as ALS (amyotrophic lateral sclerosis). A brain-computer interface (BCI), which links the brain directly to a computer, offers a new way to study the brain and potentially restore function in patients living with debilitating conditions. One of the challenges currently facing BCI technology, however, is how to minimize surgical risk. Minimally invasive techniques, such as stereoelectroencephalography (SEEG) have become more widely used in clinical applications since they can lead to fewer complications. SEEG electrodes also give access to sulcal and white matter areas of the brain but have not been widely studied in brain-computer interfaces. We therefore investigated the viability of using SEEG electrodes in a BCI for recording and decoding neural signals related to movement and the sense of touch and compared its performance to electrocorticography electrodes (ECoG) placed on gyri. Initial poor decoding performance and the observation that most neural modulation patterns were variable trial-to-trial and transient (significantly shorter than the sustained finger movements studied), led to the development of a feature selection method based on temporal autocorrelation, a repeatability metric. An algorithm based on temporal autocorrelation was developed to isolate features that consistently repeated (required for accurate decoding) and possessed information content related to movement or touch-related stimuli. We subsequently used these features, along with deep learning methods, to automatically classify various motor and sensory events for individual fingers with high accuracy. Repeating features were found in sulcal, gyral, and white matter areas and were predominantly phasic or phasic-tonic across a wide frequency range for both HD (high density) ECoG and SEEG recordings. These findings motivated the use of long short-term memory (LSTM) recurrent neural networks (RNNs) which are well-suited to handling both transient and sustained input features. Combining temporal autocorrelation-based feature selection with LSTM yielded decoding accuracies of up to 92.04 +/- 1.51% for hand movements, up to 91.69 +/- 0.49% for individual finger movements, and up to 80.64 +/- 1.64% for focal tactile stimuli to the finger pads and palm while using a relatively small number of SEEG electrodes. These findings may lead to a new class of minimally invasive brain-computer interface systems in the future, increasing its applicability to a wider variety of conditions.
Feature Selection and Blind Source Separation in an EEG-Based Brain-Computer Interface
