LFP-Net: A deep learning framework to recognize human behavioral activities using brain STN-LFP signals

• Published in: Journal of neuroscience methods 2020-04, Vol.335, p.108621-108621, Article 108621
• Main Authors: Golshan, Hosein M., Hebb, Adam O., Mahoor, Mohammad H.
• Format: Article
• Language: English
• Subjects: Behavior classification; Convolutional neural networks; Deep brain stimulation; Local field potential; Time-frequency analysis
• ISSN: 0165-0270; 1872-678X
• DOI: 10.1016/j.jneumeth.2020.108621

•Developed a deep convolutional neural network for behavior classification using brain STN-LFP signals.•Developed a wavelet-based feature extraction method for analysis of STN-LFP signals.•Evaluated the performance of the proposed classification method on human subjects with Parkinson’s disease. Recognition of human behavioral activities using local field potential (LFP) signals recorded from the Subthalamic Nuclei (STN) has applications in developing the next generation of deep brain stimulation (DBS) systems. DBS therapy is often used for patients with Parkinson’s disease (PD) when medication cannot effectively tackle patients’ motor symptoms. A DBS system capable of adaptively adjusting its parameters based on patients’ activities may optimize therapy while reducing the stimulation side effects and improving the battery life. STN-LFP reveals motor and language behavior, making it a reliable source for behavior classification. This paper presents LFP-Net, an automated machine learning framework based on deep convolutional neural networks (CNN) for classification of human behavior using the time-frequency representation of STN-LFPs within the beta frequency range. CNNs learn different features based on the beta power patterns associated with different behaviors. The features extracted by the CNNs are passed through fully connected layers and then to the softmax layer for classification. Our experiments on ten PD patients performing three behavioral tasks including “button press”, “target reaching”, and “speech” show that the proposed approach obtains an average classification accuracy of ∼88 %. Comparison with existing methods: The proposed method outperforms other state-of-the-art classification methods based on STN-LFP signals. Compared to well-known deep neural networks such as AlexNet, our approach gives a higher accuracy using significantly fewer parameters. CNNs show a high performance in decoding the brain neural response, which is crucial in designing the automatic brain-computer interfaces and closed-loop systems.