Wavelet-based Multi-branch Convolutional Neural Network for Cross-individual ALS Disease Identification with EMG Signal

Although the needle Electromyography (EMG) is an efficient means for Amyotrophic Lateral Sclerosis (ALS) diagnosis, the proper selection of muscles with high sensitivity is an important issue in clinical application. In this paper, we propose a new deep learning method called Wavelet-based Multi-branch Convolutional Neural Network (WM-CNN) for cross-individual ALS disease identification. The proposed method uses the multi-branch network as framework to learn the relationship among EMG samples of an EMG recording, in which each sub-network with three wavelet-based convolution layers (WCL) is used to extract features of the corresponding sample. Experiments show that the proposed method obtains better performance in cross-individual and cross-muscle experiments compared with other methods, which implies that the proposed method can extract general features of neurogenic injury and could be helpful to find proper muscles more sensitive for ALS disease identification.