Classification of amyotrophic lateral sclerosis disease based on convolutional neural network and reinforcement sample learning algorithm

Abstract

Electromyogram (EMG) signals contain useful information of the neuromuscular diseases like amyotrophic lateral sclerosis (ALS). ALS is a well-known brain disease, which can progressively degenerate the motor neurons. In this paper, we propose a deep learning based method for efficient classification of ALS and normal EMG signals. Spectrogram, continuous wavelet transform (CWT), and smoothed pseudo Wigner-Ville distribution (SPWVD) have been employed for time-frequency (T-F) representation of EMG signals. A convolutional neural network is employed to classify these features. In it, Two convolution layers, two pooling layer, a fully connected layer and a lost function layer is considered in CNN architecture. The CNN architecture is trained with the reinforcement sample learning strategy. The efficiency of the proposed implementation is tested on publicly available EMG dataset. The dataset contains 89 ALS and 133 normal EMG signals with 24 kHz sampling frequency. Experimental results show 96.80% accuracy. The obtained results are also compared with other methods, which show the superiority of the proposed method.

Imaging Biomarkers for the Diagnosis and Prognosis of Neurodegenerative Diseases. The Example of Amyotrophic Lateral Sclerosis

“…These methods are not exclusive for MR imaging, and they can be used with other imaging techniques ( Segovia et al, 2017a , b ; Ortiz et al, 2019 ) and even with clinical, molecular, and genetic biomarkers applied to build a model of the pathology ( Latourelle et al, 2017 ). Some examples on this approach highlighting the benefits of this computer aided diagnosis (CAD) systems analysis is beyond the scope of this review but it’s worth mentioning some works as the following ( Sengur et al, 2017 ; van der Burgh et al, 2017 ; Martinez-Murcia et al, 2018 ; Yamashita et al, 2018 ).…”

Featureless EMG pattern recognition based on convolutional neural network

“…At the first stage, convolutional layer fixes up the units in a sequence of filters. The width and height of input image in each filter are convolved during the training process [21], [22]. For the second stage, the max pooling layer produces a non-linear sub-sampling.…”

Guest editorial: special issue on “Artificial Intelligence in Health and Medicine”

“…In "Classification of Amyotrophic Lateral Sclerosis Disease Based on Convolutional Neural Network and Reinforcement Sample Learning Algorithm" [3], the authors present a deep learning based artificial intelligent scheme for efficient identification of ALS from Electromyogram (EMG) signals. In this proposed scheme, the convolutional neural network (CNN) architecture is trained with the reinforcement sample learning strategy.…”