Deep learning for waveform identification of resting needle electromyography signals
Deep learning for waveform identification of resting needle electromyography signals
复制标题
DOI：
10.1016/j.clinph.2019.01.024
复制
发表时间：
2019-05-01
影响因子：
4.7
通讯作者：
Kaji, Ryuji
中科院分区：
文献类型：
--
作者：
Nodera, Hiroyuki;Osaki, Yusuke;Kaji, Ryuji
目的：鉴于机器学习和人工智能在医疗数据分析方面的最新进展，我们假设深度学习算法可以对静息针肌电图（nEMG）放电进行分类。方法：6个临床观察到的静息n肌电信号作为数据集。将数据转换成mel谱图。然后对训练数据进行数据增强。应用深度学习算法来评估正确分类的准确性，是否使用深度学习网络的预训练权值。结果：原始数据在测试数据集上的准确率高达0.86，而数据增强到20万张训练图像时，准确率显著提高到1.0。使用预先训练的权重（微调）比“从头开始训练”显示出更高的准确性。结论：利用深度学习算法，特别是利用数据增强和迁移学习技术，可以成功分类静息n-肌电图信号。意义：通过深度学习算法，临床n-肌电图检测的计算机辅助信号识别可能成为可能。(C) 2019国际临床神经生理学联合会。Elsevier B.V.版权所有。
Objective: Given the recent advent in machine learning and artificial intelligence on medical data analysis, we hypothesized that the deep learning algorithm can classify resting needle electromyography (nEMG) discharges.Methods: Six clinically observed resting n-EMG signals were used as a dataset. The data were converted to Mel-spectrogram. Data augmentation was then applied to the training data. Deep learning algorithms were applied to assess the accuracies of correct classification, with or without the use of pre-trained weights for deep-learning networks.Results: While the original data yielded the accuracy up to 0.86 on the test dataset, data-augmentation up to 200,000 training images showed significant increase in the accuracy to 1.0. The use of pre-trained weights (fine tuning) showed greater accuracy than "training from scratch".Conclusions: Resting n-EMG signals were successfully classified by deep-learning algorithm, especially with the use of data augmentation and transfer learning techniques.Significance: Computer-aided signal identification of clinical n-EMG testing might be possible by deep-learning algorithms. (C) 2019 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.