Automatic Recognition of Auditory Brainstem Response Characteristic Waveform Based on Bidirectional Long Short-Term Memory.
Automatic Recognition of Auditory Brainstem Response Characteristic Waveform Based on Bidirectional Long Short-Term Memory.
复制标题
基于双向长短时记忆的听觉脑干反应特征波形自动识别
DOI：
10.3389/fmed.2020.613708
复制
发表时间：
2020
影响因子：
3.9
通讯作者：
Xiao R
中科院分区：
文献类型：
--
作者：
Chen C;Zhan L;Pan X;Wang Z;Guo X;Qin H;Xiong F;Shi W;Shi M;Ji F;Wang Q;Yu N;Xiao R
背景：听性脑干反应（ABR）测试是一种有创性电生理听觉功能测试。它的波形和阈值能反映脑干听觉中枢的听觉功能变化，在临床上广泛用于听力障碍的诊断。然而，识别其波形和阈值主要依赖于实验人员的手动识别，这可能主要受个人经验的影响。这在临床实践中也是一项繁重的工作。方法：本工作记录了人类ABR。首先，创建二值化以相应地标记1，024个采样点。ABR数据的特征区域选取范围为0-8 ms，通过扩大标记区域，扩大特征信息，减少标记误差。其次，建立双向长短期记忆（BiLSTM）网络结构，提高采样点的相关性，并通过训练得到ABR采样点分类器。最后通过阈值分割得到标记点。结果如下：通过对614组ABR临床数据的分析，探讨了神经网络的具体结构、相关参数、识别效果和抗噪能力。实验结果表明，每个数据的平均检测时间为0.05 s，识别准确率达到92.91%。讨论：该研究提出了一种自动识别ABR波形使用的BiLSTM为基础的机器学习技术。实验结果表明，该方法可以减少记录时间，帮助医生进行诊断，具有一定的临床应用价值。
Background: Auditory brainstem response (ABR) testing is an invasive electrophysiological auditory function test. Its waveforms and threshold can reflect auditory functional changes in the auditory centers in the brainstem and are widely used in the clinic to diagnose dysfunction in hearing. However, identifying its waveforms and threshold is mainly dependent on manual recognition by experimental persons, which could be primarily influenced by individual experiences. This is also a heavy job in clinical practice. Methods: In this work, human ABR was recorded. First, binarization is created to mark 1,024 sampling points accordingly. The selected characteristic area of ABR data is 0–8 ms. The marking area is enlarged to expand feature information and reduce marking error. Second, a bidirectional long short-term memory (BiLSTM) network structure is established to improve relevance of sampling points, and an ABR sampling point classifier is obtained by training. Finally, mark points are obtained through thresholding. Results: The specific structure, related parameters, recognition effect, and noise resistance of the network were explored in 614 sets of ABR clinical data. The results show that the average detection time for each data was 0.05 s, and recognition accuracy reached 92.91%. Discussion: The study proposed an automatic recognition of ABR waveforms by using the BiLSTM-based machine learning technique. The results demonstrated that the proposed methods could reduce recording time and help doctors in making diagnosis, suggesting that the proposed method has the potential to be used in the clinic in the future.
登录
查看更多内容
影响因子：
1.6
作者：
Bradley, AP;Wilson, WJ
通讯作者：
Wilson, WJ
影响因子：
5.1
作者：
Fallatah, Anwar;Dajani, Hilmi R.
通讯作者：
Dajani, Hilmi R.
影响因子：
2.4
作者：
Lewis, James D.;Kopun, Judy;Gorga, Michael P.
通讯作者：
Gorga, Michael P.
影响因子：
2.7
作者：
Madsen, Sara M. K.;Harte, James M.;Dau, Torsten
通讯作者：
Dau, Torsten
影响因子：
6.1
作者：
Krumbholz K;Hardy AJ;de Boer J
通讯作者：
de Boer J