Ganapathy Nagarajan, Swaminathan Ramakrishnan, Deserno Thomas M
Peter L. Reichertz Institute for Medical Informatics, University of Braunschweig - Institute of Technology and Hannover Medical School, Braunschweig, Germany.
Indian Institute of Technology Madras, Chennai, India.
Yearb Med Inform. 2018 Aug;27(1):98-109. doi: 10.1055/s-0038-1667083. Epub 2018 Aug 29.
Deep learning models such as convolutional neural networks (CNNs) have been applied successfully to medical imaging, but biomedical signal analysis has yet to fully benefit from this novel approach. Our survey aims at (i) reviewing deep learning techniques for biosignal analysis in computer- aided diagnosis; and (ii) deriving a taxonomy for organizing the growing number of applications in the field.
A comprehensive literature research was performed using PubMed, Scopus, and ACM. Deep learning models were classified with respect to the (i) origin, (ii) dimension, and (iii) type of the biosignal as input to the deep learning model; (iv) the goal of the application; (v) the size and (vi) type of ground truth data; (vii) the type and (viii) schedule of learning the network; and (ix) the topology of the model.
Between January 2010 and December 2017, a total 71 papers were published on the topic. The majority (n = 36) of papers are on electrocariography (ECG) signals. Most applications (n = 25) aim at detection of patterns, while only a few (n = 6) at predection of events. Out of 36 ECG-based works, many (n = 17) relate to multi-lead ECG. Other biosignals that have been identified in the survey are electromyography, phonocardiography, photoplethysmography, electrooculography, continuous glucose monitoring, acoustic respiratory signal, blood pressure, and electrodermal activity signal, while ballistocardiography or seismocardiography have yet to be analyzed using deep learning techniques. In supervised and unsupervised applications, CNNs and restricted Boltzmann machines are the most and least frequently used, (n = 34) and (n = 15), respectively.
Our key-code classification of relevant papers was used to cluster the approaches that have been published to date and demonstrated a large variability of research with respect to data, application, and network topology. Future research is expected to focus on the standardization of deep learning architectures and on the optimization of the network parameters to increase performance and robustness. Furthermore, application-driven approaches and updated training data from mobile recordings are needed.
卷积神经网络（CNN）等深度学习模型已成功应用于医学成像，但生物医学信号分析尚未充分受益于这种新方法。我们的调查旨在：（i）回顾计算机辅助诊断中生物信号分析的深度学习技术；（ii）推导一种分类法，用于组织该领域中不断增加的应用。
使用PubMed、Scopus和ACM进行了全面的文献研究。深度学习模型根据以下方面进行分类：（i）作为深度学习模型输入的生物信号的来源、（ii）维度和（iii）类型；（iv）应用的目标；（v）真实数据的大小和（vi）类型；（vii）学习网络的类型和（viii）时间表；以及（ix）模型的拓扑结构。
在2010年1月至2017年12月期间，共发表了71篇关于该主题的论文。大多数论文（n = 36）是关于心电图（ECG）信号的。大多数应用（n = 25）旨在检测模式，而只有少数（n = 6）旨在预测事件。在36项基于心电图的研究中，许多（n = 17）与多导联心电图有关。调查中确定的其他生物信号包括肌电图、心音图、光电容积脉搏波描记术、眼电图、连续血糖监测、声学呼吸信号、血压和皮肤电活动信号，而心冲击图或心震图尚未使用深度学习技术进行分析。在监督和无监督应用中，CNN和受限玻尔兹曼机分别是使用最频繁和最不频繁的，分别为（n = 34）和（n = 15）。
我们对相关论文的关键代码分类用于对迄今为止发表的方法进行聚类，并表明在数据、应用和网络拓扑方面存在很大的研究差异。未来的研究预计将集中在深度学习架构的标准化以及网络参数的优化上，以提高性能和鲁棒性。此外，需要应用驱动的方法和来自移动记录的更新训练数据。
