Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, 38106 Braunschweig, Germany; Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, 600036 Tamil Nadu, India.
Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, 600036 Tamil Nadu, India.
Comput Methods Programs Biomed. 2021 Mar;200:105931. doi: 10.1016/j.cmpb.2021.105931. Epub 2021 Jan 8.
Automated R-wave detection plays a vital role in electrocardiography (ECG) and ECG-based computer-aided diagnosis. Recently, a multi-level one-dimensional (1D) deep learning approach was presented that shows good performance as compared to traditional methods.
In this paper, we present several improvements of the multi-level 1D convolutional neural network (CNN)-based deep learning approach using: (i) adaptive deep learning, (ii) cross-database training, and (iii) cross-lead training. For this, we consider ECG signals from four publicly available databases: MIT-BIH, INCART, TELE, and SDDB, having 109,404, 175,660, 6,708, and 1,684,447 annotated beats, respectively. Except for TELE, all databases provide at least two-lead recordings. To evaluate the improvements, experiments are performed with adaptive k-times cross-trained databases validation scheme (k = 5). The hypothesis tested are: (i) the improvements outperform the state-of-the-art, (ii) cross-database training and adaptive deep learning contribute, and (iii) additional databases or cross-lead training further improves the results.
Our proposed approach outperforms the state-of-the-art. In terms of F-measure, F = 99.75% and F = 95.25% is obtained for the MIT-BIH and TELE databases, respectively. Further, cross-database training (F = 98.02%) is found to be more effective than training on individual databases (F = 97.33%). The performance of our approach further improves when additional databases and different leads are used for training.
Existing state-of-the-art methods perform low on noisy and pathological signals. Adaptive cross-data training identifies the optimal model. Using multiple datasets and leads allows analyzing noisy, pathological and mobile-recorded long-term ECG signals without ground truths. These conclusions are based on the comprehensive evaluation of four different databases, and in total, about 4.5 million annotated beats.
自动 R 波检测在心电图（ECG）和基于 ECG 的计算机辅助诊断中起着至关重要的作用。最近，提出了一种多层一维（1D）深度学习方法，与传统方法相比，该方法表现出了良好的性能。
在本文中，我们使用以下方法对基于多层 1D 卷积神经网络（CNN）的深度学习方法进行了几项改进：（i）自适应深度学习，（ii）跨数据库训练，和（iii）跨导联训练。为此，我们考虑了来自四个公开可用数据库的 ECG 信号：MIT-BIH、INCART、TELE 和 SDDB，分别具有 109404、175660、6708 和 1684447 个已注释的节拍。除了 TELE 之外，所有数据库都至少提供了两个导联的记录。为了评估改进，使用自适应 k 倍交叉训练数据库验证方案（k=5）进行实验。测试的假设是：（i）改进方法优于最先进的方法，（ii）跨数据库训练和自适应深度学习有贡献，以及（iii）额外的数据库或跨导联训练进一步提高了结果。
我们提出的方法优于最先进的方法。在 MIT-BIH 和 TELE 数据库中，F 度量分别为 99.75%和 95.25%。进一步，发现跨数据库训练（F=98.02%）比在单个数据库上训练（F=97.33%）更有效。当使用额外的数据库和不同的导联进行训练时，我们的方法的性能进一步提高。
现有的最先进的方法在嘈杂和病理信号上表现不佳。自适应交叉数据训练确定了最佳模型。使用多个数据集和导联可以在没有真实值的情况下分析嘈杂、病理和移动记录的长期 ECG 信号。这些结论是基于对四个不同数据库的综合评估得出的，总共约有 450 万个已注释节拍。
