Precise and efficient heartbeat classification using a novel lightweight-modified method. (July 2021)

• Record Type: Journal Article
• Authors: Liu, Yunqing; Jin, Yanrui; Liu, Jinlei; Qin, Chengjin; Lin, Ke; Shi, Haotian; Tao, Jianfeng; Zhao, Liqun; Liu, Chengliang
• Is Part Of: Biomedical signal processing and control. Volume 68(2021)
• Publication Date: 2021-07
• Subjects: Electrocardiogram -- Heartbeat classification -- 2D convolutional neural network -- Lightweight-modified method; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102771
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: We propose a novel lightweight-modified two-dimensional neural network for heartbeat classification. It takes the modified VGGNet network as the backbone and contains inverted residual with linear bottleneck module. Compared with the existing methods, it can reduce the computational complexity and improve classification efficiency. It could effectively ensure the accuracy of heartbeat classification. It would be helpful for the application of original two-dimensional ECG in computer-aided diagnosis. Abstract: Background and objective: Development of lightweight model with high accuracy is an important study in order to better transfer arrhythmia diagnostic models to mobile terminals or embedded devices. Methods: A novel lightweight-modified two-dimensional neural network is presented for accurately identifying whether certain types of heartbeats are occurred based on information of heartbeat images. The MIT-BIH arrhythmia database is taken as the dataset. Firstly, data preprocessing is performed that one-dimensional ECG signals are converted into two-dimensional heartbeat images. Then, the obtained heartbeat images are fed into the proposed two-dimensional network for training. Moreover, in order to reduce the network model parameters, we integrate the small-scale convolution kernels and inverted residual with linear bottleneck module into the proposed network. Finally, comparisons of several related classification networks are conducted to verify the effectiveness and superiority of the proposed method. Results: Result shows the classification accuracy is 99.41 % in the test dataset originated in the aforementioned MIT-BIH database. The TPR of APC, LBBB, Normal, RBBB and VPC are 0.995, 1.0, 0.993, 1.0, 0.994, respectively. Compared with VGG16, the number of parameters is reduced by 8, 525, 312, and it achieves the optimal in network complexity and accuracy among the related networks of heartbeat classification. In terms of time consumption, the network proposed is better than some networks suitable for image classification. It takes around 0.0039478 s to complete the heartbeat classification of each ECG image using the proposed method. Conclusions: Result shows the effectiveness of the new method and the simplicity of the model parameters.