基于注意力机制与卷积神经网络的不均衡多标签心电图分类方法研究
Attention-Based Convolutional Neural Network for Imbalanced Multi-Label Electrocardiogram
DOI: 10.12677/mos.2024.134391, PDF,    科研立项经费支持
作者: 张诗雨：上海理工大学理学院，上海；孙占全, 顾浩丞, 陈骏立：上海理工大学光电信息与计算机工程学院，上海
关键词: 心电信号分类；多标签；注意力机制；Transformer；深度学习；Electrocardiogram Classification； Multi-Label； Attention； Transformer； Deep Learning
摘要: 心血管疾病是全球主要死因之一，及早发现心脏病的风险因素对于预防猝死至关重要，基于心电图的心律失常自动检测是心脏病筛查的重要手段，对降低心脏病死亡率至关重要。临床上同一患者可能同时出现多个心电异常类型，因此，解决心电图数据中多标签问题且考虑标签关系显得尤为重要。本文提出了一个多标签心电图分类模型，包括卷积神经网络、Transformer和注意力机制等模块，其中卷积神经网络用于提取局部特征，Transformer用于提取全局特征，采用非对称损失函数平衡正负标签。对两个心电数据集进行实验，实验结果表明，本文提出的模型相较于现有心电图分类方法，表现更优异。
Abstract: Cardiovascular disease is one of the leading causes of death worldwide. Early detection of risk factors for heart disease is essential to prevent sudden death. The automatic detection of arrhythmia based on electrocardiogram is an important means of heart disease screening, which is crucial to reduce the mortality of heart disease. In clinical settings, patients may exhibit multiple abnormal categories rather than just one. Therefore, it becomes necessary to address the issue of multiple labels in electrocardiogram data and consider the relationships between these labels. We propose a multi-label classification model composed of convolutional neural networks, Transformers and attention mechanisms. The convolutional neural network is used to extract local features, Transformer is used to extract global features, and an asymmetric loss function is used to balance positive and negative labels. Experimental results on two electrocardiogram dataset show that the proposed model has better performance than the existing electrocardiogram classification methods.
文章引用：张诗雨, 孙占全, 顾浩丞, 陈骏立. 基于注意力机制与卷积神经网络的不均衡多标签心电图分类方法研究[J]. 建模与仿真, 2024, 13(4): 4317-4334. https://doi.org/10.12677/mos.2024.134391

参考文献

[1] Mendis, S., Puska, P., Norrving, B., et al. (2011) Global Atlas on Cardiovascular Disease Prevention and Control. World Health Organization.
[2] Mehra, R. (2007) Global Public Health Problem of Sudden Cardiac Death. Journal of Electrocardiology, 40, S118-S122. [Google Scholar] [CrossRef] [PubMed]
[3] Hagiwara, Y., Fujita, H., Oh, S.L., Tan, J.H., Tan, R.S., Ciaccio, E.J., et al. (2018) Computer-Aided Diagnosis of Atrial Fibrillation Based on ECG Signals: A Review. Information Sciences, 467, 99-114. [Google Scholar] [CrossRef] 
[4] Übeyli, E.D. (2007) ECG Beats Classification Using Multiclass Support Vector Machines with Error Correcting Output Codes. Digital Signal Processing, 17, 675-684. [Google Scholar] [CrossRef] 
[5] Pan, J. and Tompkins, W.J. (1985) A Real-Time QRS Detection Algorithm. IEEE Transactions on Biomedical Engineering, 32, 230-236. [Google Scholar] [CrossRef] [PubMed]
[6] Jambukia, S.H., Dabhi, V.K. and Prajapati, H.B. (2015) Classification of ECG Signals Using Machine Learning Techniques: A Survey. 2015 International Conference on Advances in Computer Engineering and Applications, Ghaziabad, 19-20 March 2015, 714-721. [Google Scholar] [CrossRef] 
[7] Ge, R., Shen, T., Zhou, Y., Liu, C., Zhang, L., Yang, B., et al. (2021) Convolutional Squeeze-and-Excitation Network for ECG Arrhythmia Detection. Artificial Intelligence in Medicine, 121, Article ID: 102181. [Google Scholar] [CrossRef] [PubMed]
[8] Yao, Q., Fan, X., Cai, Y., Wang, R., Yin, L. and Li, Y. (2018) Time-Incremental Convolutional Neural Network for Arrhythmia Detection in Varied-Length Electrocardiogram. 2018 IEEE 16th Conference on Dependable, Autonomic and Secure Computing, 16th Conference on Pervasive Intelligence and Computing, 4th Conference on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech), Athens, 12-15 August 2018, 754-761. [Google Scholar] [CrossRef] 
[9] Yao, Q., Wang, R., Fan, X., Liu, J. and Li, Y. (2020) Multi-Class Arrhythmia Detection from 12-Lead Varied-Length ECG Using Attention-Based Time-Incremental Convolutional Neural Network. Information Fusion, 53, 174-182. [Google Scholar] [CrossRef] 
[10] Zhang, J., Liu, A., Gao, M., Chen, X., Zhang, X. and Chen, X. (2020) ECG-Based Multi-Class Arrhythmia Detection Using Spatio-Temporal Attention-Based Convolutional Recurrent Neural Network. Artificial Intelligence in Medicine, 106, Article ID: 101856. [Google Scholar] [CrossRef] [PubMed]
[11] He, R., Liu, Y., Wang, K., Zhao, N., Yuan, Y., Li, Q., et al. (2019) Automatic Cardiac Arrhythmia Classification Using Combination of Deep Residual Network and Bidirectional LSTM. IEEE Access, 7, 102119-102135. [Google Scholar] [CrossRef] 
[12] Liu, F., Liu, C., Zhao, L., Zhang, X., Wu, X., Xu, X., et al. (2018) An Open Access Database for Evaluating the Algorithms of Electrocardiogram Rhythm and Morphology Abnormality Detection. Journal of Medical Imaging and Health Informatics, 8, 1368-1373. [Google Scholar] [CrossRef] 
[13] Prabhakararao, E. and Dandapt, S. (2023) Multi-Label ECG Classification Using Temporal Convolutional Neural Network.
[14] Sheikh, D., Verma, H. and Chauhan, N. (2024) Reduced Lead ECG Multi-Label Classification with Higher Generalization Using 2D SEResnets with Self Attention. Multimedia Tools and Applications. [Google Scholar] [CrossRef] 
[15] Chen, T., Huang, C., Shih, E.S.C., Hu, Y. and Hwang, M. (2020) Detection and Classification of Cardiac Arrhythmias by a Challenge-Best Deep Learning Neural Network Model. iScience, 23, Article ID: 100886. [Google Scholar] [CrossRef] [PubMed]
[16] Woo, S., Park, J., Lee, J. and Kweon, I.S. (2018) CBAM: Convolutional Block Attention Module. In: Computer Vision—ECCV 2018, Springer, 3-19. [Google Scholar] [CrossRef] 
[17] Tseng, K.K., Lee, D. and Chen, C. (2016) ECG Identification System Using Neural Network with Global and Local Features. International Association for Development of the Information Society.
[18] He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[19] Ioffe, S. and Szegedy, C. (2015) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. International Conference on Machine Learning, Lille, 6-11 July 2015, 448-456.
[20] Nair, V. and Hinton, G.E. (2010) Rectified Linear Units Improve Restricted Boltzmann Machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), Omnipress, Haifa, 807-814.
[21] Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 6000-6010.
[22] Ridnik, T., Ben-Baruch, E., Zamir, N., Noy, A., Friedman, I., Protter, M., et al. (2021). Asymmetric Loss for Multi-Label Classification. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, 10-17 October 2021, 82-91.[CrossRef] 
[23] Wagner, P., Strodthoff, N., Bousseljot, R., Kreiseler, D., Lunze, F.I., Samek, W., et al. (2020) PTB-XL, a Large Publicly Available Electrocardiography Dataset. Scientific Data, 7, Article No. 154. [Google Scholar] [CrossRef] [PubMed]
[24] Da, K. (2014) A Method for Stochastic Optimization.
[25] Zhang, D., Yang, S., Yuan, X. and Zhang, P. (2021) Interpretable Deep Learning for Automatic Diagnosis of 12-Lead Electrocardiogram. iScience, 24, Article ID: 102373. [Google Scholar] [CrossRef] [PubMed]
[26] Jyotishi, D. and Dandapat, S. (2023) An Attentive Spatio-Temporal Learning-Based Network for Cardiovascular Disease Diagnosis. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 53, 4661-4671. [Google Scholar] [CrossRef] 
[27] Geng, Q., Liu, H., Gao, T., Liu, R., Chen, C., Zhu, Q., et al. (2023) An ECG Classification Method Based on Multi-Task Learning and Cot Attention Mechanism. Healthcare, 11, Article No. 1000. [Google Scholar] [CrossRef] [PubMed]
[28] Ge, Z., Jiang, X., Tong, Z., Feng, P., Zhou, B., Xu, M., et al. (2021) Multi-Label Correlation Guided Feature Fusion Network for Abnormal ECG Diagnosis. Knowledge-Based Systems, 233, Article ID: 107508. [Google Scholar] [CrossRef] 
[29] Śmigiel, S., Pałczyński, K. and Ledziński, D. (2021) ECG Signal Classification Using Deep Learning Techniques Based on the PTB-XL Dataset. Entropy, 23, Article No. 1121. [Google Scholar] [CrossRef] [PubMed]
[30] Śmigiel, S., Pałczyński, K. and Ledziński, D. (2021) Deep Learning Techniques in the Classification of ECG Signals Using R-Peak Detection Based on the PTB-XL Dataset. Sensors, 21, Article No. 8174. [Google Scholar] [CrossRef] [PubMed]
[31] Pałczyński, K., Śmigiel, S., Ledziński, D. and Bujnowski, S. (2022) Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset. Sensors, 22, Article No. 904. [Google Scholar] [CrossRef] [PubMed]
[32] Hou, Q., Zhou, D. and Feng, J. (2021). Coordinate Attention for Efficient Mobile Network Design. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 13708-13717.[CrossRef] 
[33] Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 7132-7141. [Google Scholar] [CrossRef] 
[34] Roy, A.G., Navab, N. and Wachinger, C. (2018) Concurrent Spatial and Channel “Squeeze & Excitation” in Fully Convolutional Networks. In: Medical Image Computing and Computer Assisted Intervention—MICCAI 2018, Springer International Publishing, 421-429. [Google Scholar] [CrossRef] 

为你推荐