An image classification method for arrhythmias based on Gramian angular summation field and improved Inception-ResNet-v2_Journal of Biomedical Engineering

Authors：

WAN Xiangkui ¹ , LUO Jing ¹ , LIU Yang ¹ ,  CHEN Yunfan ¹ , PENG Xingwei ² , WANG Xi ³

1. Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System, Hubei University of Technology, Wuhan 430068, P. R. China;
2. Wuhan Sichuang Electronics Co., Ltd., Wuhan 430074, P. R. China;
3. Department of Cardiology, Renmin Hospital of Wuhan University, Wuhan 430060, P. R. China;

Corresponding author：

CHEN Yunfan, Email: yfchen@hbut.com

Keywords：

Image classification of arrhythmias; Inception-ResNet-v2; Deep convolutional generative adversarial network; Gramian angular summation field

DOI：

10.7507/1001-5515.202207049

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Arrhythmia is a significant cardiovascular disease that poses a threat to human health, and its primary diagnosis relies on electrocardiogram (ECG). Implementing computer technology to achieve automatic classification of arrhythmia can effectively avoid human error, improve diagnostic efficiency, and reduce costs. However, most automatic arrhythmia classification algorithms focus on one-dimensional temporal signals, which lack robustness. Therefore, this study proposed an arrhythmia image classification method based on Gramian angular summation field (GASF) and an improved Inception-ResNet-v2 network. Firstly, the data was preprocessed using variational mode decomposition, and data augmentation was performed using a deep convolutional generative adversarial network. Then, GASF was used to transform one-dimensional ECG signals into two-dimensional images, and an improved Inception-ResNet-v2 network was utilized to implement the five arrhythmia classifications recommended by the AAMI (N, V, S, F, and Q). The experimental results on the MIT-BIH Arrhythmia Database showed that the proposed method achieved an overall classification accuracy of 99.52% and 95.48% under the intra-patient and inter-patient paradigms, respectively. The arrhythmia classification performance of the improved Inception-ResNet-v2 network in this study outperforms other methods, providing a new approach for deep learning-based automatic arrhythmia classification.

Citation： WAN Xiangkui, LUO Jing, LIU Yang, CHEN Yunfan, PENG Xingwei, WANG Xi. An image classification method for arrhythmias based on Gramian angular summation field and improved Inception-ResNet-v2. Journal of Biomedical Engineering, 2023, 40(3): 465-473. doi: 10.7507/1001-5515.202207049 Copy

1.	中国心血管健康与疾病报告编写组. 中国心血管健康与疾病报告2021概要. 心脑血管病防治, 2022, 22(4): 20-36, 40.
2.	Engin M. ECG beat classification using neuro-fuzzy network. Pattern Recogn Lett, 2004, 25(15): 1715-1722.
3.	Lv S Q, Wang Z P, Na J Y. Arrhythmia classification of merged features method based on SENet and BiLSTM// 2021 4th International Conference on Information Communication and Signal Processing (ICICSP). Paris: ICICSP, 2021: 162-167.
4.	Latif G, Anezi F Y A, Zikria M, et al. EEG-ECG signals classification for arrhythmia detection using decision trees// 2020 4th International Conference on Inventive Systems and Control (ICISC). Coimbatore: IEEE, 8: 192-196.
5.	Kung B H, Hu P Y, Huang C C, et al. An efficient ECG classification system using resource-saving architecture and random forest. IEEE J Biomed Health, 2021, 25(6): 1904-1914.
6.	Khatibi T, Rabinezhadsadatmahaleh N. Proposing feature engineering method based on deep learning and KNNs for ECG beat classification and arrhythmia detection. Phys Eng Sci Med, 2020, 43(1): 49-68.
7.	Yogesh D, Vedavathi D, Hiremath D S G. Implementation of five classes of automated ECG arrhythmia classification using KNN classifier. Int J Creat Res Thoughts, 2021, 9(2): 635-640.
8.	Liang W, Zhang Y L, Tan J D, et al. A novel approach to ECG classification based upon two-layered HMMs in body sensor networks. Sensors (basel), 2014, 14(4): 5994-6011.
9.	唐建军, 李兴秀, 华晶, 等. 基于神经网络的心电图检测分类综述. 计算机应用与软件, 2021, 38(5): 1-9, 41.
10.	Goodfellow I J, Bengio Y, Courville A C. Deep learning. Nature, 2015, 521: 436-444.
11.	Xia Y F, Xie Y Q. A novel wearable electrocardiogram classification system using convolutional neural networks and active learning. IEEE Access, 2019, 7: 7989-8001.
12.	Kiranyaz S, Ince T, Gabbouj M. Real-time patient-specific ECG classification by 1-d convolutional neural networks. IEEE T Biomed Eng, 2016, 63: 664-675.
13.	Obeidat Y M, Alqudah A M. A hybrid lightweight 1d CNN-LSTM architecture for automated ECG beat-wise classification. Trait Signal, 2021, 38: 1281-1291.
14.	骆俊锦, 王万良, 王铮, 等. 基于时序二维化和卷积特征融合的表面肌电信号分类方法. 模式识别与人工智能, 2020, 33(7): 588-599.
15.	Baspinar U, Şenyurek V Y, Doğan B, et al. A comparative study of denoising sEMG signals. Turk J Electr Eng Co, 2015, 23: 931-944.
16.	Sharma A, Singh P K, Chandra R. SMOTified-GAN for class imbalanced pattern classification problems. IEEE Access, 2022, 10: 30655-30665.
17.	Huang J S, Chen B G, Yao B, et al. ECG arrhythmia classification using STFT-based spectrogram and convolutional neural network. IEEE Access, 2019, 7: 92871-92880.
18.	Wang T, Lu C H, Sun Y N, et al. Automatic ECG classification using continuous wavelet transform and convolutional neural network. Entropy, 2021, 23(1): 119.
19.	Zyout A, Alquran H, Mustafa W A, et al. Advanced time-frequency methods for ECG waves recognition. Diagnostics, 2023, 13(2): 308.
20.	Moody G B, Mark R G. The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol, 2001, 20: 45-50.
21.	Bajaj A, Kumar S. A robust approach to denoise ECG signals based on fractional stockwell transform. Biomed Signal Proces, 2020, 62: 102090.
22.	Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE T Signal Proces, 2014, 62: 531-544.
23.	Kapfo A, Dandapat S, Bora P K. Automated detection of myocardial infarction from ECG signal using variational mode decomposition based analysis. Healthcare Technol Lett, 2020, 7: 155-160.
24.	Wang Y, Bai D Y. Application of wavelet threshold method based on optimized VMD to ECG denoising// 2021 IEEE 3rd International Conference on Frontiers Technology of Information and Computer (ICFTIC). Qingdao: ICFTIC, 2021: 741-744.
25.	Chawla N, Bowyer K, Hall L O, et al. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res, 2002, 16: 321-357.
26.	Shukla J, Panigrahi B K, Ray P K. Power quality disturbances classification based on gramian angular summation field method and convolutional neural networks. Int T Electr Energy, 2021, 31(12): e13222.1-e13222.16.
27.	Woo S, Park J, Lee J, et al. CBAM: convolutional block attention module// European Conference on Computer Vision (ECCV). Munich: ECCV, 2018: 3-19.
28.	Niu C M, Nan F Z, Wang X R. A super resolution frontal face generation model based on 3DDFA and CBAM. Displays, 2021, 69: 102043.
29.	Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning. Comput Sci, 2017: 11231.
30.	Sun L, Wang Y L, Qu Z G, et al. BeatClass: a sustainable ECG classification system in IoT-based eHealth. IEEE Internet Things, 2022, 9: 7178-7195.
31.	Wang H R, Shi H T, Chen X J, et al. An improved convolutional neural network based approach for automated heartbeat classification. J Med Syst, 2019, 44(2): 35.
32.	Sellami A, Hwang H. A robust deep convolutional neural network with batch-weighted loss for heartbeat classification. Expert Syst Appl, 2019, 122: 75-84.
33.	Huang H F, Liu J, Zhu Q, et al. A new hierarchical method for inter-patient heartbeat classification using random projections and RR Intervals. Biomed Eng Online, 2014, 13: 90.
34.	Garcia G, Moreira G J P, Menotti D, et al. Inter-patient ECG heartbeat classification with temporal VCG optimized by PSO. Sci Rep-UK, 2017, 7(1): 10543.

1. 中国心血管健康与疾病报告编写组. 中国心血管健康与疾病报告2021概要. 心脑血管病防治, 2022, 22(4): 20-36, 40.
2. Engin M. ECG beat classification using neuro-fuzzy network. Pattern Recogn Lett, 2004, 25(15): 1715-1722.
3. Lv S Q, Wang Z P, Na J Y. Arrhythmia classification of merged features method based on SENet and BiLSTM// 2021 4th International Conference on Information Communication and Signal Processing (ICICSP). Paris: ICICSP, 2021: 162-167.
4. Latif G, Anezi F Y A, Zikria M, et al. EEG-ECG signals classification for arrhythmia detection using decision trees// 2020 4th International Conference on Inventive Systems and Control (ICISC). Coimbatore: IEEE, 8: 192-196.
5. Kung B H, Hu P Y, Huang C C, et al. An efficient ECG classification system using resource-saving architecture and random forest. IEEE J Biomed Health, 2021, 25(6): 1904-1914.
6. Khatibi T, Rabinezhadsadatmahaleh N. Proposing feature engineering method based on deep learning and KNNs for ECG beat classification and arrhythmia detection. Phys Eng Sci Med, 2020, 43(1): 49-68.
7. Yogesh D, Vedavathi D, Hiremath D S G. Implementation of five classes of automated ECG arrhythmia classification using KNN classifier. Int J Creat Res Thoughts, 2021, 9(2): 635-640.
8. Liang W, Zhang Y L, Tan J D, et al. A novel approach to ECG classification based upon two-layered HMMs in body sensor networks. Sensors (basel), 2014, 14(4): 5994-6011.
9. 唐建军, 李兴秀, 华晶, 等. 基于神经网络的心电图检测分类综述. 计算机应用与软件, 2021, 38(5): 1-9, 41.
10. Goodfellow I J, Bengio Y, Courville A C. Deep learning. Nature, 2015, 521: 436-444.
11. Xia Y F, Xie Y Q. A novel wearable electrocardiogram classification system using convolutional neural networks and active learning. IEEE Access, 2019, 7: 7989-8001.
12. Kiranyaz S, Ince T, Gabbouj M. Real-time patient-specific ECG classification by 1-d convolutional neural networks. IEEE T Biomed Eng, 2016, 63: 664-675.
13. Obeidat Y M, Alqudah A M. A hybrid lightweight 1d CNN-LSTM architecture for automated ECG beat-wise classification. Trait Signal, 2021, 38: 1281-1291.
14. 骆俊锦, 王万良, 王铮, 等. 基于时序二维化和卷积特征融合的表面肌电信号分类方法. 模式识别与人工智能, 2020, 33(7): 588-599.
15. Baspinar U, Şenyurek V Y, Doğan B, et al. A comparative study of denoising sEMG signals. Turk J Electr Eng Co, 2015, 23: 931-944.
16. Sharma A, Singh P K, Chandra R. SMOTified-GAN for class imbalanced pattern classification problems. IEEE Access, 2022, 10: 30655-30665.
17. Huang J S, Chen B G, Yao B, et al. ECG arrhythmia classification using STFT-based spectrogram and convolutional neural network. IEEE Access, 2019, 7: 92871-92880.
18. Wang T, Lu C H, Sun Y N, et al. Automatic ECG classification using continuous wavelet transform and convolutional neural network. Entropy, 2021, 23(1): 119.
19. Zyout A, Alquran H, Mustafa W A, et al. Advanced time-frequency methods for ECG waves recognition. Diagnostics, 2023, 13(2): 308.
20. Moody G B, Mark R G. The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol, 2001, 20: 45-50.
21. Bajaj A, Kumar S. A robust approach to denoise ECG signals based on fractional stockwell transform. Biomed Signal Proces, 2020, 62: 102090.
22. Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE T Signal Proces, 2014, 62: 531-544.
23. Kapfo A, Dandapat S, Bora P K. Automated detection of myocardial infarction from ECG signal using variational mode decomposition based analysis. Healthcare Technol Lett, 2020, 7: 155-160.
24. Wang Y, Bai D Y. Application of wavelet threshold method based on optimized VMD to ECG denoising// 2021 IEEE 3rd International Conference on Frontiers Technology of Information and Computer (ICFTIC). Qingdao: ICFTIC, 2021: 741-744.
25. Chawla N, Bowyer K, Hall L O, et al. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res, 2002, 16: 321-357.
26. Shukla J, Panigrahi B K, Ray P K. Power quality disturbances classification based on gramian angular summation field method and convolutional neural networks. Int T Electr Energy, 2021, 31(12): e13222.1-e13222.16.
27. Woo S, Park J, Lee J, et al. CBAM: convolutional block attention module// European Conference on Computer Vision (ECCV). Munich: ECCV, 2018: 3-19.
28. Niu C M, Nan F Z, Wang X R. A super resolution frontal face generation model based on 3DDFA and CBAM. Displays, 2021, 69: 102043.
29. Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning. Comput Sci, 2017: 11231.
30. Sun L, Wang Y L, Qu Z G, et al. BeatClass: a sustainable ECG classification system in IoT-based eHealth. IEEE Internet Things, 2022, 9: 7178-7195.
31. Wang H R, Shi H T, Chen X J, et al. An improved convolutional neural network based approach for automated heartbeat classification. J Med Syst, 2019, 44(2): 35.
32. Sellami A, Hwang H. A robust deep convolutional neural network with batch-weighted loss for heartbeat classification. Expert Syst Appl, 2019, 122: 75-84.
33. Huang H F, Liu J, Zhu Q, et al. A new hierarchical method for inter-patient heartbeat classification using random projections and RR Intervals. Biomed Eng Online, 2014, 13: 90.
34. Garcia G, Moreira G J P, Menotti D, et al. Inter-patient ECG heartbeat classification with temporal VCG optimized by PSO. Sci Rep-UK, 2017, 7(1): 10543.

Journal of Biomedical Engineering

An image classification method for arrhythmias based on Gramian angular summation field and improved Inception-ResNet-v2

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content