The Classification of Fetal ECG Arrhythmia by Using Fusion Method of CNN-Transformer
Abstract Early detection of fetal cardiac arrhythmia remains a challenging problem due to the complex and non-stationary nature of fetal electrocardiogram (fECG) signals. Traditional approaches often fail to effectively capture both morphological and temporal dependencies present in these signals. In this study, we propose a hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) and Transformer architecture for accurate classification of fetal arrhythmia using non-invasive fECG signals. The proposed model leverages CNN to extract spatial (morphological) features from ECG signal representations, while the Transformer utilizes a self-attention mechanism to capture long-range temporal dependencies in the signal. Short-Time Fourier Transform (STFT) is employed to convert ECG signals into time–frequency representations, enabling effective feature learning. Experiments are conducted on the publicly available Non-Invasive Fetal ECG Arrhythmia Database (NIFEADB), consisting of recordings from 26 subjects. To avoid data leakage, subject-wise data splitting is considered. The proposed hybrid model achieves a classification accuracy of 96.53 %, outperforming standalone CNN and Transformer models. The results demonstrate that combining spatial and temporal feature extraction significantly improves classification performance and provides a promising approach for early diagnosis of fetal cardiac abnormalities.
- Referencias
- Cómo citar
- Del mismo autor
- Métricas
Apsana, S., Suresh, M. G., & Aneesh, R. P. (2017). A novel algorithm for early detection of fetal arrhythmia using independent component analysis. In 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT) (pp. 1277–1283). IEEE. https://doi.org/10.1109/ICICICT1.2017.8342753
Behar, J. A., Bonnemains, L., Shulgin, V., Oster, J., Ostras, O., & Lakhno, I. (2019). Noninvasive fetal electrocardiography for the detection of fetal arrhythmias. Prenatal Diagnosis, 39(3), 178–187. https://doi.org/10.1002/pd.5412
Bravo-Valenzuela, N. J., Rocha, L. A., Machado Nardozza, L. M., & Araujo Júnior, E. (2018). Fetal cardiac arrhythmias: Current evidence. Annals of Pediatric Cardiology, 11(2), 148–163. https://doi.org/10.4103/APC.APC_134_17
Dai, W., Dai, C., Qu, S., Li, J., & Das, S. (2017). Very deep convolutional neural networks for raw waveforms. arXiv. https://arxiv.org/abs/1610.00087
Eke, A. C. (2019). Does evidence from randomized controlled trials support the use of cardiotocography in pregnant women instead of intermittent auscultation of fetal heart rate? Cochrane Clinical Answers. https://doi.org/10.1002/cca.2903
Fotiadou, E., & Vullings, R. (2020). Multi-channel fetal ECG denoising with deep convolutional neural networks. Frontiers in Pediatrics, 8, Article 508. https://doi.org/10.3389/fped.2020.00508
Ganguly, B., Das, A., Ghosal, A., Das, D., Chatterjee, D., Rakshit, D., & Das, E. (2020). A non-invasive approach for fetal arrhythmia detection and classification from ECG signals. In 2020 IEEE VLSI Device, Circuit and System Conference (VLSI-DCS) (pp. 84–88). IEEE. https://doi.org/10.1109/VLSIDCS47293.2020.917992
Graham, T. P. (2008). Hypoplastic left heart syndrome is heritable. Yearbook of Cardiology, 2008, 111–112. https://doi.org/10.1016/S0146-2806(08)70243-9
Greenwald, S. D., Patil, R. S., & Mark, R. G. (2002). Improved detection and classification of arrhythmias in noise-corrupted electrocardiograms using contextual information [Doctoral dissertation, Massachusetts Institute of Technology]. MIT DSpace. https://dspace.mit.edu
Hao, Z., Zhang, X., Gao, L., Li, J., Liu, J., & Lai, Z. (2024). A filter design method based on evolutionary learning for R-peak detection in portable ECG testing devices. Biomedical Signal Processing and Control, 88, Article 105649. https://doi.org/10.1016/j.bspc.2024.105649
Khandoker, A. H., Wahbah, M., Yoshida, C., Kimura, Y., & Kasahara, Y. (2020). Effect of anesthesia on fetal-maternal heart rate variability and coupling in pregnant mice and fetuses. In 2020 Computing in Cardiology (CinC) (pp. 1–4). https://doi.org/10.22489/CinC.2020.197
Kleyko, D., Osipov, E., & Wiklund, R. (2020). A comprehensive study of complexity and performance of automatic detection of atrial fibrillation: Classification of long ECG recordings based on the PhysioNet Computing in Cardiology Challenge 2017. Biomedical Physics & Engineering Express, 6(2), Article 025010. https://doi.org/10.1088/2057-1976/ab6e1e
Martis, R. J., Acharya, U. R., & Min, L. C. (2013). ECG beat classification using PCA, LDA, ICA and discrete wavelet transform. Biomedical Signal Processing and Control, 8(5), 437–448. https://doi.org/10.1016/j.bspc.2013.01.002
Meng, Q., Shao, H., Shi, N., Wang, G., & Lv, Y. (2023). Arrhythmia classification detection based on multiple electrocardiogram databases. PLoS ONE, 18(9), Article e0290995. https://doi.org/10.1371/journal.pone.0290995
Moody, G. B., & Mark, R. G. (2001). The impact of the MIT-BIH Arrhythmia Database. IEEE Engineering in Medicine and Biology Magazine, 20(3), 45–50. https://doi.org/10.1109/51.932724
Nakatani, S., Yamamoto, K., & Ohtsuki, T. (2022). Fetal arrhythmia detection based on deep learning using fetal ECG signals. In 2022 IEEE Global Communications Conference (GLOBECOM) (pp. 2266–2271). IEEE. https://doi.org/10.1109/GLOBECOM48099.2022.10001697
Niu, J., Tang, Y., Sun, Z., & Zhang, W. (2020). Inter-patient ECG classification with symbolic representations and multi-perspective convolutional neural networks. IEEE Journal of Biomedical and Health Informatics, 24(5), 1321–1332. https://doi.org/10.1109/JBHI.2019.2923323
Pan, J., & Tompkins, W. J. (1985). A real-time QRS detection algorithm. IEEE Transactions on Biomedical Engineering, BME-32(3), 230–236. https://doi.org/10.1109/TBME.1985.325532
Pradipta, G. A., Ayu, P. D. W., Liandana, M., & Hostiadi, D. P. (2025). Enhanced fetal arrhythmia classification by non-invasive ECG using cross-domain feature and spatial differences windows information. IEEE Access, 13, 6729–6749. https://doi.org/10.1109/ACCESS.2025.3526586
Rahman, S., Islam, M. R., & Siddiqee, A. M. (2019). Fetal arrhythmia detection using fetal ECG signal. In 2019 IEEE International Conference on Telecommunications and Photonics (ICTP). IEEE. https://doi.org/10.1109/ICTP48844.2019.9041789
Rahman, T., Al-Ruweidi, M. K. A. A., Sumon, M. S. I., Kamal, R. Y., Chowdhury, M. E. H., & Yalcin, H. C. (2023). Deep learning technique for congenital heart disease detection using stacking-based CNN-LSTM models from fetal echocardiogram: A pilot study. IEEE Access, 11, 110375–110390. https://doi.org/10.1109/ACCESS.2023.3316719
Rai, R. K., Singh, A., Srivastava, R., & Kumar, G. (2023). Fetal ECG arrhythmia detection based on DenseNet transfer learning. Frontiers in Biomedical Technologies, 10(4), 417–426. https://doi.org/10.18502/fbt.v10i4.13723
Shekhawat, D., Chaudhary, D., Kumar, A., Kalwar, A., Mishra, N., & Sharma, D. (2024). Binarized spiking neural network optimized with momentum search algorithm for fetal arrhythmia detection and classification from ECG signals. Biomedical Signal Processing and Control, 89, Article 105713. https://doi.org/10.1016/j.bspc.2024.105713
Singh, S., Pandey, S. K., Pawar, U., & Janghel, R. R. (2018). Classification of ECG arrhythmia using recurrent neural networks. Procedia Computer Science, 132, 1290–1297. https://doi.org/10.1016/j.procs.2018.05.020
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008.
Wahbah, M., Zitouni, M. S., Al Sakaji, R., Funamoto, K., Widatalla, N., Krishnan, A., Kimura, Y., & Khandoker, A. H. (2024). A deep learning framework for noninvasive fetal ECG signal extraction. Frontiers in Physiology, 15, Article 1329313. https://doi.org/10.3389/fphys.2024.1329313
Wang, S.-H., Govindaraj, V. V., Górriz, J. M., Zhang, X., & Zhang, Y.-D. (2021). COVID-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network. Information Fusion, 67, 208–229. https://doi.org/10.1016/j.inffus.2020.10.004
Zhao, L., Chen, L., Yang, T., Wang, T., Zhang, S., Chen, L., Ye, Z., Luo, L., & Qin, J. (2020). Birth prevalence of congenital heart disease in China, 1980-2019: A systematic review and meta-analysis of 617 studies. European Journal of Epidemiology, 35(7), 631–642. https://doi.org/10.1007/s10654-020-00653-0
Zhou, F., & Wang, J. (2024). Heartbeat classification method combining multi-branch convolutional neural networks and transformer. iScience, 27(3), Article 109307. https://doi.org/10.1016/j.isci.2024.109307
Zhou, W., & Gotman, J. (2004). Removal of EMG and ECG artifacts from EEG based on wavelet transform and ICA. Clinical Neurophysiology, 115(1), 95–100. https://doi.org/10.1016/S1388-2457(03)00341-0