{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,9]],"date-time":"2026-11-09T23:42:41Z","timestamp":1794267761120,"version":"4.9.0"},"reference-count":30,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T00:00:00Z","timestamp":1737417600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Fetal electrocardiogram (FECG) signals directly reflect the electrical activity of the fetal heart, enabling the assessment of fetal cardiac health. To effectively separate and extract FECG signals from maternal abdominal electrocardiogram (ECG) signals, this study proposed a W-shaped parallel network, termed Attention R2W-Net, which consisted of two Attention R2U-Nets. In the encoder and decoder, recurrent residual modules were used to replace feedforward convolutional layers, significantly enhancing feature representation and improving noise suppression. Additionally, attention gates were used to replace skip connections, enabling precise correction of low-resolution features using deep features and further improving model performance. The decoders at both ends of the network were utilized to reconstruct FECG and MECG signals, respectively. The algorithm was validated using simulated and real datasets, achieving F1 scores of 99.17%, 98.03%, and 97.08% on the ADFECGDB, PCDB, and NIFECGDB datasets, respectively, demonstrating superior performance in both subjective visual effects and objective evaluation metrics. Attention R2W-Net\u2019s ability to extract robustly and accurately FECG signals, even in complex noisy environments, make it a reliable tool for FECG extraction. The proposed method\u2019s efficiency and accuracy highlight its potential for widespread clinical application, contributing to improved early diagnosis of fetal cardiac abnormalities.<\/jats:p>","DOI":"10.3390\/s25030601","type":"journal-article","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T05:47:42Z","timestamp":1737438462000},"page":"601","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Fetal ECG Signal Extraction from Maternal Abdominal ECG Signals Using Attention R2W-Net"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9333-4206","authenticated-orcid":false,"given":"Lin","family":"Chen","sequence":"first","affiliation":[{"name":"College of Chemistry and Life Sciences, Beijing University of Technology, Beijing 100124, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuicai","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Chemistry and Life Sciences, Beijing University of Technology, Beijing 100124, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0570-8473","authenticated-orcid":false,"given":"Zhuhuang","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Chemistry and Life Sciences, Beijing University of Technology, Beijing 100124, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2793","DOI":"10.1109\/TBME.2017.2675543","article-title":"Non-invasive Fetal ECG Signal Quality Assessment for Multichannel Heart Rate Estimation","volume":"64","author":"Andreotti","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"28608","DOI":"10.1109\/ACCESS.2021.3058733","article-title":"Non-Invasive Fetal Electrocardiogram Extraction Based on Novel Hybrid Method for Intrapartum ST Segment Analysis","volume":"9","author":"Martinek","year":"2021","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1088\/0967-3334\/35\/8\/1521","article-title":"Non-invasive fetal ECG analysis","volume":"35","author":"Clifford","year":"2014","journal-title":"Physiol. Meas."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"616","DOI":"10.2967\/jnumed.117.200170","article-title":"Optimizing Image Quantification for 177Lu SPECT\/CT Based on a 3D Printed 2-Compartment Kidney Phantom","volume":"59","author":"Lassmann","year":"2018","journal-title":"J. Nucl. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100133","DOI":"10.1016\/j.array.2022.100133","article-title":"Removal of multiple artifacts from ECG signal using cascaded multistage adaptive noise cancellers","volume":"14","author":"Faiz","year":"2022","journal-title":"Array"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Sarafan, S., Le, T., Lau, M.P.H., Hameed, A., Ghirmai, T., and Cao, H. (2022). Fetal Electrocardiogram Extraction from the Mother's Abdominal Signal Using the Ensemble Kalman Filter. Sensors, 22.","DOI":"10.3390\/s22072788"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mian Qaisar, S., Barnova, K., Martinek, R., Jaros, R., Kahankova, R., Matonia, A., Jezewski, M., Czabanski, R., Horoba, K., and Jezewski, J. (2021). A novel algorithm based on ensemble empirical mode decomposition for non-invasive fetal ECG extraction. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0256154"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1016\/j.procs.2020.08.060","article-title":"Blind Source Separation (BSS) of Mixed Maternal and Fetal Electrocardiogram (ECG) Signal: A comparative Study","volume":"176","author":"Ramli","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhao, J., and Wu, X. (2024). Comprehensive Separation Algorithm for Single-Channel Signals Based on Symplectic Geometry Mode Decomposition. Sensors, 24.","DOI":"10.3390\/s24020462"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Oyarz\u00fan, L., Castillo, E., Parrilla, L., and Garc\u00eda, A. (2021, January 24\u201326). Window Polarization in PCA-based Analysis of Non-Invasive Fetal ECG recordings. Proceedings of the 2021 XXXVI Conference on Design of Circuits and Integrated Systems (DCIS), Vila do Conde, Portugal.","DOI":"10.1109\/DCIS53048.2021.9666154"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Lee, J.S., Seo, M., Kim, S.W., and Choi, M. (2018, January 24\u201327). Fetal QRS Detection Based on Convolutional Neural Networks in Noninvasive Fetal Electrocardiogram. Proceedings of the 2018 4th International Conference on Frontiers of Signal Processing (ICFSP), Poitiers, France.","DOI":"10.1109\/ICFSP.2018.8552074"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Huang, K., Qiu, Y., Shen, H., and Ming, Z. (2021). Morphology extraction of fetal electrocardiogram by slow-fast LSTM network. Biomed. Signal Process. Control, 68.","DOI":"10.1016\/j.bspc.2021.102664"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Jimenez-Perez, G., Acosta, J., Bocanegra-P\u00e9rez, \u00c1.J., Arana-Rueda, E., Frutos-L\u00f3pez, M., S\u00e1nchez-Brotons, J.A., Llamas-L\u00f3pez, H., Di Massa Pezzutti, R., Gonz\u00e1lez de la Portilla Concha, C., and Camara, O. (2024). Delineation of intracavitary electrograms for the automatic quantification of decrement-evoked potentials in the coronary sinus with deep-learning techniques. Front. Physiol., 15.","DOI":"10.3389\/fphys.2024.1331852"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1109\/TBME.2022.3189617","article-title":"Fetal Electrocardiogram Extraction Using Dual-Path Source Separation of Single-Channel Non-Invasive Abdominal Recordings","volume":"70","author":"Shokouhmand","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"22908","DOI":"10.1109\/JSEN.2022.3213586","article-title":"A Dual Attention-Based Autoencoder Model for Fetal ECG Extraction From Abdominal Signals","volume":"22","author":"Ghonchi","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105011","DOI":"10.1088\/1361-6579\/ac2c5b","article-title":"Fetal ECG extraction using short time Fourier transform and generative adversarial networks","volume":"42","author":"Zhong","year":"2021","journal-title":"Physiol. Meas."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"121196","DOI":"10.1016\/j.eswa.2023.121196","article-title":"A novel deep learning technique for morphology preserved fetal ECG extraction from mother ECG using 1D-CycleGAN","volume":"235","author":"Basak","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"39782","DOI":"10.1109\/ACCESS.2022.3166925","article-title":"End-to-End Deep Learning Architecture for Separating Maternal and Fetal ECGs Using W-Net","volume":"10","author":"Lee","year":"2022","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/RBME.2019.2938061","article-title":"A Review of Signal Processing Techniques for Non-Invasive Fetal Electrocardiography","volume":"13","author":"Kahankova","year":"2020","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_20","first-page":"4","article-title":"A Review of Fetal ECG Signal Processing; Issues and Promising Directions","volume":"3","author":"Sameni","year":"2010","journal-title":"Open Pacing Electrophysiol. Ther. J."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1161\/01.CIR.81.2.730","article-title":"Recommendations for standardization and specifications in automated electrocardiography: Bandwidth and digital signal processing. A report for health professionals by an ad hoc writing group of the Committee on Electrocardiography and Cardiac Electrophysiology of the Council on Clinical Cardiology, American Heart Association","volume":"81","author":"Bailey","year":"1990","journal-title":"Circulation"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wei, C., Zhao, M., Liu, Q., and Wu, H. (2021, January 6\u201311). A Novel Convolutional Neural Network Model to Remove Muscle Artifacts from EEG. Proceedings of the ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9414228"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.neucom.2020.09.005","article-title":"DK-CNNs: Dynamic kernel convolutional neural networks","volume":"422","author":"Liu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Alom, M.Z., Yakopcic, C., Taha, T.M., and Asari, V.K. (2018, January 23\u201326). Nuclei Segmentation with Recurrent Residual Convolutional Neural Networks based U-Net (R2U-Net). Proceedings of the NAECON 2018\u2014IEEE National Aerospace and Electronics Conference, Dayton, OH, USA.","DOI":"10.1109\/NAECON.2018.8556686"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/TBME.2006.883728","article-title":"Extraction of Fetal Electrocardiogram Using Adaptive Neuro-Fuzzy Inference Systems","volume":"54","author":"Assaleh","year":"2007","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1007\/s13246-019-00805-x","article-title":"Fetal electrocardiography extraction with residual convolutional encoder-decoder networks","volume":"42","author":"Zhong","year":"2019","journal-title":"Australas. Phys. Eng. Sci. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2022.3216413","article-title":"PA\u00b2Net: Period-Aware Attention Network for Robust Fetal ECG Detection","volume":"71","author":"Wang","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1109\/JBHI.2021.3111873","article-title":"Fetal ECG Extraction From Maternal ECG Using Attention-Based CycleGAN","volume":"26","author":"Mohebbian","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"106414","DOI":"10.1016\/j.engappai.2023.106414","article-title":"Fetal ECG extraction from maternal ECG using deeply supervised LinkNet++ model","volume":"123","author":"Rahman","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3198","DOI":"10.1109\/JBHI.2023.3266645","article-title":"One-Dimensional W-NETR for Non-Invasive Single Channel Fetal ECG Extraction","volume":"27","author":"Almadani","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/3\/601\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:32:39Z","timestamp":1759919559000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/3\/601"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,21]]},"references-count":30,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["s25030601"],"URL":"https:\/\/doi.org\/10.3390\/s25030601","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,21]]}}}