Accurate segmentation of biomedical time-series, such as intracardiac electrograms, is vital for understanding physiological states and supporting clinical interventions. Traditional rule-based and feature engineering approaches often struggle with complex clinical patterns and noise. Recent deep learning advancements offer solutions, showing various benefits and drawbacks in segmentation tasks. This study evaluates five segmentation algorithms, from traditional rule-based methods to advanced deep learning models, using a unique clinical dataset of intracardiac signals from 100 patients. We compared a rule-based method, a support vector machine (SVM), fully convolutional semantic neural network (UNet), region proposal network (Faster R-CNN), and recurrent neural network for electrocardiographic signals (DENS-ECG). Notably, Faster R-CNN has never been applied to 1D signals segmentation before. Each model underwent Bayesian optimization to minimize hyperparameter bias. Results indicated that deep learning models outperformed traditional methods, with UNet achieving the highest segmentation score of 88.9 % (root mean square errors for onset and offset of 8.43 ms and 7.49 ms), closely followed by DENS-ECG at 87.8 %. Faster R-CNN and SVM showed moderate performance, while the rule-based method had the lowest accuracy (77.7 %). UNet and DENS-ECG excelled in capturing detailed features and handling noise, highlighting their potential for clinical application. Despite greater computational demands, their superior performance and diagnostic potential support further exploration in biomedical time-series analysis.

1st Department of Internal Medicine Cardioangiology St Anne's Hospital Masaryk University Pekarska 664 53 Brno 60200 Czech Republic

Children's Hospital Faculty Hospital Brno Cernopolni 9 Brno 61300 Czech Republic

Department of Biomedical Engineering Brno University of Technology Technicka 12 Brno 61600 Czech Republic

International Clinical Research Centre St Anna's Faculty Hospital Pekarska 53 Brno 60200 Czech Republic

Zobrazit více v PubMed

Ivaturi, P. et al. A comprehensive explanation framework for biomedical time series classification. IEEE Journal of Biomedical and Health Informatics25, 2398–2408. 10.1109/JBHI.2021.3060997 (2021). PubMed PMC

Alcaine, A. et al. A wavelet-based electrogram onset delineator for automatic ventricular activation mapping. IEEE Transactions on Biomedical Engineering61, 2830–2839. 10.1109/TBME.2014.2330847 (2014). PubMed

Martinez, J., Almeida, R., Olmos, S., Rocha, A. & Laguna, P. A wavelet-based ECG delineator: evaluation on standard databases. IEEE Transactions on Biomedical Engineering51, 570–581. 10.1109/TBME.2003.821031 (2004). PubMed

Peimankar, A. & Puthusserypady, S. DENS-ECG: A deep learning approach for ECG signal delineation. Expert Systems with Applications165, 113911. 10.1016/j.eswa.2020.113911 (2021).

Issa, Z. F., Miller, J. M. & Zipes, D. P. Clinical arrhythmology and electrophysiology: a companion to Braunwald’s heart disease (Elsevier, Philadelphia, PA, 2024), fourth edition edn. OCLC: 1381742307.

Kaiser, D. W. et al. The precise timing of tachycardia entrainment is determined by the postpacing interval, the tachycardia cycle length, and the pacing rate: Theoretical insights and practical applications. Heart Rhythm13, 695–703. 10.1016/j.hrthm.2015.11.032 (2016). PubMed PMC

Shenasa, M., Hindricks, G., Callans, D. J., Miller, J. M. & Josephson, M. E. Cardiac Mapping (Wiley, 2019), 1 edn.

Pascale, P. et al. Pattern and timing of the coronary sinus activation to guide rapid diagnosis of atrial tachycardia after atrial fibrillation ablation. Circulation: Arrhythmia and Electrophysiology6, 481–490. 10.1161/CIRCEP.113.000182 (2013). PubMed

Steven, D., Seiler, J., Roberts-Thomson, K. C., Inada, K. & Stevenson, W. G. Mapping of atrial tachycardias after catheter ablation for atrial fibrillation: Use of bi-atrial activation patterns to facilitate recognition of origin. Heart Rhythm7, 664–672. 10.1016/j.hrthm.2010.01.009 (2010). PubMed

Haïssaguerre, M. et al. Localized Sources Maintaining Atrial Fibrillation Organized by Prior Ablation. Circulation113, 616–625. 10.1161/CIRCULATIONAHA.105.546648 (2006). PubMed

Hongo, R. Catheter Ablation of Scar-mediated Ventricular Tachycardia: Are Substrate-based Approaches Replacing Mapping?. Journal of Innovations in Cardiac Rhythm Management10, 3707–3715. 10.19102/icrm.2019.100603 (2019). PubMed PMC

Fustes, O. J. H. et al. Somatosensory evoked potentials in clinical practice: a review. Arquivos de Neuro-Psiquiatria79, 824–831. 10.1590/0004-282x-anp-2020-0427 (2021). PubMed

Lantz, G. et al. Space-oriented segmentation and 3-dimensional source reconstruction of ictal EEG patterns. Clinical Neurophysiology112, 688–697. 10.1016/S1388-2457(01)00479-5 (2001). PubMed

Costa-Garcia, A., Itkonen, M., Yamasaki, H., Shibata-Alnajjar, F. & Shimoda, S. A Novel Approach to the Segmentation of sEMG Data Based on the Activation and Deactivation of Muscle Synergies During Movement. IEEE Robotics and Automation Letters3, 1972–1977. 10.1109/LRA.2018.2811506 (2018).

McKinnon, M. L., Hill, N. J., Carp, J. S., Dellenbach, B. & Thompson, A. K. Methods for automated delineation and assessment of EMG responses evoked by peripheral nerve stimulation in diagnostic and closed-loop therapeutic applications. Journal of Neural Engineering20, 046012. 10.1088/1741-2552/ace6fb (2023). PubMed PMC

Clayson, P. E., Baldwin, S. A. & Larson, M. J. ow does noise affect amplitude and latency measurement of event-related potentials (ERPs)? A methodological critique and simulation study. Psychophysiology50, 174–186. 10.1111/psyp.12001 (2013). PubMed

Paradeshi, K., Scholar, R. & Kolekar, P. D. U. Removal of EMG Artifacts from Multichannel EEG Signal Using Automatic Dynamic Segmentation and Adaptive Thresholding with Multilevel Decomposed Wavelets. IOSR Journal of Electrical and Electronics Engineering12, 30–35. 10.9790/1676-1203043035 (2017).

Cazzaniga, G. et al. Improving the Annotation Process in Computational Pathology: A Pilot Study with Manual and Semi-automated Approaches on Consumer and Medical Grade Devices. Journal of Imaging Informatics in Medicine[SPACE]10.1007/s10278-024-01248-x (2024). PubMed PMC

Tizhoosh, H. R. et al. Searching Images for Consensus. The American Journal of Pathology191, 1702–1708. 10.1016/j.ajpath.2021.01.015 (2021). PubMed

Khalifa, M. & Albadawy, M. AI in diagnostic imaging: Revolutionising accuracy and efficiency. Computer Methods and Programs in Biomedicine Update5, 100146. 10.1016/j.cmpbup.2024.100146 (2024).

Faust, O., Hagiwara, Y., Hong, T. J., Lih, O. S. & Acharya, U. R. Deep learning for healthcare applications based on physiological signals: A review. Computer Methods and Programs in Biomedicine161, 1–13. 10.1016/j.cmpb.2018.04.005 (2018). PubMed

Estes, N. M. EP News: Clinical. Heart Rhythm17, 1054. 10.1016/j.hrthm.2020.04.002 (2020).

El Haddad, M. et al. Algorithmic detection of the beginning and end of bipolar electrograms: Implications for novel methods to assess local activation time during atrial tachycardia. Biomedical Signal Processing and Control8, 981–991. 10.1016/j.bspc.2012.11.005 (2013).

Nothstein, M. et al. CVAR-Seg: An Automated Signal Segmentation Pipeline for Conduction Velocity and Amplitude Restitution. Frontiers in Physiology12, 673047. 10.3389/fphys.2021.673047 (2021). PubMed PMC

Sánchez, J. et al. Using Machine Learning to Characterize Atrial Fibrotic Substrate From Intracardiac Signals With a Hybrid in silico and in vivo Dataset. Frontiers in Physiology12, 699291. 10.3389/fphys.2021.699291 (2021). PubMed PMC

Ředina, R. et al. Arrhythmia Database with Annotated Intracardial Atrial Signals from Pediatric Patients Undergoing Catheter Ablation. 10.22489/CinC.2022.282 (2022).

Hejc, J., Redina, R., Kolarova, J. & Starek, Z. Epycon: A Single-Platform Python Package for Parsing and Converting Raw Electrophysiology Data into Open Formats. 10.22489/CinC.2023.315 (2023).

Wang, Z.-Y., Xiang, Z.-R., Zhi, J.-Y., Ding, T.-C. & Zou, R. A novel physiological signal denoising method coupled with multispectral adaptive wavelet denoising(MAWD) and unsupervised source counting algorithm(USCA). Journal of Engineering Research12, 175–189. 10.1016/j.jer.2023.07.016 (2024).

Hejč, J., Vítek, M., Ronzhina, M., Nováková, M. & Kolářová, J. A Wavelet-Based ECG Delineation Method: Adaptation to an Experimental Electrograms with Manifested Global Ischemia. Cardiovascular Engineering and Technology6, 364–375. 10.1007/s13239-015-0224-z (2015). PubMed

Daubechies, I. The wavelet transform, time-frequency localization and signal analysis. IEEE Transactions on Information Theory36, 961–1005. 10.1109/18.57199 (1990).

Lee, G., Gommers, R., Waselewski, F., Wohlfahrt, K. & O’Leary, A. PyWavelets: A Python package for wavelet analysis. Journal of Open Source Software4, 1237. 10.21105/joss.01237 (2019).

Ouali, M. A., Ghanai, M. & Chafaa, K. Upper envelope detection of ECG signals for baseline wander correction: a pilot study. TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES26, 803–816. 10.3906/elk-1705-165 (2018).

Benitez, D., Gaydecki, P., Zaidi, A. & Fitzpatrick, A. The use of the Hilbert transform in ECG signal analysis. Computers in Biology and Medicine31, 399–406. 10.1016/S0010-4825(01)00009-9 (2001). PubMed

Burges, C. J. A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery2, 121–167. 10.1023/A:1009715923555 (1998).

Nasiri, J. A., Naghibzadeh, M., Yazdi, H. S. & Naghibzadeh, B. ECG Arrhythmia Classification with Support Vector Machines and Genetic Algorithm. In 2009 Third UKSim European Symposium on Computer Modeling and Simulation, 187–192, 10.1109/EMS.2009.39 (IEEE, Athens, Greece, 2009).

Rabee, A. & Barhumi, I. ECG signal classification using support vector machine based on wavelet multiresolution analysis. In 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA), 1319–1323, 10.1109/ISSPA.2012.6310497 (IEEE, Montreal, QC, Canada, 2012).

Turnip, A., Ilham Rizqywan, M., Kusumandari, D. E., Turnip, M. & Sihombing, P. Classification of ECG signal with Support Vector Machine Method for Arrhythmia Detection. Journal of Physics: Conference Series970, 012012. 10.1088/1742-6596/970/1/012012 (2018).

Smisek, R. et al. Multi-stage SVM approach for cardiac arrhythmias detection in short single-lead ECG recorded by a wearable device. Physiological Measurement39, 094003. 10.1088/1361-6579/aad9e7 (2018). PubMed

LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature521, 436–444. 10.1038/nature14539 (2015). PubMed

Farabet, C., Couprie, C., Najman, L. & LeCun, Y. Learning Hierarchical Features for Scene Labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence35, 1915–1929. 10.1109/TPAMI.2012.231 (2013). PubMed

Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. Communications of the ACM60, 84–90. 10.1145/3065386 (2017).

Hinton, G. et al. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Magazine29, 82–97. 10.1109/MSP.2012.2205597 (2012).

Leung, M. K. K., Xiong, H. Y., Lee, L. J. & Frey, B. J. Deep learning of the tissue-regulated splicing code. Bioinformatics30, i121–i129. 10.1093/bioinformatics/btu277 (2014). PubMed PMC

Ma, J., Sheridan, R. P., Liaw, A., Dahl, G. E. & Svetnik, V. Deep Neural Nets as a Method for Quantitative Structure-Activity Relationships. Journal of Chemical Information and Modeling55, 263–274. 10.1021/ci500747n (2015). PubMed

Somani, S. et al. Deep learning and the electrocardiogram: review of the current state-of-the-art. EP Europace23, 1179–1191. 10.1093/europace/euaa377 (2021). PubMed PMC

Stracina, T., Ronzhina, M., Redina, R. & Novakova, M. Golden Standard or Obsolete Method? Review of ECG Applications in Clinical and Experimental Context. Frontiers in Physiology13, 867033. 10.3389/fphys.2022.867033 (2022). PubMed PMC

Hejc, J., Redina, R., Kolarova, J. & Starek, Z. Multi-channel delineation of intracardiac electrograms for arrhythmia substrate analysis using implicitly regularized convolutional neural network with wide receptive field. Biomedical Signal Processing and Control94, 106274. 10.1016/j.bspc.2024.106274 (2024).

Ren, S., He, K., Girshick, R. & Sun, J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2016). ArXiv:1506.01497 [cs]. PubMed

Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation, 10.48550/ARXIV.1505.04597 (2015). Version Number: 1.

Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K. & Yuille, A. L. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs, 10.48550/ARXIV.1606.00915 (2016). Version Number: 2. PubMed

Abraham, N. & Khan, N. M. A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation, 10.48550/ARXIV.1810.07842 (2018). Version Number: 1.

Han, S., Eom, H., Kim, J. & Park, C. Optimal DNN architecture search using Bayesian Optimization Hyperband for arrhythmia detection. In 2020 IEEE Wireless Power Transfer Conference (WPTC), 357–360, 10.1109/WPTC48563.2020.9295590 (IEEE, Seoul, Korea (South), 2020).

Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: A Next-generation Hyperparameter Optimization Framework, 10.48550/ARXIV.1907.10902 (2019). Version Number: 1.

Kwak, S. G. & Kim, J. H. Central limit theorem: the cornerstone of modern statistics. Korean Journal of Anesthesiology70, 144. 10.4097/kjae.2017.70.2.144 (2017). PubMed PMC

Callaert, H. & Janssen, P. The Berry-Esseen Theorem for U-Statistics. The Annals of Statistics6, 417–421 (1978).

Zhou, Y., Zhu, Y. & Wong, W. K. Statistical tests for homogeneity of variance for clinical trials and recommendations. Contemporary Clinical Trials Communications33, 101119. 10.1016/j.conctc.2023.101119 (2023). PubMed PMC

Dubé, B. et al. Automatic detection and classification of human epicardial atrial unipolar electrograms. Physiological Measurement30, 1303–1325. 10.1088/0967-3334/30/12/002 (2009). PubMed

Trigano, T. & Luengo, D. Intracardiac ECG pulse localization using overlapping block sparse reconstruction. Biomedical Signal Processing and Control79, 103921. 10.1016/j.bspc.2022.103921 (2023).

Gong, S. et al. Dilated FCN: Listening Longer to Hear Better, 10.48550/ARXIV.1907.11956 (2019). Version Number: 1.

Kim, K., Chalidabhongse, T. H., Harwood, D. & Davis, L. Real-time foreground-background segmentation using codebook model. Real-Time Imaging11, 172–185. 10.1016/j.rti.2004.12.004 (2005).

Parks, D. H. & Fels, S. S. Evaluation of Background Subtraction Algorithms with Post-Processing. In 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance, 192–199, 10.1109/AVSS.2008.19 (IEEE, Santa Fe, NM, USA, 2008).

Waheed, K., Weaver, K. & Salam, F. A robust algorithm for detecting speech segments using an entropic contrast. In The 2002 45th Midwest Symposium on Circuits and Systems, 2002. MWSCAS-2002., vol. 3, III–328–III–331, 10.1109/MWSCAS.2002.1187039 (IEEE, Tulsa, OK, USA, 2002).

Blanco-Velasco, M., Weng, B. & Barner, K. E. ECG signal denoising and baseline wander correction based on the empirical mode decomposition. Computers in Biology and Medicine38, 1–13. 10.1016/j.compbiomed.2007.06.003 (2008). PubMed

Martínez, M., Ródenas, J., Alcaraz, R. & Rieta, J. J. Study on the Alternatives to Reduce High-Frequency Noise from Invasive Recordings of Atrial Fibrillation. 10.22489/CinC.2017.111-048 (2017).

Alwosheel, A., Van Cranenburgh, S. & Chorus, C. G. Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis. Journal of Choice Modelling28, 167–182. 10.1016/j.jocm.2018.07.002 (2018).

Veshchezerova, D., Bars, C. & Seitz”, J. Cycle Length Estimation Using Accurate Adaptive Detection of Local Activations in Atrial Intracardiac Electrograms. 10.22489/CinC.2022.142 (2022).

Liao, S. et al. Deep learning classification of unipolar electrograms in human atrial fibrillation: application in focal source mapping. Frontiers in Physiology12, 704122. 10.3389/fphys.2021.704122 (2021). PubMed PMC

Rodrigo, M., Rogers, A. J., Ganesan, P., Alhusseini, M. & Narayan, S. M. Abstract 14742: Deep Learning of Intracardiac Electrograms in Atrial Arrhythmia. Circulation142, 10.1161/circ.142.suppl_3.14742 (2020).

Rodrigo, M. et al. Machine learning classifies intracardiac electrograms of atrial fibrillation from other arrhythmias. Journal of the American College of Cardiology77, 279. 10.1016/S0735-1097(21)01638-7 (2021).