{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:11:20Z","timestamp":1767204680463,"version":"build-2238731810"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:00:00Z","timestamp":1715040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002809","name":"Generalitat de Catalunya","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:p>Cardiac arrhythmias cause depolarization waves to conduct unevenly on the myocardial surface, potentially delaying local components with respect to a previous beat when stimulated at faster frequencies. Despite the diagnostic value of localizing the distinct local electrocardiogram (EGM) components for identifying regions with decrement-evoked potentials (DEEPs), current software solutions do not perform automatic signal quantification. Electrophysiologists must manually measure distances on the EGM signals to assess the existence of DEEPs during pacing or extra-stimuli protocols. In this work, we present a deep learning (DL)-based algorithm to identify decrement in atrial components (measured in the coronary sinus) with respect to their ventricular counterparts from EGM signals, for disambiguating between accessory pathways (APs) and atrioventricular re-entrant tachycardias (AVRTs). Several U-Net and W-Net neural networks with different configurations were trained on a private dataset of signals from the coronary sinus (312 EGM recordings from 77 patients who underwent AP or AVRT ablation). A second, separate dataset was annotated for clinical validation, with clinical labels associated to EGM fragments in which decremental conduction was elucidated. To alleviate data scarcity, a synthetic data augmentation method was developed for generating EGM recordings. Moreover, two novel loss functions were developed to minimize false negatives and delineation errors. Finally, the addition of self-attention mechanisms and their effect on model performance was explored. The best performing model was a W-Net model with 6 levels, optimized solely with the Dice loss. The model obtained precisions of 91.28%, 77.78% and of 100.0%, and recalls of 94.86%, 95.25% and 100.0% for localizing local field, far field activations, and extra-stimuli, respectively. The clinical validation model demonstrated good overall agreement with respect to the evaluation of decremental properties. When compared to the criteria of electrophysiologists, the automatic exclusion step reached a sensitivity of 87.06% and a specificity of 97.03%. Out of the non-excluded signals, a sensitivity of 96.77% and a specificity of 95.24% was obtained for classifying them into decremental and non-decremental potentials. Current results show great promise while being, to the best of our knowledge, the first tool in the literature allowing the delineation of all local components present in an EGM recording. This is of capital importance at advancing processing for cardiac electrophysiological procedures and reducing intervention times, as many diagnosis procedures are performed by comparing segments or late potentials in subsequent cardiac cycles.<\/jats:p>","DOI":"10.3389\/fphys.2024.1331852","type":"journal-article","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:33:52Z","timestamp":1715042032000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Delineation of intracavitary electrograms for the automatic quantification of decrement-evoked potentials in the coronary sinus with deep-learning techniques"],"prefix":"10.3389","volume":"15","author":[{"given":"Guillermo","family":"Jimenez-Perez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Acosta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u00c1lvaro J.","family":"Bocanegra-P\u00e9rez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo","family":"Arana-Rueda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Frutos-L\u00f3pez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan A.","family":"S\u00e1nchez-Brotons","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helena","family":"Llamas-G\u00f3mez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rodrigo","family":"Di Massa Pezzutti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carmen","family":"Gonz\u00e1lez de la Portilla Concha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oscar","family":"Camara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alonso","family":"Pedrote","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,5,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1093\/europace\/euw325","article-title":"Elucidation of hidden slow conduction by double ventricular extrastimuli: a method for further arrhythmic substrate identification in ventricular tachycardia ablation procedures","volume":"20","author":"Acosta","year":"2016","journal-title":"EP Eur."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1016\/j.hrthm.2020.05.017","article-title":"Long-term outcomes of ventricular tachycardia substrate ablation incorporating hidden slow conduction analysis","volume":"17","author":"Acosta","year":"2020","journal-title":"Heart rhythm."},{"key":"B3","first-page":"615","article-title":"Wavelet-based electrogram onset identification for ventricular electroanatomical mapping","volume-title":"Computing in cardiology 2013","author":"Alcaine","year":"2013"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2830","DOI":"10.1109\/TBME.2014.2330847","article-title":"A wavelet-based electrogram onset delineator for automatic ventricular activation mapping","volume":"61","author":"Alcaine","year":"2014","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B29","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"B5","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","volume-title":"Computer vision \u2013 eccv 2018","author":"Chen","year":"2018"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1109\/TBME.2002.805472","article-title":"A method for quantifying atrial fibrillation organization based on wave-morphology similarity","volume":"49","author":"Faes","year":"2002","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B7","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/CIC.2015.7408582","article-title":"Adaptive wavelets applied to automatic local activation wave detection in fractionated atrial electrograms of atrial fibrillation","volume-title":"2015 computing in cardiology conference (CinC)","author":"Felix","year":"2015"},{"key":"B8","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.artmed.2018.02.003","article-title":"Inflection point analysis: a machine learning approach for extraction of IEGM active intervals during atrial fibrillation","volume":"85","author":"Hajimolahoseini","year":"2018","journal-title":"Artif. Intell. Med."},{"key":"B9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"B10","volume-title":"Generalizing electrocardiogram delineation \u2013 training convolutional neural networks with synthetic data augmentation","author":"Jimenez-Perez","year":""},{"key":"B11","first-page":"1","article-title":"U-net architecture for the automatic detection and delineation of the electrocardiogram","volume-title":"CinC","author":"Jimenez-Perez","year":"2019"},{"key":"B12","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1038\/s41598-020-79512-7","article-title":"Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks","volume":"11","author":"Jimenez-Perez","year":"","journal-title":"Sci. Rep."},{"key":"B13","volume-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"B14","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B15","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"B16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.22489\/CinC.2017.202-031","article-title":"A fractionation-based local activation wave detector for atrial electrograms of atrial fibrillation","volume-title":"2017 computing in cardiology (CinC)","author":"Osorio","year":"2017"},{"key":"B30","first-page":"1095","article-title":"Causality-inspired single-source domain generalization for medical image segmentation","volume-title":"IEEE Trans. Med. Imaging","author":"Ouyang","year":"2023"},{"key":"B17","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.jacep.2017.12.005","article-title":"Multicenter study of ischemic ventricular tachycardia ablation with decrement-evoked potential (DEEP) mapping with extra stimulus","volume":"4","author":"Porta-S\u00e1nchez","year":"2018","journal-title":"JACC Clin. Electrophysiol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"8711","DOI":"10.1109\/jsen.2020.2984493","article-title":"Myocardial infarction severity stages classification from ECG signals using attentional recurrent neural network","volume":"20","author":"Prabhakararao","year":"2020","journal-title":"IEEE Sensors J."},{"key":"B19","doi-asserted-by":"publisher","first-page":"3217","DOI":"10.1016\/s0735-1097(21)04572-1","article-title":"Classification of individual atrial intracardiac electrograms by Deep Learning","volume":"77","author":"Rodrigo","year":"2021","journal-title":"J. Am. Coll. Cardiol."},{"key":"B20","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","volume-title":"Miccai","author":"Ronneberger","year":"2015"},{"key":"B21","first-page":"5998","article-title":"Attention is all you need","volume-title":"NIPS","author":"Vaswani","year":"2017"},{"key":"B22","first-page":"11534","article-title":"ECA-net: efficient channel attention for deep convolutional neural networks","volume-title":"Cvpr","author":"Wang","year":"2020"},{"key":"B23","volume-title":"W-net: a deep model for fully unsupervised image segmentation","author":"Xia","year":"2017"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1505.00853","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"Comput. Res. Repos. (CoRR)"},{"key":"B25","doi-asserted-by":"publisher","first-page":"80437","DOI":"10.1109\/access.2020.2984630","article-title":"Convolutional-neural-network-based approach for segmentation of apical four-chamber view from fetal echocardiography","volume":"8","author":"Xu","year":"2020","journal-title":"IEEE Access"},{"key":"B26","first-page":"665","article-title":"Dense-U-Net: densely connected convolutional network for semantic segmentation with a small number of samples","volume-title":"10th international conference on graphics and image processing, ICGIP 2018","author":"Zeng","year":"2019"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1794","DOI":"10.1016\/j.jacep.2020.06.032","article-title":"Automated functional substrate mapping: further hurdles to Be cleared","volume":"6","author":"Zeppenfeld","year":"2020","journal-title":"JACC Clin. Electrophysiol."},{"key":"B28","article-title":"Mixup: beyond empirical risk minimization","volume-title":"International conference on learning representations","author":"Zhang","year":"2018"}],"updated-by":[{"DOI":"10.3389\/fphys.2025.1726050","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000}}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2024.1331852\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T08:39:56Z","timestamp":1762763996000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2024.1331852\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,7]]},"references-count":30,"alternative-id":["10.3389\/fphys.2024.1331852"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2024.1331852","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,7]]},"article-number":"1331852"}}