Please use this identifier to cite or link to this item: https://repositorio.usj.es/handle/123456789/463

Full metadata record
DC FieldValueLanguage
dc.contributor.authorJiménez-Pérez, Guillermo-
dc.contributor.authorAlcaine Otín, Alejandro-
dc.contributor.authorCámara, Óscar-
dc.date.accessioned2021-02-11T13:25:45Z-
dc.date.available2021-02-11T13:25:45Z-
dc.date.issued2021-01-13-
dc.identifier.citationJimenez-Perez, G., Alcaine, A. & Camara, O. Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks. Sci Rep 11, 863 (2021). https://doi.org/10.1038/s41598-020-79512-7es_ES
dc.identifier.issn2045-2322es_ES
dc.identifier.urihttps://repositorio.usj.es/handle/123456789/463-
dc.description.abstractDetection and delineation are key steps for retrieving and structuring information of the electrocardiogram (ECG), being thus crucial for numerous tasks in clinical practice. Digital signal processing (DSP) algorithms are often considered state-of-the-art for this purpose but require laborious rule readaptation for adapting to unseen morphologies. This work explores the adaptation of the the U-Net, a deep learning (DL) network employed for image segmentation, to electrocardiographic data. The model was trained using PhysioNet’s QT database, a small dataset of 105 2-lead ambulatory recordings, while being independently tested for many architectural variations, comprising changes in the model’s capacity (depth, width) and inference strategy (single- and multi-lead) in a fivefold cross-validation manner. This work features several regularization techniques to alleviate data scarcity, such as semi-supervised pre-training with low-quality data labels, performing ECG-based data augmentation and applying in-built model regularizers. The best performing configuration reached precisions of 90.12%, 99.14% and 98.25% and recalls of 98.73%, 99.94% and 99.88% for the P, QRS and T waves, respectively, on par with DSP-based approaches. Despite being a data-hungry technique trained on a small dataset, a U-Net based approach demonstrates to be a viable alternative for this task.es_ES
dc.format.extent11 p.es_ES
dc.format.mimetypeapplication/pdfes_ES
dc.language.isoenges_ES
dc.publisherNature Researches_ES
dc.relationThis research was supported by the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia (2017 FI_B 01008), by the Gobierno de Aragón and FEDER 2014– 2020 (T39_20R) and by the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502). The GPU was donated by the NVIDIA Corporation.es_ES
dc.relation.requiresAdobe PDFes_ES
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectHeart Arrhythmiaes_ES
dc.subjectElectrocardiographes_ES
dc.subjectSupraventricular Premature Beates_ES
dc.titleDelineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networkses_ES
dc.typejournal articlees_ES
dc.subject.unescoInvestigaciónes_ES
dc.relation.publisherversionhttps://www.nature.com/articles/s41598-020-79512-7es_ES
dc.identifier.publicationfirstpage1es_ES
dc.identifier.publicationlastpage11es_ES
dc.identifier.doi10.1038/s41598-020-79512-7es_ES
dc.rights.accessRightsopen accesses_ES
Appears in Collections:Artículos de revistas

Files in This Item:
File Description SizeFormat 
Delineation of the electrocardiogram with a mixed-quality-annotations.pdf1,82 MBAdobe PDFThumbnail
View/Open


This item is licensed under a Creative Commons License Creative Commons