165254 20251219174252.0 doi 10.1038/s41598-020-79512-7 sideral 146786 ART-2021-146786 eng Jimenez-Perez, Guillermo Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks 2021 Detection 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. Access copy available to the general public Unrestricted info:eu-repo/grantAgreement/ES/DGA-FEDER/T39-20R info:eu-repo/grantAgreement/ES/MINECO/MDM-2015-0502 info:eu-repo/semantics/openAccess by https://creativecommons.org/licenses/by/4.0/deed.es 4.997 2021 MULTIDISCIPLINARY SCIENCES 19 / 74 = 0.257 2021 Q2 T1 1.005 2021 Multidisciplinary 2021 Q1 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Alcaine, Alejandro (orcid)0000-0002-0166-2837 Camara, Oscar 11, 1 (2021), [11 pp.] Sci. rep. (Nat. Publ. Group) Scientific reports (Nature Publishing Group) 2045-2322 1971924 http://zaguan.unizar.es/record/165254/files/texto_completo.pdf Versión publicada 2421316 http://zaguan.unizar.es/record/165254/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:165254 articulos driver 2025-12-19-14:43:52 ARTICLE