Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks
Abstract 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 labori...
Guardado en:
Autores principales: | , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/3180f946800943f3a9609917b881d0e7 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:3180f946800943f3a9609917b881d0e7 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:3180f946800943f3a9609917b881d0e72021-12-02T15:23:02ZDelineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks10.1038/s41598-020-79512-72045-2322https://doaj.org/article/3180f946800943f3a9609917b881d0e72021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-79512-7https://doaj.org/toc/2045-2322Abstract 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.Guillermo Jimenez-PerezAlejandro AlcaineOscar CamaraNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Guillermo Jimenez-Perez Alejandro Alcaine Oscar Camara Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks |
description |
Abstract 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. |
format |
article |
author |
Guillermo Jimenez-Perez Alejandro Alcaine Oscar Camara |
author_facet |
Guillermo Jimenez-Perez Alejandro Alcaine Oscar Camara |
author_sort |
Guillermo Jimenez-Perez |
title |
Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks |
title_short |
Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks |
title_full |
Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks |
title_fullStr |
Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks |
title_full_unstemmed |
Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks |
title_sort |
delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/3180f946800943f3a9609917b881d0e7 |
work_keys_str_mv |
AT guillermojimenezperez delineationoftheelectrocardiogramwithamixedqualityannotationsdatasetusingconvolutionalneuralnetworks AT alejandroalcaine delineationoftheelectrocardiogramwithamixedqualityannotationsdatasetusingconvolutionalneuralnetworks AT oscarcamara delineationoftheelectrocardiogramwithamixedqualityannotationsdatasetusingconvolutionalneuralnetworks |
_version_ |
1718387315542327296 |