Deep-Learning Premature Contraction Localization in 12-lead ECG From Whole Signal Annotations

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F20%3APU137401" target="_blank" >RIV/00216305:26220/20:PU137401 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9344059" target="_blank" >https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9344059</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.22489/CinC.2020.193" target="_blank" >10.22489/CinC.2020.193</a>

Result language
angličtina
Original language name
Deep-Learning Premature Contraction Localization in 12-lead ECG From Whole Signal Annotations
Original language description
Since common electrocardiography (ECG) diagnostics approaches are time-consuming and arrhythmia-type sensitive, deep-learning methods are state-of-the-art for their detection accuracy. However, premature ventricular contractions' (PVC) localization via common deep-learning approaches requires large training set, therefore Multiple Instance Learning (MIL) framework was applied, where model is trained from whole-signal annotations. Proposed MIL framework is based on 1D Convolutional Neural Network (CNN), with global max-pooling in the last layer. The detection of PVCs' positions was done by the peak detector with specified parameters - threshold, minimal distance and peak prominence. Our method was tested on database containing 1590 ECGs, including 672 signals with PVCs. Dice coefficient reaches 0.947. This simple deep-learning method for the localization of PVC achieves a promising performance while being trainable from the whole-signal annotations instead of positional labels.
Czech name
—
Czech description
—

Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)