Publication detail

ECG Abnormalities Recognition Using Convolutional Network With Global Skip Connections and Custom Loss Function

VIČAR, T. HEJČ, J. NOVOTNÁ, P. RONZHINA, M. JANOUŠEK, O.

Original Title

ECG Abnormalities Recognition Using Convolutional Network With Global Skip Connections and Custom Loss Function

Type

conference paper

Language

English

Original Abstract

The latest trends in clinical care and telemedicine suggest a demand for a reliable automated electrocardiogram (ECG) signal classification methods. In this paper, we present customized deep learning model for ECG classification as a part of the Physionet/CinC Challenge 2020. The method is based on modified ResNet type convolutional neural network and is capable to automatically recognize 24 cardiac abnormalities using 12-lead ECG. We have adopted several preprocessing and learning techniques including custom tailored loss function, dedicated classification layer and Bayesian threshold optimization which have major positive impact on the model performance. At the official phase of the Challenge, our team BUT-Team - reached a challenge validation score of 0.696, and the full test score of 0.202, placing us 21 out of 40 in the official ranking. This implies that our method performed well on data from the same source (reached first place with validation score), however, it has very poor generalization to data from different sources.

Keywords

ECG, arrhythmia, signal, classification, challenge, CinC 2020, Computing in Cardiology

Authors

VIČAR, T.; HEJČ, J.; NOVOTNÁ, P.; RONZHINA, M.; JANOUŠEK, O.

Released

30. 9. 2020

Publisher

IEEE

Location

NEW YORK

ISBN

978-1-7281-7382-5

Book

Computing in Cardiology 2020

Edition

47

Edition number

1

ISBN

2325-8861

Periodical

Compuing in Cardiology 2013

State

Kingdom of Spain

Pages from

1

Pages to

4

Pages count

4

URL

BibTex

@inproceedings{BUT165485,
  author="Tomáš {Vičar} and Jakub {Hejč} and Petra {Novotná} and Marina {Filipenská} and Oto {Janoušek}",
  title="ECG Abnormalities Recognition Using Convolutional Network With Global Skip Connections and Custom Loss Function",
  booktitle="Computing in Cardiology 2020",
  year="2020",
  series="47",
  journal="Compuing in Cardiology 2013",
  number="1",
  pages="1--4",
  publisher="IEEE",
  address="NEW YORK",
  doi="10.22489/CinC.2020.189",
  isbn="978-1-7281-7382-5",
  issn="2325-8861",
  url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9344393"
}