Detail publikačního výsledku

Cardiac Abnormalities Recognition in ECG Using a Convolutional Network with Attention and Input with an Adaptable Number of Leads

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

Original Title

Cardiac Abnormalities Recognition in ECG Using a Convolutional Network with Attention and Input with an Adaptable Number of Leads

English Title

Cardiac Abnormalities Recognition in ECG Using a Convolutional Network with Attention and Input with an Adaptable Number of Leads

Type

Paper in proceedings (conference paper)

Original Abstract

In this work, we present an algorithm for automatically identifying the cardiac abnormalities in ECG records with the various number of leads. The algorithm is based on the modified ResNet convolutional neural network with the attention layer. The network input is modified to allow using a single network for different lead subsets. In an official phase challenge entry, our BUTTeam reached the 15th place. In our test challenge entry, we have achieved 0.470, 0.460, 0.470, 0.460, and 0.460 of the challenge metric for 12, 6, 4, 3 and 2 leads with ranking 14th, 14th, 11th, 15th and 11th place, respectively. From additional evaluation of other lead subsets, the leads representing a common heart axis orientation achieved the best detection results. However, all lead subsets performed very similarly.

English abstract

In this work, we present an algorithm for automatically identifying the cardiac abnormalities in ECG records with the various number of leads. The algorithm is based on the modified ResNet convolutional neural network with the attention layer. The network input is modified to allow using a single network for different lead subsets. In an official phase challenge entry, our BUTTeam reached the 15th place. In our test challenge entry, we have achieved 0.470, 0.460, 0.470, 0.460, and 0.460 of the challenge metric for 12, 6, 4, 3 and 2 leads with ranking 14th, 14th, 11th, 15th and 11th place, respectively. From additional evaluation of other lead subsets, the leads representing a common heart axis orientation achieved the best detection results. However, all lead subsets performed very similarly.

Keywords

arrhythmias; cardiac abnormalities; convolutional neural network; attention layer; ResNet

Key words in English

arrhythmias; cardiac abnormalities; convolutional neural network; attention layer; ResNet

Authors

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

RIV year

2022

Released

18.11.2021

Publisher

Computing in Cardiology 2021

Location

Brno

Book

Computing in Cardiology 2021

ISBN

2325-887X

Periodical

Computing in Cardiology

State

United States of America

Pages from

1

Pages to

4

Pages count

4

URL

https://www.cinc.org/archives/2021/pdf/CinC2021-047.pdf

Full text in the Digital Library

http://hdl.handle.net/

BibTex

@inproceedings{BUT173258,
  author="Tomáš {Vičar} and Petra {Novotná} and Jakub {Hejč} and Oto {Janoušek} and Marina {Filipenská}",
  title="Cardiac Abnormalities Recognition in ECG Using a Convolutional Network with Attention and Input with an Adaptable Number of Leads",
  booktitle="Computing in Cardiology 2021",
  year="2021",
  journal="Computing in Cardiology",
  pages="1--4",
  publisher="Computing in Cardiology 2021",
  address="Brno",
  doi="10.22489/CinC.2021.047",
  issn="2325-887X",
  url="https://www.cinc.org/archives/2021/pdf/CinC2021-047.pdf"
}