Deep_Discriminative_Domain_Generalization_with_Adversarial_Feature_Learning_for_Classifying_ECG_Signals.pdf (612.52 kB)
Download file

Deep discriminative domain generalization with adversarial feature learning for classifying ECG signals

Download (612.52 kB)
conference contribution
posted on 03.08.2022, 14:02 authored by Zuogang Shang, Zhibin Zhao, Hui FangHui Fang, Samuel Relton, Darcy Murphy, Zoe Hancox, Ruqiang Yan, David Wong
Introduction: The goal of the 2021 PhysioNet/CinC challenge is diagnosing cardiac abnormalities from electrocardiograms (ECGs) and evaluating the diagnostic potential of reduced-lead ECGs. We describe the whole model created by the team “AI Healthcare” for this goal.
Methods: ECGs were downsampled to 300 Hz and filtered by wavelet. Then ECGs we randomly clipped or zeropadded to 4,096 samples. To have a better representative learning ability, a modified ResNet with larger kernel sizes was used. Multi-source adversarial feature learning was used to learn domain-invariant and discriminative representations with a special gradient reversal layer (GRL). The performance with and without the domain generation methods was compared.
Results: We achieved a challenge score of 0.66, 0.64, 0.65, 0.65, 0.62 on the validation data. We ranked 8th, 7th, 6th, 6th, and 12th for 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead ECGs, respectively. Testing showed that domain generation improved metric scores on the unseen domain.
Conclusion: Generalized representations perform well for “unseen” data. It is a general method for other models to improve generalization performance by learning a domain-invariant feature representation.

History

School

  • Science

Department

  • Computer Science

Published in

2021 Computing in Cardiology (CinC)

Pages

1-4

Source

2021 Computing in Cardiology (CinC)

Publisher

IEEE

Version

AM (Accepted Manuscript)

Rights holder

© The Authors

Publisher statement

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Publication date

2022-01-10

Copyright date

2022

ISBN

978-1-6654-7916-5; 978-1-6654-6721-6

ISSN

2325-8861

eISSN

2325-887X

Language

en

Location

Brno, Czech Republic

Event dates

13th September 2021 - 15th September 2021

Depositor

Dr Hui Fang. Deposit date: 20 September 2021