Publication detail

Multiple Instance Learning Framework Used For ECG Premature Contraction Localization

NOVOTNÁ, P.

Original Title

Multiple Instance Learning Framework Used For ECG Premature Contraction Localization

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

We propose the model combining convolutional neural network with multiple instance learning in order to localize the premature atrial contraction and premature ventricular contraction. The model is based on ResNet architecture modified for 1D signal processing. Model was trained on China Physiological Signal Challenge 2018 database extended by manually labeled ground truth positions of premature complexes. The presented method did not reach satisfying results in PAC localization (with dice = 0.127 for avg-pooling implementation). On the other hand, results of lo- calization of PVCs were comparable with other published studies (with dice = 0.952 for avg-pooling implementation).

Keywords

EEICT, ECG, PAC, PVC, CNN, MIL, arrhytmia, localization

Authors

NOVOTNÁ, P.

Released

3. 5. 2021

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií

Location

Brno

ISBN

978-80-214-5942-7

Book

Proceedings I of the 27th Conference STUDENT EEICT 2021

Edition

1

Edition number

1

Pages from

311

Pages to

315

Pages count

5

URL

https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2021_sbornik_1.pdf

BibTex

@inproceedings{BUT172365,
  author="Petra {Novotná}",
  title="Multiple Instance Learning Framework Used For ECG Premature Contraction Localization",
  booktitle="Proceedings I of the 27th Conference STUDENT EEICT 2021
",
  year="2021",
  series="1",
  number="1",
  pages="311--315",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  address="Brno",
  isbn="978-80-214-5942-7",
  url="https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2021_sbornik_1.pdf"
}