2021 Computing in Cardiology (CinC) 2021
DOI: 10.23919/cinc53138.2021.9662787
|View full text |Cite
|
Sign up to set email alerts
|

Multi-Label Cardiac Abnormality Classification from Electrocardiogram Using Deep Convolutional Neural Networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
8
0
3

Year Published

2022
2022
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 11 publications
(11 citation statements)
references
References 7 publications
0
8
0
3
Order By: Relevance
“…An interesting choice to check would be building one model that always works on 12 input signals (12-leads) and zeroing signals for not used leads, as was proposed in Nejedly et al (2021). Also worth testing is using an additional hand-picked feature vector, as in (Nejedly et al 2021, Wickramasinghe andAthif 2021).…”
Section: Discussionmentioning
confidence: 99%
“…An interesting choice to check would be building one model that always works on 12 input signals (12-leads) and zeroing signals for not used leads, as was proposed in Nejedly et al (2021). Also worth testing is using an additional hand-picked feature vector, as in (Nejedly et al 2021, Wickramasinghe andAthif 2021).…”
Section: Discussionmentioning
confidence: 99%
“…These are the methods that are developed in a similar way to that of our proposed algorithm. The proposed algorithm is also compared with the Challenge's top entrants, who have developed their algorithm using end-to-end deep learning techniques (Han et al 2021, Nejedly et al 2021, Wickramasinghe and Athif 2021.…”
Section: Discussionmentioning
confidence: 99%
“…Similar to Challenge 2020, 90% of the participants of the 2021 PhysioNet Challenge employed deep neural networks. Given this, one of the top entrants to the Challenge employed two convolutional neural networks to perform the multi-label classification using the pre-processed ECG signals and fast Fourier transformed ECG signals as inputs (Wickramasinghe and Athif 2021). Similarly, the first rank entrant of the Challenge developed a method using ResNet deep neural network architecture for classification with a multi-head attention mechanism (Nejedly et al 2021).…”
Section: Introductionmentioning
confidence: 99%
“…Finally, we removed the signal segments beyond the first 15 s if they were available. Hence, we used short ECG segments and avoided big differences in the lasting time of the dataset samples, as previously done in Xiaoyu et al (2021), Wickramasinghe and Athif (2021), Aublin et al (2021).…”
Section: Signal Preprocessingmentioning
confidence: 99%