Fusing Transformer Model with Temporal Features for ECG Heartbeat Classification

Yan, Genshen; Shen, Liang; Zhang, Yanchun; Liu, Fan

doi:10.1109/bibm47256.2019.8983326

Cited by 68 publications

(55 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To our knowledge, this is the first study in which neural architectures are applied for S484 B. Petryshak et al / Robust deep learning pipeline for PVC beats localization segmentation of anomalous beats and IncpetionNet-like architecture is used for the ECG classification task. Our results are comparable to the state of the art approaches reported in the literature [40][41][42]. Also similar kinds of cross dataset experiments were reported by [44] for beats of ventricular origin resulting in sensitivity and precision metrics comparable to our results, i.e.…”

Section: Discussionsupporting

confidence: 91%

“…Table 5 demonstrates generalization capabilities of our model in case of cross-dataset evaluation. While such cross dataset evaluation is not directly com-parable with the result reported in the literature, the high F1 score of the order 0.85 and 0.95 is qualitatively comparable to other large scale experiments in the literature [40][41][42].…”

Section: Classificationsupporting

confidence: 81%

“…We have compared our model with two other architectures, which are widely used for arrhythmia classification. Our model shows excellent performance on both datasets comparable to results reported in the literature [40][41][42]. As all datasets are extremely imbalanced and they contain a minimum 10 times more normal bits than PVC beats, the class imbalance negatively affects the classification model's performance.…”

Section: Segmentationsupporting

confidence: 77%

See 2 more Smart Citations

Robust deep learning pipeline for PVC beats localization

Petryshak

Kachko

Maksymenko

et al. 2021

THC

View full text Add to dashboard Cite

BACKGROUND: Premature ventricular contraction (PVC) is among the most frequently occurring types of arrhythmias. Existing approaches for automated PVC identification suffer from a range of disadvantages related to hand-crafted features and benchmarking on datasets with a tiny sample of PVC beats. OBJECTIVE: The main objective is to address the drawbacks described above in the proposed framework, which takes a raw ECG signal as an input and localizes R peaks of the PVC beats. METHODS: Our method consists of two neural networks. First, an encoder-decoder architecture trained on PVC-rich dataset localizes the R peak of both Normal and anomalous heartbeats. Provided R peaks positions, our CardioIncNet model does the delineation of healthy versus PVC beats. RESULTS: We have performed an extensive evaluation of our pipeline with both single- and cross-dataset paradigms on three public datasets. Our approach results in over 0.99 and 0.979 F1-measure on both single- and cross-dataset paradigms for R peaks localization task and above 0.96 and 0.85 F1 score for the PVC beats classification task. CONCLUSIONS: We have shown a method that provides robust performance beyond the beats of Normal nature and clearly outperforms classical algorithms both in the case of a single and cross-dataset evaluation. We provide a Github1 repository for the reproduction of the results.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Classificationsupporting

confidence: 81%

Section: Segmentationsupporting

confidence: 77%

See 1 more Smart Citation

Robust deep learning pipeline for PVC beats localization

Petryshak

Kachko

Maksymenko

et al. 2021

THC

View full text Add to dashboard Cite

show abstract

“…Then, we can obtain a low-dimensional embedding representation for transformer learning by concatenating the DWT decomposed wavelets, reconstructed signal, the original ECG signal and its magnitude and phase angle. As this representation already contains the information from both time and frequency domain, there is no need to use other function as in [12] to add additional temporal information to the embedding result. The details of the LDE method is given as follows.…”

Section: Low-dimensional Denoising Embeddingmentioning

confidence: 99%

Low-Dimensional Denoising Embedding Transformer for ECG Classification

Guan

Wang

Feng³

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The transformer based model (e.g., FusingTF) has been employed recently for Electrocardiogram (ECG) signal classification. However, the high-dimensional embedding obtained via 1-D convolution and positional encoding can lead to the loss of the signal's own temporal information and a large amount of training parameters. In this paper, we propose a new method for ECG classification, called low-dimensional denoising embedding transformer (LDTF), which contains two components, i.e., low-dimensional denoising embedding (LDE) and transformer learning. In the LDE component, a low-dimensional representation of the signal is obtained in the time-frequency domain while preserving its own temporal information. And with the low-dimensional embedding, the transformer learning is then used to obtain a deeper and narrower structure with fewer training parameters than that of the FusingTF. Experiments conducted on the MIT-BIH dataset demonstrates the effectiveness and the superior performance of our proposed method, as compared with state-of-the-art methods.

show abstract

“…In the recent years, transformers have been used on time-series based tasks [4,5]. Regarding ECG classification, Yan et al [6] got good results on the MIT-BIH database, i.e. a per heartbeat classification task.…”

Section: Previous Workmentioning

confidence: 99%

Generative Pre-Trained Transformer for Cardiac Abnormality Detection

Gaudilliere¹,

Sigurthorsdottir²,

Aguet³

et al. 2021

Preprint

View full text Add to dashboard Cite

ECG heartbeat classification plays a vital role in diagnosis of cardiac arrhythmia. The goal of the Physionet/CinC 2021 challenge was to accurately classify clinical diagnosis based on 12, 6, 4, 3 or 2-lead ECG recordings in order to aid doctors in the diagnoses of different heart conditions. Transformers have had great success in the field of natural language processing in the past years. Our team, CinCSEM, proposes to draw the parallel between text and periodic time series signals by viewing the repeated period as "words" and the whole signal as a sequence of such words. In this way, the attention mechanisms of the transformers can be applied to periodic time series signals. In our implementation, we follow the Transformer Encoder architecture, which combines several encoder layers followed by a dense layer with linear or sigmoid activation for generative pre-training or classification, respectively. The use case presented here is multi-label classification of heartbeat abnormalities of ECG recordings shared by the challenge. Our best entry, not exceeding the challenge's hardware limitations, achieved a score of 0.12, 0.07, 0.10, 0.10 and 0.07 on 12lead, 6-lead, 4-lead, 3-lead and 2-lead test set respectively. Unfortunately, our team was unable to be ranked because of a missing pre-print.

show abstract

Fusing Transformer Model with Temporal Features for ECG Heartbeat Classification

Cited by 68 publications

References 20 publications

Robust deep learning pipeline for PVC beats localization

Robust deep learning pipeline for PVC beats localization

Low-Dimensional Denoising Embedding Transformer for ECG Classification

Generative Pre-Trained Transformer for Cardiac Abnormality Detection

Contact Info

Product

Resources

About