Self-Trained Model for ECG Complex Delineation

TL;DR

This paper presents a new ECG delineation dataset and a self-training approach that leverages unlabeled data to improve delineation accuracy, addressing limitations of dataset size and robustness in prior methods.

Contribution

The paper introduces a novel dataset for ECG delineation and a self-training method that enhances model performance by utilizing unlabeled ECG data.

Findings

The dataset is effective for training robust ECG delineation models.

Self-training improves the prediction quality of ECG delineation.

The approach leverages pseudolabeling to utilize unlabeled data effectively.

Abstract

Electrocardiogram (ECG) delineation plays a crucial role in assisting cardiologists with accurate diagnoses. Prior research studies have explored various methods, including the application of deep learning techniques, to achieve precise delineation. However, existing approaches face limitations primarily related to dataset size and robustness. In this paper, we introduce a dataset for ECG delineation and propose a novel self-trained method aimed at leveraging a vast amount of unlabeled ECG data. Our approach involves the pseudolabeling of unlabeled data using a neural network trained on our dataset. Subsequently, we train the model on the newly labeled samples to enhance the quality of delineation. We conduct experiments demonstrating that our dataset is a valuable resource for training robust models and that our proposed self-trained method improves the prediction quality of ECG delineation.