SEResUTer: a deep learning approach for accurate ECG signal delineation and atrial fibrillation detection

Objective.Accurate detection of electrocardiogram (ECG) waveforms is crucial for computer-aided diagnosis of cardiac abnormalities. This study introduces SEResUTer, an enhanced deep learning model designed for ECG delineation and atrial fibrillation (AF) detection.Approach. Built upon a U-Net architecture, SEResUTer incorporates ResNet modules and Transformer encoders to replace convolution blocks, resulting in improved optimization and encoding capabilities. A novel masking strategy is proposed to handle incomplete expert annotations. The model is trained on the QT database (QTDB) and evaluated on the Lobachevsky University Electrocardiography Database (LUDB) to assess its generalization performance. Additionally, the model's scope is extended to AF detection using the the China Physiological Signal Challenge 2021 (CPSC2021) and the China Physiological Signal Challenge 2018 (CPSC2018) datasets.Main results.The proposed model surpasses existing traditional and deep learning approaches in ECG waveform delineation on the QTDB. It achieves remarkable average F1 scores of 99.14%, 98.48%, and 98.46% for P wave, QRS wave, and T wave delineation, respectively. Moreover, the model demonstrates exceptional generalization ability on the LUDB, achieving average SE, positive prediction rate, and F1 scores of 99.05%, 94.59%, and 94.62%, respectively. By analyzing RR interval differences and the existence of P waves, our method achieves AF identification with 99.20% accuracy on the CPSC2021 test set and demonstrates strong generalization on CPSC2018 dataset.Significance.The proposed approach enables highly accurate ECG waveform delineation and AF detection, facilitating automated analysis of large-scale ECG recordings and improving the diagnosis of cardiac abnormalities.

ECG_SegNet: An ECG delineation model based on the encoder-decoder structure

With the increasing usage of wearable electrocardiogram (ECG) monitoring devices, it is necessary to develop models and algorithms that can analyze the large amounts of ECG data obtained in real-time. Accurate ECG delineation is key to assisting cardiologists in diagnosing cardiac diseases. The main objective of this study is to design a delineation model based on the encoder-decoder structure to detect different heartbeat waveforms, including P-waves, QRS complexes, T-waves, and No waves (NW), as well as the onset and offset of these waveforms. First, the introduction of a standard dilated convolution module (SDCM) into the encoder path enabled the model to extract more useful ECG signal-informative features. Subsequently, bidirectional long short-term memory (BiLSTM) was added to the encoding structure to obtain numerous temporal features. Moreover, the feature sets of the ECG signals at each level in the encoder path were connected to the decoder part for multi-scale decoding to mitigate the information loss caused by the pooling operation in the encoding process. Finally, the proposed model was trained and tested on both QT and LU databases, and it achieved accurate results compared to other state-of-the-art methods. Regarding the QT database, the average accuracy of ECG waveform classification was 96.90%, and an average classification accuracy of 95.40% was obtained on the LU database. In addition, average F1 values of 99.58% and 97.05% were achieved in the ECG delineation task of the QT and LU databases, respectively. The results show that the proposed ECG_SegNet model has good flexibility and reliability when applied to ECG delineation, and it is a reliable method for analyzing ECG signals in real-time.

A Wavelet-Based ECG Delineation Method: Adaptation to an Experimental Electrograms with Manifested Global Ischemia

We present a novel wavelet-based ECG delineation method with robust classification of P wave and T wave. The work is aimed on an adaptation of the method to long-term experimental electrograms (EGs) measured on isolated rabbit heart and to evaluate the effect of global ischemia in experimental EGs on delineation performance. The algorithm was tested on a set of 263 rabbit EGs with established reference points and on human signals using standard Common Standards for Quantitative Electrocardiography Standard Database (CSEDB). On CSEDB, standard deviation (SD) of measured errors satisfies given criterions in each point and the results are comparable to other published works. In rabbit signals, our QRS detector reached sensitivity of 99.87% and positive predictivity of 99.89% despite an overlay of spectral components of QRS complex, P wave and power line noise. The algorithm shows great performance in suppressing J-point elevation and reached low overall error in both, QRS onset (SD = 2.8 ms) and QRS offset (SD = 4.3 ms) delineation. T wave offset is detected with acceptable error (SD = 12.9 ms) and sensitivity nearly 99%. Variance of the errors during global ischemia remains relatively stable, however more failures in detection of T wave and P wave occur. Due to differences in spectral and timing characteristics parameters of rabbit based algorithm have to be highly adaptable and set more precisely than in human ECG signals to reach acceptable performance.

A novel method to capture the onset of dynamic electrocardiographic ischemic changes and its implications to arrhythmia susceptibility

Background

This study investigates the hypothesis that morphologic analysis of intracardiac electrograms provides a sensitive approach to detect acute myocardial infarction or myocardial infarction‐induced arrhythmia susceptibility. Large proportions of irreversible myocardial injury and fatal ventricular tachyarrhythmias occur in the first hour after coronary occlusion; therefore, early detection of acute myocardial infarction may improve clinical outcomes.

Methods and Results

We developed a method that uses the wavelet transform to delineate electrocardiographic signals, and we have devised an index to quantify the ischemia‐induced changes in these signals. We recorded body‐surface and intracardiac electrograms at baseline and following myocardial infarction in 24 swine. Statistically significant ischemia‐induced changes after the initiation of occlusion compared with baseline were detectable within 30 seconds in intracardiac left ventricle (P<0.0016) and right ventricle–coronary sinus (P<0.0011) leads, 60 seconds in coronary sinus leads (P<0.0002), 90 seconds in right ventricle leads (P<0.0020), and 360 seconds in body‐surface electrocardiographic signals (P<0.0022). Intracardiac leads exhibited a higher probability of detecting ischemia‐induced changes than body‐surface leads (P<0.0381), and the right ventricle–coronary sinus configuration provided the highest sensitivity (96%). The 24‐hour ECG recordings showed that the ischemic index is statistically significantly increased compared with baseline in lead I, aVR, and all precordial leads (P<0.0388). Finally, we showed that the ischemic index in intracardiac electrograms is significantly increased preceding ventricular tachyarrhythmic events (P<0.0360).

Conclusions

We present a novel method that is capable of detecting ischemia‐induced changes in intracardiac electrograms as early as 30 seconds following myocardial infarction or as early as 12 minutes preceding tachyarrhythmic events.