Deep Learning Based QRS Multilead Delineator in Electrocardiogram Signals

Abstract

The surface electrocardiogram (ECG) is the most widely adopted test to diagnose cardiac diseases. Extracting critical biomarkers from these signals, such as the QRS width, requires delineating the fundamental waves in them. However, even though ECG signals significantly change depending on the recording methodology and cardiac condition, the available QRS delineators are hard to adapt to non-considered cases. We present a deep learning-based multilead ECG delineation method which can successfully delineate QRS complexes. Our approach reached root-mean-square errors (RMSE) of 12.1±0.5 and 18.5±1.1 ms for QRS onset and offset, respectively, when evaluated on the QT database; thus, demonstrating to be comparable to the state-of-the-art. Moreover, these results are similar to the RMSE calculated from differences between the two cardiologists that annotated this database, namely, 14.7 ms for the QRS onset and 17.2 ms for the offset.

U-Net Architecture for the Automatic Detection and Delineation of the Electrocardiogram

“…When compared to DL methods [9], our network outperforms or has comparable detection performance, except when using a tolerance window of 150ms. On the other hand, our delineation results are poorer than [8]. However, our network also provides delineations for the P and T waves.…”

“…Alternatively, machine learning techniques have been proposed [5][6][7]. However, these methods have been recently surpassed by deep learning (DL) techniques, using convolutional neural networks (CNN) [8,9] and long short-term memory [10]. Nonetheless, these methods employ non-optimal and outdated architectures for this task, especially given the state of the art results using modern pattern recognition architectures for semantic segmentation or image classification.…”

“…The average precision and recall are 93.68% and 94.59%, respectively. The error in the onset and offset locations were shown in Table 2, compared against [3,8]. Figure 2 shows detection examples.…”

Applications of Machine Learning

“…Techniques used in QRS complex detection range from signal derivative and digital filters [43,44,45,46,47], wavelet transforms [48,49,50,51,52], Hilbert transforms [53,54,55], matched filters [56,57], compressed sensing [58,59], to machine learning and neural networks (NN) approaches [60,61,62,63,64,65,66,67,68]. Among the many classical derivative and digital filter algorithms after the first Pan and Tompkins method [43], GQRS [47] is a simple one with superior performance by using adaptive search intervals and amplitude thresholds.…”

“…The CNN has the advantage of adapting to different types of QRS complexes, but it does not directly predict the timing information of R peaks. Paper [66] segments the QRS complexes by removing the regions outside of the QRS complexes using the first CNN. Then the second CNN finds the starts and ends of the QRS complexes.…”