A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision

Abstract

Providing reliable detection of QRS complexes is key in automated analyses of electrocardiograms (ECG). Accurate and timely R-peak detections provide a basis for ECG-based diagnoses and to synchronize radiologic, electrophysiologic, or other medical devices. Compared with classical algorithms, deep learning (DL) architectures have demonstrated superior accuracy and high generalization capacity. Furthermore, they can be embedded on edge devices for real-time inference. 3D vectorcardiograms (VCG) provide a unifying framework for detecting R-peaks regardless of the acquisition strategy or number of ECG leads. In this article, a DL architecture was demonstrated to provide enhanced precision when trained and applied on 3D VCG, with no pre-processing nor post-processing steps. Experiments were conducted on four different public databases. Using the proposed approach, high F1-scores of 99.80% and 99.64% were achieved in leave-one-out cross-validation and cross-database validation protocols, respectively. False detections, measured by a precision of 99.88% or more, were significantly reduced compared with recent state-of-the-art methods tested on the same databases, without penalty in the number of missed peaks, measured by a recall of 99.39% or more. This approach can provide new applications for devices where precision, or positive predictive value, is essential, for instance cardiac magnetic resonance imaging.

A Generative Adversarial Network to Synthesize 3D Magnetohydrodynamic Distortions for Electrocardiogram Analyses Applied to Cardiac Magnetic Resonance Imaging

“…Evaluating the performance of augmented data when training a DL-based R-peak detector is another way to measure the adequacy of synthesized MHD-distorted ECG databases in real-world applications. The DL-based model used for this evaluation was described by Mehri et al [7], along with the metrics used to measure its accuracy: precision P (or positive predictive value), recall R (or sensitivity), and F1-score [5]. A tolerance of ±75 ms was set between the annotated R-peak locations and the detected locations when counting true positives (TPs), false positives (FPs), or false negatives (FNs).…”

“…In a strong magnetic field, MHD distortions, mostly caused by blood flowing through large vessels, induce elevated voltages in nearby conductors, which typically alter the shapes and amplitudes of T waves, as well as ECG baselines. An MHD-distorted ECG renders automated analyses unreliable, whether they are classical algorithms or DL architectures trained on non-distorted datasets [9]. Other distortions, caused by gradient switching and radiofrequency irradiation, are routinely removed by signal filtering and are out of the scope of the present work.…”

“…Since the 1980s, algorithms have steadily increased in performance [4,5]. Machine learning, and particularly deep learning (DL), models have proven their superiority over classical algorithms in ECG analyses [6,7]. DL typically requires vast amounts of labeled training data.…”