Extraction of QRS fiducial points from the ECG using adaptive mathematical morphology

• Published in: Digital signal processing 2016-09, Vol.56, p.100-109
• Main Authors: Yazdani, Sasan, Vesin, Jean-Marc
• Format: Article
• Language: English
• Subjects: Adaptive mathematical morphology; Arrhythmia; Devices; Error detection; Extraction; Mathematical morphology; Perturbation methods; QRS complex extraction; QRS fiducial point extraction; State of the art; Wearable ECG
• ISSN: 1051-2004; 1095-4333
• DOI: 10.1016/j.dsp.2016.06.010

QRS complex detection in the electrocardiogram (ECG) has been extensively investigated over the last two decades. Still, some issues remain pending due to the diversity of QRS complex shapes and various perturbations, notably baseline drift. This is especially true for ECG signals acquired using wearable devices. Our study aims at extracting QRS complexes and their fiducial points using Mathematical Morphology (MM) with an adaptive structuring element, on a beat-to-beat basis. The structuring element is updated based on the characteristics of the previously detected QRS complexes for a more robust and precise detection. The MIT-BIH arrhythmia and Physionet QT databases were respectively used for assessing the detection performance of R-waves and other fiducial points. Furthermore, the proposed method was evaluated on a wearable-device dataset of ECGs during vigorous exercises. Results show comparable or better performance than the state-of-the-art with a 99.87% sensitivity and 0.22% detection error rate for the MIT-BIH arrhythmia database. Efficient extraction of QRS fiducial points was achieved against the Physionet QT database. On the wearable-device dataset, an improvement of more than 10% in QRS complex detection rate compared to classic approaches was obtained. •Our study aims at extracting QRS complexes and their fiducial points using a mathematical morphology approach with an adaptive structuring element, on a beat-to-beat basis. The structuring element is updated based on the characteristics of the previously detected QRS complexes for a more precise detection.•The adaptive structuring element uses the shape of the QRS complex waveform not only to extract the R-peaks, but also to estimate the location of other fiducial points in the QRS complex, i.e. QRS-onset, QRS-offset, Q-point, and S-point.•A comprehensive study was performed and reported on parameter optimization.•The proposed method was evaluated on wearable recording technologies with a clear improvement in performance over classical approaches.•The proposed method is robust against perturbations such as baseline drift. It uses limited number of parameters while offering low computational cost which makes it a suitable choice for real-time/online scenarios such as body area networks.