Visual saliency detection approach for long-term ECG analysis

Sourav Kumar Mukhopadhyay; Sridhar Krishnan

doi:10.1016/j.cmpb.2021.106518

Visual saliency detection approach for long-term ECG analysis

Comput Methods Programs Biomed. 2022 Jan:213:106518. doi: 10.1016/j.cmpb.2021.106518. Epub 2021 Nov 11.

Authors

Sourav Kumar Mukhopadhyay¹, Sridhar Krishnan²

Affiliations

¹ Department of Electrical, Computer and Biomedical Engineering, Ryerson University, 350 Victoria Street, Toronto, Ontario M5B 2K3, Canada. Electronic address: sourav.mukhopadhyay@ryerson.ca.
² Department of Electrical, Computer and Biomedical Engineering, Ryerson University, 350 Victoria Street, Toronto, Ontario M5B 2K3, Canada. Electronic address: krishnan@ryerson.ca.

PMID: 34808531
DOI: 10.1016/j.cmpb.2021.106518

Abstract

Background and objective: Detection and analysis of QRS-complex as well as the processing of electrocardiogram (ECG) signal using computers are being practiced for over the last fifty-eight years, approximately, and yet the thirst of designing superior ECG processing and recognition algorithms still captures researchers' attention around the globe. A saliency detection-based technique for the processing of one-dimensional biomedical signals such as ECG is proposed here for the first time, to the best or our knowledge.

Methods and results: In this proposed research work, first, a trigonometric threshold-based technique is used to identify the QRS-complexes from the ECG signal. Motion-artifact (MA) and sudden-change-in-baseline (SCB) types of noises are considered to be the toughest among others to filter out from the ECG signals as the bandwidths of these two types of noises overlap with that of the ECG. Only one feature is extracted from each of the QRS-complex-intervals, and the normalised values of this feature are arranged in the form of a gray-scale image. Then, a saliency detection-based technique is applied iteratively on the gray-scale image to detect those regions of the ECG signals, which are highly corrupted with MA and (or) SCB noises. Next, three unique geometric-features are extracted from the rest of the QRS-complexes, which are not corrupted with MA or SCB noises, and the normalised values of these three features are arranged in the form of an Red-Green-Blue (RGB) image. Again, the saliency detection-based technique is applied to identify the abnormal QRS-complexes from the RGB image.

Conclusions: The technique is tested on long-term ECG signals; totaling a duration of 17.54 days, and its performance is evaluated through both quantitative and qualitative measures. The applicability, scope of implement in real-time scenarios, advantage of the proposed technique over the existing ones are discussed with a group of clinicians and cardiologists, and very affirmative and encouraging responses are received from them.

Keywords: Abnormal QRS-complex; Electrocardiogram; Histogram; Motion artifact; Saliency detection.

MeSH terms

Algorithms
Arrhythmias, Cardiac
Artifacts
Electrocardiography*
Humans
Signal Processing, Computer-Assisted*