استخراج سیگنال نوار قلبی خودکار دیجیتال
Abstract
۱٫ Introduction
۲٫ Methods
۳٫ Results and discussion
۴٫ Conclusions
Declaration of Competing Interest
Funding
Appendix. Supplementary materials
Research Data
References
Abstract
Background and objective Electrocardiogram (ECG) is one of the most important tools for assessing cardiac function and detecting potential heart problems. However, most of the current ECG report records remain on the paper, which makes it difficult to preserve and analyze the data. Moreover, paper records could result in the loss significant data, which brings inconvenience to the subsequent clinical diagnosis or artificial intelligence-assisted heart health diagnosis. Taking digital pictures is an intuitive way of preserving these files and can be done simply using smartphones or any other devices with cameras. However, these real scene ECG images often have some image noise that hinders signal extraction. How to eliminate image noise and extract ECG binary image automatically from the noisy and low-quality real scene images of ECG reports is the first problem to be solved in this paper. Next, QRS recognition is implemented on the extracted binary images to determine key points of ECG signals. 1D digital ECG signal is also extracted for accessing the exact values of the extracted points. In light of these tasks, an automatic digital ECG signal extraction and normal QRS recognition from real scene ECG images is proposed in this paper. Methods The normal QRS recognition approach for real scene ECG images in this paper consists of two steps: ECG binary image extraction from ECG images using a new two-layer hierarchical method, and the subsequent QRS recognition based on a novel feature-fusing method. ECG binary image extraction is implemented using sub-channel filters followed by an adaptive filtering algorithm. According to the ratio between pixel and real value of ECG binary image, 1D digital ECG signal is obtained. The normal QRS recognition includes three main steps: establishment of candidate point sets, feature fusion extraction, and QRS recognition. Two datasets are introduced for evaluation including a real scene ECG images dataset and the public Non-Invasive Fetal Electrocardiogram Database (FECG). Results Through the experiment on real scene ECG image, the F1 score for Q, R, S detection is 0.841, 0.992, and 0.891, respectively. The evaluation on the public FECG dataset also proves the robustness of our algorithm, where F1 score for R is 0.992 (0.996 for thoracic lead) and 0.988 for thoracic S wave. Conclusions The proposed method in this article is a promising tool for automatically extracting digital ECG signals and detecting QRS complex in real scene ECG images with normal QRS.
Introduction
According to the report of American Heart Association, 11.5% of American adults (27.6 million) were diagnosed with heart disease [1]. Electrocardiogram (ECG), a record of the electrical activity of the heart, is an important clinical tool for diagnosing cardiovascular diseases. An accurate and long-term ECG recording can not only help to evaluate the functional alterations of the heart or some other circulation related diseases, especially for the unhealthy population with cardiac problems or the pregnant population for fetal heart rate detection [2], [3], but also benefit medical research by providing precious clinical data. However, most ECG devices, including conventional 12-lead electrocardiograph and cardiotocograph that records fetal heartbeat still provide paper reports. Those digital and high-quality ECG signals are not always preserved in the machines. In fact, the ECG records in most cases are only available in printout clinical reports that are kept by individuals. This further hinders the popularization of Electronic Health Record (EHR) and poses problems for data management as these paper reports are not convenient for collecting, storing and analyzing. Moreover, deep learning methods have been utilized on ECG signal[4] , which requires a large amount of training data. For example, a recent study [5] by Andrew Y. Ng team, which collected 64,121 ECG records from 29,163 patients for arrhythmia classification. Therefore, a large number of printed ECG images need to be processed and extracted.