{"title":"An Effective Integrated Framework for Fetal QRS Complex Detection Based on Abdominal ECG Signal","authors":"","doi":"10.1007/s40846-024-00850-2","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <span> <h3>Purpose</h3> <p>Non-invasive fetal electrocardiography (fECG) has a promising application prospect in offering crucial information for assessing early diagnosis and intervention of fetal distress and morbidity during pregnancy. Nevertheless, the detection and extraction of fetal ECG signals are still challenging since fetal ECG signals are exceedingly weak, and liability is affected by maternal ECG and other noises.</p> </span> <span> <h3>Methods</h3> <p>In this study, a comprehensive framework is developed for fECG signal extraction and fetal QRS complex location. A negative entropy-based blind source separation (BSS) method combined with a template subtraction (TS) method is exploited to obtain fECG signals from abdominal ECG (aECG) recordings. It effectively combines the arithmetic characteristics of fixed-point iteration and the effectiveness of template filtering, making the algorithm simple and fast to obtain clearer fetal ECG signals. Additionally, the combination of filter transformation and adaptive threshold algorithm is adopted for fetal QRS wave location. The filtering operation makes the fECG signal into single peaks. The design of low threshold and high threshold ensures that R waves can be located and detected more accurately.</p> </span> <span> <h3>Results</h3> <p>The performance results in terms of diagnostic sensitivity (Se), positive predictive value (PPV), accuracy (ACC), and harmonic mean (F1) scores are 96.12%, 96.20%, 92.60%, and 95.94% for the PCDB database, respectively, and 99.78%, 99.10%, 98.88%, and 99.44% for the ADFECGDB database. In addition, the results in terms of Se, PPV, ACC, and F1 scores are 99.46%, 97.89%, 97.37%, and 98.67% for the AECGDB database, respectively.</p> </span> <span> <h3>Conclusion</h3> <p>This study demonstrates that the proposed framework exhibits superior performance, which can improve the accuracy of fetal QRS complex detection.</p> </span>","PeriodicalId":50133,"journal":{"name":"Journal of Medical and Biological Engineering","volume":"35 1","pages":""},"PeriodicalIF":1.6000,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Medical and Biological Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s40846-024-00850-2","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose
Non-invasive fetal electrocardiography (fECG) has a promising application prospect in offering crucial information for assessing early diagnosis and intervention of fetal distress and morbidity during pregnancy. Nevertheless, the detection and extraction of fetal ECG signals are still challenging since fetal ECG signals are exceedingly weak, and liability is affected by maternal ECG and other noises.
Methods
In this study, a comprehensive framework is developed for fECG signal extraction and fetal QRS complex location. A negative entropy-based blind source separation (BSS) method combined with a template subtraction (TS) method is exploited to obtain fECG signals from abdominal ECG (aECG) recordings. It effectively combines the arithmetic characteristics of fixed-point iteration and the effectiveness of template filtering, making the algorithm simple and fast to obtain clearer fetal ECG signals. Additionally, the combination of filter transformation and adaptive threshold algorithm is adopted for fetal QRS wave location. The filtering operation makes the fECG signal into single peaks. The design of low threshold and high threshold ensures that R waves can be located and detected more accurately.
Results
The performance results in terms of diagnostic sensitivity (Se), positive predictive value (PPV), accuracy (ACC), and harmonic mean (F1) scores are 96.12%, 96.20%, 92.60%, and 95.94% for the PCDB database, respectively, and 99.78%, 99.10%, 98.88%, and 99.44% for the ADFECGDB database. In addition, the results in terms of Se, PPV, ACC, and F1 scores are 99.46%, 97.89%, 97.37%, and 98.67% for the AECGDB database, respectively.
Conclusion
This study demonstrates that the proposed framework exhibits superior performance, which can improve the accuracy of fetal QRS complex detection.
期刊介绍：
The purpose of Journal of Medical and Biological Engineering, JMBE, is committed to encouraging and providing the standard of biomedical engineering. The journal is devoted to publishing papers related to clinical engineering, biomedical signals, medical imaging, bio-informatics, tissue engineering, and so on. Other than the above articles, any contributions regarding hot issues and technological developments that help reach the purpose are also included.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
