DocumentCode :
2075945
Title :
Combined method for fetal electrocardiogram extraction from noninvasive abdominal recordings
Author :
Ye-Lin, Y. ; Prats-Boluda, Gema ; Alberola-Rubio, J. ; Garcia-Casado, Javier
Author_Institution :
Grupo de Bioelectronica, Univ. Politec. de Valencia, Valencia, Spain
fYear :
2012
fDate :
Aug. 28 2012-Sept. 1 2012
Firstpage :
356
Lastpage :
359
Abstract :
Abdominal electrocardiogram (AECG) recording is a non-invasive method to assess fetal well-being during both pregnancy and delivery. However, AECG recording is contaminated by a series of physiological interferences which make difficult the extraction of morphological and temporal parameters of fetal ECG from the raw signals. In this work, it is proposed a combined method to extract the fetal ECG from AECG recording by removing the interferences on a cascade structure using a priori information about the signals nature. In this work, a total of 54 multichannel AECG recordings taken from 21 to 40 weeks of gestation were enrolled. Experimental results show that the proposed method outperforms conventional independent component analysis, and provides fetal heart rate detection in 80% of the cases. In addition it also permits to obtain fetal ECG morphology from AECG recordings.
Keywords :
cascade systems; electrocardiography; independent component analysis; medical signal detection; medical signal processing; obstetrics; abdominal electrocardiogram recording; cascade structure; conventional independent component analysis; fetal ECG morphology; fetal electrocardiogram extraction; fetal heart rate detection; gestation; morphological extraction; multichannel AECG recordings; noninvasive abdominal recordings; noninvasive method; physiological interferences; pregnancy; priori information; raw signals; temporal parameters; Algorithm design and analysis; Electrocardiography; Electrodes; Fetal heart rate; Independent component analysis; Interference; Pregnancy; Electrocardiography; Female; Fetus; Gestational Age; Humans; Pregnancy; Prenatal Diagnosis; Signal Processing, Computer-Assisted;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE
Conference_Location :
San Diego, CA
ISSN :
1557-170X
Print_ISBN :
978-1-4244-4119-8
Electronic_ISBN :
1557-170X
Type :
conf
DOI :
10.1109/EMBC.2012.6345942
Filename :
6345942
Link To Document :
بازگشت