Efficacy of Independent Component Analysis on Twin Fetal Signal Extraction from fMCG data

Abstract

Event Abstract Back to Event Efficacy of Independent Component Analysis on Twin Fetal Signal Extraction from fMCG data Nana Aba Mensah-Brown1*, Silvia Comani2 and Ronald Wakai1 1 University of Wisconsin , United States 2 University of Chieti, Italy We assess the overall performance of the FastICA algorithm on 13 sessions of normal and high-risk twins ranging from 20 weeks to 37 weeks’ gestation. The quality of the separated components was rated on: 1) percentage peak detection of QRS peaks 2) comparison of signal-to-noise ratio (SNR) of twin ICA datasets against SNR of raw match-filtered datasets 3) Magnitude of twin residue in each twin ICA dataset 4) Visual correlation of twin ICA datasets and raw datasets as a measure of distortion. 5) visibility of important cardiac cycle components such as QRS, p-wave and t-wave. The average peak detection for the twin datasets was 97.5±3.6%. The average SNR using ICA was 3.95±0.28 compared with the average SNR from the raw match-filtered data of 3.27±0.26. Twin residue averaged 67±4% before ICA and 45±3% after ICA, with an average noise:signal ratio of 29±2%. The average waveforms of the ICA and raw data, were aligned in time implying that the distortion in time was insignificant. However, the QRS phase distortion was largely noticeable in 8 of 26 subjects. Although the SNR of the ICA datasets was greater than that of the raw datasets, the amplitude of p-wave was significantly diminished in 8 of 26 studies. The fast ICA algorithm effectively separates twin datasets while enhancing the relative amplitude of the QRS complex, at times distorting its phase, and reducing the relative amplitude of the p and T waves. Conference: Biomag 2010 - 17th International Conference on Biomagnetism , Dubrovnik, Croatia, 28 Mar - 1 Apr, 2010. Presentation Type: Poster Presentation Topic: Fetal and neonatal biomagnetism Citation: Mensah-Brown N, Comani S and Wakai R (2010). Efficacy of Independent Component Analysis on Twin Fetal Signal Extraction from fMCG data. Front. Neurosci. Conference Abstract: Biomag 2010 - 17th International Conference on Biomagnetism . doi: 10.3389/conf.fnins.2010.06.00142 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 25 Mar 2010; Published Online: 25 Mar 2010. * Correspondence: Nana Aba Mensah-Brown, University of Wisconsin, Madison, United States, mensahbrown@wisc.edu Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Nana Aba Mensah-Brown Silvia Comani Ronald Wakai Google Nana Aba Mensah-Brown Silvia Comani Ronald Wakai Google Scholar Nana Aba Mensah-Brown Silvia Comani Ronald Wakai PubMed Nana Aba Mensah-Brown Silvia Comani Ronald Wakai Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.