Time-structure based reconstruction of physiological independent sources extracted from noisy abdominal phonograms

Jimenez-Gonzalez, Aida and James, C.J. (2010) Time-structure based reconstruction of physiological independent sources extracted from noisy abdominal phonograms. 8th Symposium of Mexican Students - Biological Sciences/Public Health Workshop, Manchester, United Kingdom.

Abstract

The abdominal phonogram is a signal recorded by a sensitive acoustic sensor positioned on the maternal womb. The signal conveys information which is valuable for foetal surveillance (e.g. heart sounds), but hidden by maternal and environmental noises. To recover such information, previous work successfully used single-channel independent component analysis (SCICA) to decompose the phonogram into independent components (ICs). After that, knowing that some ICs belong to the same process, similar ICs were grouped using K -means through similarities in their spectral content, a step that misclassified some foetal and maternal ICs and, consequently, distorted the recovered sources and made them virtually useless for studying foetal condition.

Here, as an alternative, the rich time-structure of the physiological components underlying the abdominal phonogram was exploited to automatically classify similar ICs, which made it suitable to retrieve the independent sources corresponding to maternal activity (respiration and cardiovascular), foetal heart sounds, and noise. To do so, a rhythmicity-based analysis scheme was proposed and tested on a dataset composed of 750 ICs extracted by SCICA from segments of 25 single-channel phonograms (recorded at foetal gestational ages between 29 and 40 weeks). Based on autocorrelation and PSD analysis, this scheme not only managed to quickly and automatically group similar ICs, but also correlated the recovered sources with specific physiological phenomena (either maternal or foetal), which is a desirable advantage. Further research will be conducted on more abdominal phonograms to explore alternatives for dimensional reduction and reconstruction of entire time-series that become suitable for surveillance, not only for foetal well-being but also for maternal condition.

This record has no associated files available for download.

Contributors

Download statistics