Analysis of Fetal Heart Rate Signal based on Neighborhood-based Variance Compression Method

Cardiotocography (CTG) is a fetal monitoring technique and it constitutes two distinct simultaneously recorded biophysical signals which are fetal heart rate (FHR) and uterine contractions (UC). In clinical practice, CTG traces are interpreted visually by obstetricians and midwives, and such a visual examination leads to an increase in disagreement level among observers. Although existing of several guidelines to ensure more consistent interpretation, computerized CTG analysis is seen as the most promising way to tackle the disadvantages which CTG has. In this study, we deal with a neighborhood-based variance compression method on FHR signals. For this particular purpose, we employed the proposed compression algorithms on normal and hypoxic samples obtained from an open-access intrapartum CTG database. The diagnostic indices obtained from time, frequency and bi-spectral domains were taken into account in the experiment. Also, the differences in original and compressed signal were examined statistically. The experimental results point out that the proposed algorithm can be used successfully for FHR signal compression.