Skip to Main content Skip to Navigation

Analyse, caractérisation et classification de signaux foetaux

Abstract : This thesis is in the biomedical field, at the interface of the instrumentation and signal processing. The objective of this work is to assess the fetal parameters (fetal heart rate and fetal movements) and the fetal well-being for different stages of pregnancy using a mixture of fetal parameters. In our days, the parameters derived from heart rate and fetal movements that characterize the fetal distress are assessed by the physician and unified in the score of Manning. Two major disadvantages of Manning's score exist: a) the assessment of the score is time consuming; b) there are variations inter and intra operators leading to different interpretations of the patient's medical record. To overcome these disadvantages we assess the fetal well-being objectively, by computing an automatique/electronic score. To achieve this goal, we developed an ultrasonic multi-sensor unit with 12 sensors allowing to collect sixty (pairs) Doppler signals from the heart, lower and upper limbs. In this thesis our first contribution is based on the implementation of new algorithms for detecting fetal heart rate from one single channel and several multi-channel. Our second contribution concerns the implementation of two categories of parameters based on heart rate: a) the classes of "traditional" parameters used by obstetricians and also evaluated in the test of Manning (baseline, acceleration, deceleration) b) the class of the parameters used by cardiologists and characterize the complexity of a time series (entropy, approximated, sampled entropy, entropy multi-scale graph of recurrence, etc.). Our third contribution was to make significant changes to the algorithms of calculation of fetal movements and the resulting parameters as: the number of movements, the percentage of time spent in motion by a fetus, the duration of movement. Our fourth contribution was the joint analysis of fetal heart rate and fetal movements. This analysis leads to the identification of different behavioral states. Development or non-development of these states is an indicator of fetal neurological development. We propose to evaluate the parameters of movement for each behavioral state. Our final contribution concerns the implementation of different scores and classifications. The new directions concerning this work are to integrate the different electronic scores and the most discrminative parameters in a monitoring device which permit a home or a clinical monitoring.
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download
Contributor : Ménigot Sébastien <>
Submitted on : Thursday, November 21, 2013 - 10:11:20 AM
Last modification on : Wednesday, March 21, 2018 - 10:54:02 AM
Long-term archiving on: : Saturday, February 22, 2014 - 4:32:32 AM


  • HAL Id : tel-00907317, version 1



Iulian Voicu. Analyse, caractérisation et classification de signaux foetaux. Ingénierie biomédicale. Université François Rabelais - Tours, 2011. Français. ⟨NNT : 2011TOUR3302⟩. ⟨tel-00907317⟩



Record views


Files downloads