Scattering Transform for Intrapartum Fetal Heart Rate Variability Fractal Analysis: A Case-Control Study

Abstract

Abstract-Intrapartum fetal heart rate monitoring, aiming at early acidosis detection, constitutes an important public health stake. Scattering Transform is proposed here as a new tool to analyze intrapartum fetal heart rate variability. It consists of a non linear extension of the underlying Wavelet Transform, that thus preserves its multiscale nature. Applied to a Fetal Heart Rate (FHR) signal database constructed in a French academic hospital, the Scattering Transform is shown to permit to efficiently measure scaling exponents characterizing the fractal properties of intrapartum fetal heart rate temporal dynamics, that relate not only to the sole covariance (correlation scaling exponent) but also to the full dependence structure of data (intermittency scaling exponent). Such exponents are found to satisfactorily discriminate temporal dynamics of Healthy subjects (from that of Non Healthy ones) and to emphasize the role of the highest frequencies (around and above 1Hz) in intrapartum fetal heart rate variability. This permits to achieve satisfactory classification performance, that improves on those obtained from the analysis of International Federation of Gynecology and Obstetrics (FIGO) criteria, notably by classifying as Healthy a number of subjects that were incorrectly classified as Non Healthy by classical clinically-used FIGO criteria. Combined to obstetrician annotations, these scaling exponents enables us to sketch a typology of these FIGO-False Positive subjects. Also, they permit to monitor the evolution along time of the intrapartum health status of the fetuses and to estimate an optimal detection time-frame.

Mutual information for intrapartum fetal heart rate analysis

“…Aiming to explore temporal dynamics beyond the mere temporal correlations, several variations of nonlinear analysis have been envisaged (cf. e.g., [5], [4], [6]). More recently the concepts of fractal [7], [8] and multifractal [9] have also been showing promising performance in fetal acidosis detection.…”

Intermittent process analysis with scattering moments

“…The scattering norm (6) can be approximated with a summation restricted to moments of order m = 1, 2, because higher order scattering moments usually have a much smaller energy [2,9]. First-and second-order scattering moments applied to image and audio textures as well as intrapartum electrocardiograms for fetal monitoring provide state of the art classification errors [2,9,13,35], but these results are strictly numerical. These algorithms are implemented with deep convolutional neural network structures [24].…”

Relevance-based quantization of scattering features for unsupervised mining of environmental audio

“…Originally developed for speech processing [7], MFCCs have recently found wider use in music information retrieval [19] and environmental audio processing [3]. A richer representation, the scattering transform, has enjoyed significant success in various audio [1] and biomedical [6] signal classification tasks. Its structure is that of a convolutional neural network [2,4,17,21], but with fixed filters.…”