Multifractal Analysis of Uterine Electromyography Signals for the Assessment of Progression of Pregnancy in Term Conditions
01 Sep 2019-IEEE Journal of Biomedical and Health Informatics (Institute of Electrical and Electronics Engineers (IEEE))-Vol. 23, Iss: 5, pp 1972-1979
TL;DR: The Hurst and scaling exponents extracted from the signals indicate that uterine EMG signals are multifractal in nature and can help in investigating the progressive changes in uterine muscle contractions during pregnancy.
Abstract: Objectives: The objectives of this paper are to examine the source of multifractality in uterine electromyography (EMG) signals and to study the progression of pregnancy in the term (gestation period > 37 weeks) conditions using multifractal detrending moving average (MFDMA) algorithm. Methods: The signals for the study, considered from an online database, are obtained from the surface of abdomen during the second (T1) and third trimester (T2). The existence of multifractality is tested using Hurst and scaling exponents. With the intention of identifying the origin of multifractality, the preprocessed signals are converted to shuffle and surrogate data. The original and the transformed signals are subjected to MFDMA to extract multifractal spectrum features, namely strength of multifractality, maximum, minimum, and peak singularity exponents. Results: The Hurst and scaling exponents extracted from the signals indicate that uterine EMG signals are multifractal in nature. Further analysis shows that the source of multifractality is mainly owing to the presence of long-range correlation, which is computed as 79.98% in T1 and 82.43% in T2 groups. Among the extracted features, the peak singularity exponent and strength of multifractality show statistical significance in identifying the progression of pregnancy. The corresponding coefficients of variation are found to be low, which show that these features have low intersubject variability. Conclusion: It appears that the multifractal analysis can help in investigating the progressive changes in uterine muscle contractions during pregnancy.
Citations
More filters
TL;DR: Evaluating different EHG segments for recognizing UCs using the convolutional neural network (CNN) could be used to determine the efficient EHg segments for recognize UC with the CNN.
Abstract: Background. Uterine contraction (UC) is the tightening and shortening of the uterine muscles which can indicate the progress of pregnancy towards delivery. Electrohysterogram (EHG), which reflects uterine electrical activities, has recently been studied for UC monitoring. In this paper, we aimed to evaluate different EHG segments for recognizing UCs using the convolutional neural network (CNN). Materials and Methods. In the open-access Icelandic 16-electrode EHG database (122 recordings from 45 pregnant women), 7136 UC and 7136 non-UC EHG segments with the duration of 60 s were manually extracted from 107 recordings of 40 pregnant women to develop a CNN model. A fivefold cross-validation was applied to evaluate the CNN based on sensitivity (SE), specificity (SP), and accuracy (ACC). Then, 1056 UC and 1056 non-UC EHG segments were extracted from the other 15 recordings of 5 pregnant women. Furthermore, the developed CNN model was applied to identify UCs using different EHG segments with the durations of 10 s, 20 s, and 30 s. Results. The CNN achieved the average SE, SP, and ACC of 0.82, 0.93, and 0.88 for a 60 s EHG segment. The EHG segments of 10 s, 20 s, and 30 s around the TOCO peak achieved higher SE and ACC than the other segments with the same duration. The values of SE from 20 s EHG segments around the TOCO peak were higher than those from 10 s to 30 s EHG segments on the same side of the TOCO peak. Conclusion. The proposed method could be used to determine the efficient EHG segments for recognizing UC with the CNN.
14 citations
TL;DR: In this paper , a review of the application of EHG signal analysis and its application to preterm birth diagnostic methods, and in particular on the analysis of such signals using machine learning techniques is presented.
Abstract: Preterm birth is the leading cause of neonatal morbidity and mortality. Early identification of high-risk deliveries, combined with appropriate medication appears as the way to treat the problem, although effective early diagnostic methods remain elusive. Since the strong contractions that drive the fetus out of the uterus can be traced back to the electrical activity of uterine muscle cells, the external recording of these activities in the form of electrohysterogram (EHG) opens a new research direction for the development of preterm diagnostic methods. This review focuses on EHG signal analysis and its application to preterm birth diagnostic methods, and in particular on the analysis of such signals using machine learning techniques. We introduce the publicly available databases of EHG recordings, used as a testing ground for this approach, as well as the methods to extract meaningful information from the raw data. We stress the problem of imbalance, due to the comparatively small number of patients suffering from preterm births, and discuss techniques to mitigate these effects. Last, we discuss the possibility to identify and characterize contractions directly from EHG signals. We conclude by discussing new research directions, in particular based on a biophysical description of uterus contraction towards the end of pregnancy, and their possible applications to extract more effective features and for better dealing with the shortage of training examples.
11 citations
TL;DR: In this article, a two dimensional multi-fractal detrended fluctuation analysis (2d MFDFA) was used to quantify the alteration of the salivary fern pattern in different OPMDs and OC in relation to normal counterpart.
Abstract: Saliva has emerged as an efficient screening sample for early stage detection of oral cancer (OC) owing to non-invasiveness coupled with high sensitivity and specificity. Although spectroscopic characterization of saliva in oral potentially malignant disorders OPMDs) and OC is extensively studied, its potential as imaging biomarker is sparsely explored. Further, the literature on crystalline pattern of saliva for other diseases or different physiological conditions is mostly qualitative. This paper proposed multifractal based methodology to quantitatively study alteration of the salivary fern pattern in different OPMDs and OC in relation to normal counterpart. The fern pattern of dried saliva is captured by stereo-zoom microscope in reflective mode and an image dataset is developed. We resort to two dimensional multi-fractal detrended fluctuation analysis (2d MFDFA) to elucidate the complexity and heterogeneity of these micro-structured patterns. Existence of multifractal nature embedded in salivary fern has been validated for the first time. Long range spatial correlation is found to be the origin of multifractality. Variation in multi-scale self-similarity of irregular pattern in different study groups is demonstrated by four features extracted from MFDFA. Statistical analysis shows discriminating nature of these features for combinations of pairwise interclass classification. This study sheds light on acceptability of microscopic images of arborized saliva in fast and cost effective screening of different oral lesions.
11 citations
TL;DR: In this article, a review of the application of EHG signal analysis and its application to preterm birth diagnostic methods, and in particular on the analysis of such signals using machine learning techniques is presented.
Abstract: Preterm birth is the leading cause of neonatal morbidity and mortality. Early identification of high-risk deliveries, combined with appropriate medication appears as the way to treat the problem, although effective early diagnostic methods remain elusive. Since the strong contractions that drive the fetus out of the uterus can be traced back to the electrical activity of uterine muscle cells, the external recording of these activities in the form of electrohysterogram (EHG) opens a new research direction for the development of preterm diagnostic methods. This review focuses on EHG signal analysis and its application to preterm birth diagnostic methods, and in particular on the analysis of such signals using machine learning techniques. We introduce the publicly available databases of EHG recordings, used as a testing ground for this approach, as well as the methods to extract meaningful information from the raw data. We stress the problem of imbalance, due to the comparatively small number of patients suffering from preterm births, and discuss techniques to mitigate these effects. Last, we discuss the possibility to identify and characterize contractions directly from EHG signals. We conclude by discussing new research directions, in particular based on a biophysical description of uterus contraction towards the end of pregnancy, and their possible applications to extract more effective features and for better dealing with the shortage of training examples.
11 citations
TL;DR: 3D brain stem structure is segmented and analysed for texture alterations using multifractal features to differentiate EMCI from other Alzheimer’s disease stages and results indicate that the proposed technique is able to segment the brainstem structure from all the considered images.
Abstract: Brainstem texture analysis can provide valuable information in the diagnosis of Early Mild Cognitive Impairment (EMCI) condition. In this work, 3D brainstem structure is segmented and analysed for texture alterations using multifractal features to differentiate EMCI from other Alzheimer’s disease stages. The images obtained from public domain database are preprocessed for spatial registration, skull stripping and contrast enhancement. White matter volume is segmented from the preprocessed images using fuzzy ‘C’ means clustering algorithm. Midsagittal white matter tissue is used as the initial seed to segment the brainstem volume using sparse field level set method. Multifractal detrended moving average algorithm is used to compute the fluctuation function, generalized Hurst exponent and mass exponent to study the multifractal characteristics of brainstem structure. Features extracted from the multifractal spectrum are analysed to differentiate the images pertaining to EMCI subject group. Results indicate that the proposed technique is able to segment the brainstem structure from all the considered images. The fluctuation function is observed to have linear relationship with scale. The generalized Hurst exponent decreases with order and mass exponent follows a non-linear trend demonstrating the multifractal nature of brainstem. Singularity spectral features namely strength of multifractality, Holder exponent at f(2.8), tangent slope and maximum Holder exponent are found to be most significant in differentiating EMCI from subject groups. As this complex EMCI distinction is clinically important, the proposed approach is useful for early diagnosis of Alzheimer’s condition.
9 citations
References
More filters
TL;DR: The newly inaugurated Research Resource for Complex Physiologic Signals (RRSPS) as mentioned in this paper was created under the auspices of the National Center for Research Resources (NCR Resources).
Abstract: —The newly inaugurated Research Resource for Complex Physiologic Signals, which was created under the auspices of the National Center for Research Resources of the National Institutes of He...
11,407 citations
TL;DR: In this article, a statistical approach for identifying nonlinearity in time series is described, which first specifies some linear process as a null hypothesis, then generates surrogate data sets which are consistent with this null hypothesis and finally computes a discriminating statistic for the original and for each of the surrogate sets.
Abstract: We describe a statistical approach for identifying nonlinearity in time series. The method first specifies some linear process as a null hypothesis, then generates surrogate data sets which are consistent with this null hypothesis, and finally computes a discriminating statistic for the original and for each of the surrogate data sets. If the value computed for the original data is significantly different than the ensemble of values computed for the surrogate data, then the null hypothesis is rejected and nonlinearity is detected. We discuss various null hypotheses and discriminating statistics. The method is demonstrated for numerical data generated by known chaotic systems, and applied to a number of experimental time series which arise in the measurement of superfluids, brain waves, and sunspots; we evaluate the statistical significance of the evidence for nonlinear structure in each case, and illustrate aspects of the data which this approach identifies.
3,405 citations
01 Jan 1991
TL;DR: A statistical approach for identifying nonlinearity in time series which is demonstrated for numerical data generated by known chaotic systems, and applied to a number of experimental time series, which arise in the measurement of superfluids, brain waves, and sunspots.
Abstract: We describe a statistical approach for identifying nonlinearity in time series; in particular, we want to avoid claims of chaos when simpler models (such as linearly correlated noise) can explain the data. The method requires a careful statement of the null hypothesis which characterizes a candidate linear process, the generation of an ensemble of surrogate'' data sets which are similar to the original time series but consistent with the null hypothesis, and the computation of a discriminating statistic for the original and for each of the surrogate data sets. The idea is to test the original time series against the null hypothesis by checking whether the discriminating statistic computed for the original time series differs significantly from the statistics computed for each of the surrogate sets. We present algorithms for generating surrogate data under various null hypotheses, and we show the results of numerical experiments on artificial data using correlation dimension, Lyapunov exponent, and forecasting error as discriminating statistics. Finally, we consider a number of experimental time series -- including sunspots, electroencephalogram (EEG) signals, and fluid convection -- and evaluate the statistical significance of the evidence for nonlinear structure in each case. 56 refs., 8 figs.
3,049 citations
"Multifractal Analysis of Uterine El..." refers background in this paper
...In phase randomization, the nonlinear properties are removed with unaltered linear signal characteristics [35]....
[...]
...2) Surrogate: Surrogate series are generated by Fourier phase randomization from which the influence of fat-tail distribution is determined [35]....
[...]
TL;DR: In this paper, the authors investigate the possibility that time series generated by certain physiological control systems may be members of a special class of complex processes, termed multifractal, which require a large number of exponents to characterize their scaling properties.
Abstract: There is evidence that physiological signals under healthy conditions may have a fractal temporal structure. Here we investigate the possibility that time series generated by certain physiological control systems may be members of a special class of complex processes, termed multifractal, which require a large number of exponents to characterize their scaling properties. We report on evidence for multifractality in a biological dynamical system, the healthy human heartbeat, and show that the multifractal character and nonlinear properties of the healthy heart rate are encoded in the Fourier phases. We uncover a loss of multifractality for a life-threatening condition, congestive heart failure.
1,448 citations
TL;DR: Support for the idea that gait dynamics has meaning has meaning and may be useful in providing insight into the neural control of locomotion and for enhancing functional assessment of aging, chronic disease, and their impact on mobility is discussed.
Abstract: Until recently, quantitative studies of walking have typically focused on properties of a typical or average stride, ignoring the stride-to-stride fluctuations and considering these fluctuations to be noise. Work over the past two decades has demonstrated, however, that the alleged noise actually conveys important information. The magnitude of the stride-to-stride fluctuations and their changes over time during a walk - gait dynamics - may be useful in understanding the physiology of gait, in quantifying age-related and pathologic alterations in the locomotor control system, and in augmenting objective measurement of mobility and functional status. Indeed, alterations in gait dynamics may help to determine disease severity, medication utility, and fall risk, and to objectively document improvements in response to therapeutic interventions, above and beyond what can be gleaned from measures based on the average, typical stride. This review discusses support for the idea that gait dynamics has meaning and may be useful in providing insight into the neural control of locomotion and for enhancing functional assessment of aging, chronic disease, and their impact on mobility.
749 citations
"Multifractal Analysis of Uterine El..." refers background in this paper
...Physiological time series such as surface EMG signals [21], electroencephalography signals [23], heart rate variability [24] and respiration analysis [25], human gait [26], blood flow, blood pressure, glucose levels, gene expression data and DNA sequencing are found to exhibit multifractal characteristics [27]....
[...]