Cardiotocograhpy Analysis Web Site

The Lastest Papers

A Study of Artificial Neural Network Training Algorithms for Classification of Cardiotocography Signals

Cardiotocography (CTG) that contains fetal heart rate (FHR) and uterine contraction (UC) signals is a monitoring technique. During the last decades, FHR signals have been classified as normal, suspicious, and pathological using machine learning techniques. As a classifier, artificial neural network (ANN) is notable due to its powerful capabilities. For this reason, behaviors and performances of neural network training algorithms were investigated and compared on classification task of the CTG traces in this study. Training algorithms of neural network were categorized in five group as Gradient Descent, Resilient Backpropagation, Conjugate Gradient, Quasi-Newton, and Levenberg-Marquardt. Two different experimental setups were performed during the training and test stages to achieve more generalized results. Furthermore, several evaluation parameters, such as accuracy (ACC), sensitivity (Se), specificity (Sp), and geometric mean (GM), were taken into account during performance comparison of the algorithms. An open access CTG dataset containing 2126 instances with 21 features and located under UCI Machine Learning Repository was used in this study. According to results of this study, all training algorithms produced rather satisfactory results. In addition, the best classification performances were obtained with Levenberg-Marquardt backpropagation (LM) and Resilient Backpropagation (RP) algorithms. The GM values of RP and LM were obtained as 89.69% and 86.14%, respectively. Consequently, this study confirms that ANN is a useful machine learning tool to classify FHR recordings.

Fetal State Assessment Based on Cardiotocography Parameters Using PCA and AdaBoost

Cardiotocography (CTG) is the widely used tool for recording fetal heart rate (FHR) signal and uterine contraction (UC) activity at the same time during pregnancy and delivery. CTG is frequently used for assisting the obstetricians to obtain detailed physiological information of fetal and pregnant woman as a technique of diagnosing fetal well-being. However, the visual analysis of the CTG traces requires a high level of expertise of the obstetricians and can cause inter-and intra-observer variability. Therefore, this research aimed at realizing a clinical decision support system for diagnosing fetal risk through advanced machine learning method applied to relevant features extracted from CTG recordings. In this paper, a CTG dataset consisting of 2126 recordings and 21 features obtained from UCI Machine Learning Repository is used for classification. After selecting more relevant features from total features based on Principle Component Analysis (PCA), data are trained and tested through Adaptive Boosting (AdaBoost) algorithm integrated with Support Vector Machine (SVM) to obtain a strong classifier for classifying the unknown CTG data and predicting the fetal state. Fetal state is divided into two classes as normal and pathological. Based on tenfold cross-validation, according to the results of this study, a good overall classification accuracy of total and selected features using AdaBoost approach were obtained as 93.0% and 98.6%, computation time of 11.6s and 2.4s, respectively. So this research shows the success of hybrid PCA and AdaBoost for classifying CTG data and assessing fetal state. Furthermore, some criterias of classification performance measure were taken into consideration, including sensitivity, specificity, AUC, etc.

Comparison of Machine Learning Techniques for Fetal Heart Rate Classification

Cardiotocography is a monitoring technique providing important and vital information on fetal status during antepartum and intrapartum periods. The advances in modern obstetric practice allowed many robust and reliable machine learning techniques to be utilized in classifying fetal heart rate signals. The role of machine learning approaches in diagnosing diseases is becoming increasingly essential and intertwined. The main aim of the present study is to determine the most efficient machine learning technique to classify fetal heart rate signals. Therefore, the research has been focused on the widely used and practical machine learning techniques, such as artificial neural network, support vector machine, extreme learning machine, radial basis function network, and random forest. In a comparative way, fetal heart rate signals were classified as normal or hypoxic using the aforementioned machine learning techniques. The performance metrics derived from confusion matrix were used to measure classifiers’ success. According to experimental results, although all machine learning techniques produced satisfactory results, artificial neural network yielded the rather well results with the sensitivity of 99.73% and specificity of 97.94%. The study results show that the artificial neural network was superior to other algorithms.

Using wavelet transform for cardiotocography signals classification

As a fetal surveillance technique, cardiotocography (CTG) involves fetal heart rate (FHR), uterine contraction activities, and fetal movements. CTG is practiced as a primary diagnostic test throughout the world to identify events that may pose a risk to the fetus during pregnancy and delivery. In this work, FHR signals carrying vital information on fetus were analyzed by using Haar (haar), Daubechies (db5), and Symlets (sym5) mother wavelet families between levels 1 and 12. The traditionally used morphological and linear features are obtained from FHR. Also, p-norm, Frobenius form, infinity, and negative infinity norms which are obtained separately from the each of the wavelet components were used as a feature to support the classification. The obtained features were applied as an input to k-nearest neighbors (kNN) and artificial neural network (ANN) classifiers in order to discriminate the normal and hypoxic fetuses. According to experimental results, 90.51% and 90.21% classification success on the discrimination of normal and hypoxic fetuses were achieved by using haar at level 4 and kNN.

Cardiotocography analysis based on segmentation-based fractal texture decomposition and extreme learning machine

Fetal heart rate (FHR) has notable patterns for the assessment of fetal physiology and typical stress conditions. FHR signals are obtained using cardiotocography (CTG) devices also providing uterine activities simultaneously and fetal movements. In this study, a total of 88 records consisting of 44 normal and 44 hypoxic fetuses instances obtained from publicly available CTU-UHB database have been considered. The basic morphological features supporting clinical diagnosis, the powers of 4 different spectral bands and Lempel Ziv complexity have been used to define FHR signals. Also, it has been proposed to use segmentation-based fractal texture analysis (SFTA) to identify the signals more accurately. The obtained feature set was applied as the input to extreme learning machine (ELM) with 5-fold cross-validation method. According to experimental results, 79.65% of accuracy, 79.92% of specificity, and 80.95% of sensitivity were obtained. It was observed that the SFTA offers useful statistical features to distinguish normal and hypoxic fetuses.

A Study Based on Gray Level Co-Occurrence Matrix and Neural Network Community for Determination of Hypoxic Fetuses

Cardiotocography (CTG) is a monitoring technique used routinely during the pregnancy and labor and including the analysis of fetal heart rates and movements with uterine contractions. The fact that CTG signals are interpreted by experts generally with eye and CTG has high false positive rate results in intra- and inter-observer conflicts and causes the observers to frequently notice real pathological cases. Therefore, various computer-aided methods supporting diagnosis process have been developed. In this study, a new approach is suggested based on signal and image processing techniques in order to provide the classification of CTG signals. In particular, morphological, spectral and statistical properties of CTG signals are obtained with the way defined conventionally. A spectrum of the signals containing time-frequency information was transformed into 8-bit gray-level image and it was enabled to build gray level co-occurrence matrix (GLCM). In the final step, a combination of morphological, statistical, spectral and image-based properties was applied as the input to the artificial neural network (ANN). In order to measure the performance of the proposed method, accuracy, sensitivity, specificity and quality indexes were used. The obtained results revealed that image-based features increased the classification success and they gave the best results when they were used with the conventional features.

Cardiotocography Signals with Artificial Neural Network and Extreme Learning Machine

Cardiotocography (CTG) is a monitoring technique that is used routinely during pregnancy and labor to assess fetal well-being. CTG consists of two signals which are fetal heart rate (FHR) and uterine contraction (UC). Twenty-one features representing the characteristic of FHR have been used in this work. The features are obtained from a large dataset consisting of 2126 records in UCI Machine Learning Repository. The prominent features, such as baseline, the number of acceleration and deceleration patterns, and variability recommended by International Federation of Gynecology and Obstetrics (FIGO) have also taken into account during CTG analysis. The features were applied as the input to feedforward neural network (ANN) and Extreme Learning Machine (ELM) to classify FHR patterns in this study. FHR is recently divided into three classes as normal, suspicious and pathological. According to the results of this study, the accuracy of classification of ANN and ELM were obtained as 91.84% and 93.42%, respectively.

Evaluation of Fetal Distress Diagnosis during Delivery Stages based on Linear and Nonlinear Features of Fetal Heart Rate for Neural Network Community

Cardiotocography (CTG) is a fetal monitoring technique used to determine the distress level of the fetus during pregnancy and delivery. CTG consists of two different signals including fetal heart rate (FHR) and uterine contraction (UC) activities. The linear features of FHR are the most powerful prognostic indices to ascertain whether the fetus in distress. In addition, it is observed that nonlinear features have produced very great results on the time series analysis in recently. In this context, the classification success of the neural network community designed based on the linear and nonlinear features of FHR is analyzed for the delivery process evaluated in three stages. The experimental results have shown that the system designed to distinguish normal and pathological instances is achieved the best classification accuracy at the first stage of the analysis. Also, the greatest contribution of nonlinear features to the classification accuracy is observed at the second stage of the delivery. Consequently, 92.40%, 83.29%, and 79.22% of accuracy obtained for the three stage of the analysis, respectively.

CTG-OAS

CTG-OAS

The Lastest Papers

A Study of Artificial Neural Network Training Algorithms for Classification of Cardiotocography Signals

Fetal State Assessment Based on Cardiotocography Parameters Using PCA and AdaBoost

Comparison of Machine Learning Techniques for Fetal Heart Rate Classification

Using wavelet transform for cardiotocography signals classification

Cardiotocography analysis based on segmentation-based fractal texture decomposition and extreme learning machine

A Study Based on Gray Level Co-Occurrence Matrix and Neural Network Community for Determination of Hypoxic Fetuses

Cardiotocography Signals with Artificial Neural Network and Extreme Learning Machine

Evaluation of Fetal Distress Diagnosis during Delivery Stages based on Linear and Nonlinear Features of Fetal Heart Rate for Neural Network Community

Research Community

Members

Join us

Publications

Download

Please feel free to meet and join us.

Let's Get In Touch!