Department of Electronic Engineering, College of Information Science and Technology, Jinan University, Guangzhou, China.
Department of Computer Science, College of Information Science and Technology, Jinan University, Guangzhou, China.
Comput Biol Med. 2021 Mar;130:104218. doi: 10.1016/j.compbiomed.2021.104218. Epub 2021 Jan 14.
Cardiotocography (CTG) signal abnormality classification plays an important role in the diagnosis of abnormal fetuses. This classification problem is made difficult by the non-stationary nature of CTG and the dataset imbalance. This paper introduces a novel application of Time-frequency (TF) features and Ensemble Cost-sensitive Support Vector Machine (ECSVM) classifier to tackle these problems.
Firstly, CTG signals are converted into TF-domain representations by Continuous Wavelet Transform (CWT), Wavelet Coherence (WTC), and Cross-wavelet Transform (XWT). From these representations, a novel image descriptor is used to extract the TF features. Then, the linear feature is derived from the time-domain representation of the CTG signal. The linear and TF features are fed to the ECSVM classifier for prediction and classification of fetal outcome.
The TF features show the significant difference (p-value<0.05) in distinguishing abnormal CTG signals, but not for traditional nonlinear features. In ECSVM abnormality classification, using only linear features, the sensitivity, specificity, and quality index are 59.3%, 78.3%, and 68.1%, respectively, whereas more effective results (sensitivity: 85.2%, specificity: 66.1%, and quality index: 75.0%) are obtained using a combination of linear and TF features, with a performance improvement index of 10.1%. Especially, the area under the receiver operating characteristic curve (0.77 vs. 0.64) is significantly increased with the ECSVM vs. SVM.
Our method can greatly improve the classification results, especially for sensitivity. It improves the true positive rate of CTG abnormality classification and reduces the false positive rate, which may help detect and treat abnormal fetuses during labor.
胎心监护图（CTG）信号异常分类在异常胎儿的诊断中起着重要作用。由于 CTG 的非平稳性和数据集的不平衡性，使得这个分类问题变得很困难。本文提出了一种将时频（TF）特征和集成代价敏感支持向量机（ECSVM）分类器应用于解决这些问题的新方法。
首先，通过连续小波变换（CWT）、小波相干（WTC）和交叉小波变换（XWT）将 CTG 信号转换为 TF 域表示。从这些表示中，使用新的图像描述符来提取 TF 特征。然后，从 CTG 信号的时域表示中提取线性特征。将线性和 TF 特征输入 ECSVM 分类器，用于预测和分类胎儿结局。
TF 特征在区分异常 CTG 信号方面表现出显著差异（p 值<0.05），而传统的非线性特征则没有。在 ECSVM 异常分类中，仅使用线性特征时，灵敏度、特异性和质量指数分别为 59.3%、78.3%和 68.1%，而使用线性和 TF 特征的组合则获得了更有效的结果（灵敏度：85.2%、特异性：66.1%和质量指数：75.0%），性能提高指数为 10.1%。特别是，ECSVM 比 SVM 的接收者操作特征曲线下面积（0.77 比 0.64）显著增加。
我们的方法可以大大提高分类结果，特别是灵敏度。它提高了 CTG 异常分类的真阳性率，降低了假阳性率，这可能有助于在分娩过程中检测和治疗异常胎儿。
