A method for detecting high-frequency oscillations using semi-supervised k-means and mean shift clustering
Introduction
Epilepsy is a worldwide epidemic of non-communicable chronic brain disease affecting all age groups. The prevalence of epilepsy accounts for about 1% of the world's population. At present, there are about 50 million people with epilepsy worldwide, and 80% of them are in developing countries. 70% of newly diagnosed epilepsy patients can be cured with antiepileptic drugs. For patients with poor drug treatment, surgery is another possible effective way to treat epilepsy [1], [2], [3]. Preoperative accurate positioning of epileptic seizures is more important than surgery itself. The traditional seizure onset zones (SOZs) are focused on electroencephalogram (EEG) data with a frequency less than 80 Hz. The epileptic origins can be located by extracting the frequency components of EEG signals [4], [5]. Since the epileptiform discharges have a wide range of transmission, and epilepsy brain telecoms in low frequency bands are easily interfered by other signals, the misjudgment of results broadly exist [6]. From the 1990s, scholars have begun to study high-frequency oscillations (HFOs) with frequencies above 80 Hz in epileptic EEG signals [7]. Researchers classify HFOs into three types according to their frequency: Rs (Ripples, 80–250 Hz), FRs (Fast Ripples, 250–500 Hz), VHFO (Very High Frequency Oscillatory, 1000–2500 Hz) [8], [9]. Among them, VHFO are difficult to be collected and their mechanism of action is not clear. A large number of literatures are related to the Rs and FRs of HFOs in EEG data and show that Rs and FRs more directly reflect the synchronization activities of neurons. Therefore, HFOs of 80–500 Hz become a new biological indicator in the location of SOZs. It can indicates the epileptic seizure area more accurately than the epileptic discharge, which can reduce the pain caused by long-term EEG recording and reduce the possibility of surgical infection [10], [11].
Current SOZs location methods can be classified as visual assessment and automated detection. Visual assessment is the most commonly used at present [12], and HFOs are visually labeled by experts according to experience. However, artificially labeled HFOs in visual assessment are very time consuming, which will greatly increases the patient's pain and the risk of surgical infection [13]. In addition, the accuracy of the visually marking will be influenced by doctors and various objective factors. Since missing labels and mislabeling are difficult to avoid, it is necessary to find a fast and efficient automatic detection method [14]. With the in-depth research of computational intelligence methods, more computational intelligence methods have been applied in different fields. In the literature [15], a high-dimensional feature is introduced to the facial expression recognition. Furthermore, the deep sparse autoencoders (DSAE) are established to recognize the facial expressions with high accuracy by learning robust and discriminative features from the data. In the literature [16], the SDPSO-SVM model was used to classify Alzheimer's disease (AD) and mild cognitive impairment (MCI), which became an effective diagnostic method for AD.
Recent studies have shown that HFOs are closely related to SOZs, and can quickly and accurately locate SOZs by detecting and judging HFOs. In related researches, automatic detection includes feature extraction and classification of HFOs. Detection algorithms in time domain, frequency domain and time-frequency domain, including root mean square (RMS) [17], short-term linear length [18], complex Morlet wavelet transform [19] and Hilbert transform [20] are used in the feature extraction. In [21], RMS is calculated from the filtered EEG signal to estimate the short-term energy. However, that method cannot accurately predict the EEG signal and its wake signal. In [22], the complex Morlet wavelet is used to extract the time-frequency characteristics of EEG from the wavelet transform of the mother wavelet. However, the time-frequency resolution of different patient data is not high. The classification methods of HFOs mainly include threshold method, fuzzy neural network (FNN), support vector machine (SVM) classification and so on. In [23], a method for automatic detection of HFOs is proposed. The fuzzy entropy and short-time energy are extracted from the EEG signal as feature input to the FNN classifier. Through the FNN classifier, the signal can be divided into HFOs and normal rhythm. In [24], Gabor transform is performed on EEG data, and the energy ratio and duration characteristics of HFOs events are extracted. Simultaneously input and train multiple types of SVM classifiers for various types of HFOs and artificial noise. The method in [25] first detects the event of suspected HFOs, and uses the continuous wavelet transform and the improved method of short-time Fourier transform to transform the time-frequency diagram of the suspected event, and considers that HFOs are in time. The frequency map shows an independent bright spot. Moreover, it is judged whether the suspected event is a HFO according to the frequency and power spectral density. The location of the epileptic SOZ is to count the frequency of occurrence of these events. In [26], a multi-feature extraction and threshold comprehensive judgment method is proposed. That method has high sensitivity, but the steps are complicated and the calculation time is long. Based on the latest research from abroad, it is still in an exploratory research stage. Although these methods have high sensitivity, their specificity is low, and there are still false positives.
Clustering algorithms have been widely used in many aspects. For example, a new clustering algorithm is proposed in [27], [28] to improve the accuracy of traditional clustering approaches with applications in analyzing real-time patient attendance data from an accident & emergency (A&E) department in a local UK hospital.
In this paper, the semi-supervised k-means and mean shift algorithms are used to analyze and process HFOs. The data are preprocessed, then the feature is composed of feature vectors, and the labeled center is used to initialize the cluster center of the k-means algorithm. In practical application, the original EEG of each channel of the patient is preprocessed and extracted feature, and the clustered center is used for clustering. The obtained suspected pathological HFOs are clustered by the mean shift algorithm, and the results are analyzed by using the spectral centroid (SC) to determine the channel of the SOZ position. The analytical method improves the sensitivity and specificity of the algorithm, and lays a solid theoretical and experimental basis for the accurate positioning of the epileptic SOZs.
Section snippets
A new method for detecting HFOs
The analysis method in this paper is to process the raw data collected by EEG machine from patients with refractory epilepsy. The sampling frequency of each channel is 2000 Hz. The acquisition electrode is a grid structure that covers the whole area of the cerebral cortex. Intermittent or pre-seizure data are taken from the multi-channel data as a sample. The main purpose of the algorithm is to detect and analyze the HFOs in the raw data, and then locate the channel where SOZ is located.
Simulations and analysis
In this paper, a training set is firstly constructed with the physiological and pathological high-frequency oscillatory rhythm data labeled by experts, which is preprocessed and extracted features, and then the clustering center of semi-supervised k-means algorithm is initialized. The original EEG data of five epileptic patients are preprocessed and extracted and classified according to the pre-initialized clustering center of semi-supervised k-means. Mean shift algorithm is used to cluster the
Conclusions
This paper has proposed a new method for HFOs detection. Two algorithms that can clearly distinguish from physiological HFOs and pathological HFOs: WE and TEO have been used as feature extraction features. The clustering center of the semi-supervised k-means algorithm is initialized by data initialization, and the unlabeled data is clustered to obtain physiological HFOs and suspected pathological HFOs. The mean shift algorithm is used to cluster suspected pathological HFOs, and the clustering
Yuxiao Du received the B.Sc., M.Sc. and the Ph.D. degrees in engineering from Central South University (CSU), China, in 1995, 2000 and 2004 respectively. He joined the staff of Guangdong University of Technology in 2004, and is currently an associate professor in the School of Automation, Guangdong University of Technology. His current research interests are biomedical engineering, digital image processing, and automation equipment and integration.
References (33)
- et al.
Application of adaptive Savitzky-Golay filter for EEG signal processing
Perspect. Sci.
(2016) - et al.
The morphology of high frequency oscillations (HFO) does not improve delineating the epileptogenic zone
Clin. Neurophysiol.
(2016) - et al.
Automated detection of epileptic EEGs using a novel fusion feature and extreme learning machine
Neurocomputing
(2016) - et al.
Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier
Neurocomputing
(2017) - et al.
A phase-locked loop epilepsy network emulator
Neurocomputing
(2016) - et al.
Improving classification of epileptic and non-epileptic EEG events by feature selection
Neurocomputing
(2016) - et al.
High-frequency oscillations (HFOs) in clinical epilepsy
Prog. Neurobiol.
(2012) - et al.
A sequential method using multiplicative extreme learning machine for epileptic seizure detection
Neurocomputing
(2016) - et al.
Improving the identification of high frequency oscillations
Clin. Neurophysiol.
(2009) - et al.
Facial expression recognition via learning deep sparse autoencoders
Neurocomputing
(2018)
A new switching-delayed-PSO-based optimized SVM algorithm for diagnosis of Alzheimer's disease
Neurocomputing
A comparison between detectors of high frequency oscillations
Clin. Neurophysiol.
Human and automated detection of high-frequency oscillations in clinical intracranial EEG re-cordings
Clin. Neurophysiol.
Automated detection and classification of high frequency oscillations (HFOs) in human intracereberal EEG
Biomed. Signal Process. Control
Multi-scale dense gate recurrent unit networks for bearing remaining useful life prediction
Futur. Gener. Comput. Syst.
Comparison of distributed evolutionary k-means clustering algorithms
Neurocomputing
Cited by (29)
Computer-aided recognition and assessment of a porous bioelastomer in ultrasound images for regenerative medicine applications
2023, Medicine in Novel Technology and DevicesInteractive interface for spatio-temporal mapping of epileptic human brain using characteristics of high frequency oscillations (HFOs)
2023, Biomedical Signal Processing and ControlClassification of High Frequency Oscillations in intracranial EEG signals based on coupled time-frequency and image-related features
2022, Biomedical Signal Processing and ControlDetection of high-frequency oscillations in electroencephalography: A scoping review and an adaptable open-source framework
2021, SeizureCitation Excerpt :Migliorelli et al. modified and implemented the algorithm developed by Burnos et al. for the automatic detection of ripples in magnetoencephalography (MEG), reporting a sensitivity of 68.66 % [39]. 25 studies leveraged data mining or machine learning in their algorithms, minimizing the need for human intervention in the automated process [46,50–73]. 22 studies utilized iEEG, 1 study used MEG, and 2 studies used scalp EEG.
Automatic detection of HFOs based on singular value decomposition and improved fuzzy c-means clustering for localization of seizure onset zones
2020, NeurocomputingCitation Excerpt :Therefore, it is regarded that HFOs are novel biomarkers of epileptic SOZs [17]. The conventional way to detect HFOs is visual marking, which helps us to gain insights into the epilepsy by HFOs [18,19]. However, due to many disadvantages of visual marking such as long time consuming [20–22], it is significant to develop automatic detection techniques on HFOs, which has attracted extensive research interests in recent decades [23,24].
Yuxiao Du received the B.Sc., M.Sc. and the Ph.D. degrees in engineering from Central South University (CSU), China, in 1995, 2000 and 2004 respectively. He joined the staff of Guangdong University of Technology in 2004, and is currently an associate professor in the School of Automation, Guangdong University of Technology. His current research interests are biomedical engineering, digital image processing, and automation equipment and integration.
Bo Sun received the B.Sc. degree from Nanyang Normal University, China, in 2016. He is currently pursuing M.Sc. degree in the School of Automation, Guangdong University of Technology. His current research interests are EEG signal processing and pattern recognition.
Renquan Lu received the Ph.D. degree in control science and engineering from Zhejiang University, Hangzhou, China, in 2004. He is currently a Professor with the School of Automation, Guangdong University of Technology, Guangzhou, China. His research was supported by the National Science Fund for Distinguished Young Scientists of China in 2014, honored as the Distinguished Professor of Pearl River Scholars Program of Guangdong Province in 2015, and the Yangtze River Scholars Program by the Ministry of Education of China in 2017. His current research interests include complex systems, networked control systems, and nonlinear systems.
Chunling Zhang received the B.S. degree from Guilin University of Electronic Technology, China, in 2017. She is currently pursuing M.Sc. degree in the School of Automation, Guangdong University of Technology. Her current research interests are EEG signal processing and pattern recognition.
Hao Wu received the B.S. degree from Chengdu University of Information Technology, China, in 2005.He is currently teaching at Hubei College of Chinese Medicine. His current research interests are Computer and Communication.
This work was supported in part by the National Natural Science Foundation of China under Grant 17ZK0029, and the Guangdong Provincial Science Foundation of China under Grant 2013B010401027.