scholarly journals Multi-Center Validation Study of Automated Classification of Pathological Slowing in Adult Scalp Electroencephalograms Via Frequency Features

2021 ◽  
pp. 2150016
Author(s):  
Wei Yan Peh ◽  
John Thomas ◽  
Elham Bagheri ◽  
Rima Chaudhari ◽  
Sagar Karia ◽  
...  
Keyword(s):  
Neurological Disorders ◽  
Visual Inspection ◽  
Detection System ◽  
Automated Classification ◽  
The Us ◽  
Electroencephalogram Eeg ◽  
Level Performance ◽  
Frequency Features ◽  
Channel Segment

Pathological slowing in the electroencephalogram (EEG) is widely investigated for the diagnosis of neurological disorders. Currently, the gold standard for slowing detection is the visual inspection of the EEG by experts, which is time-consuming and subjective. To address those issues, we propose three automated approaches to detect slowing in EEG: Threshold-based Detection System (TDS), Shallow Learning-based Detection System (SLDS), and Deep Learning-based Detection System (DLDS). These systems are evaluated on channel-, segment-, and EEG-level. The three systems perform prediction via detecting slowing at individual channels, and those detections are arranged in histograms for detection of slowing at the segment- and EEG-level. We evaluate the systems through Leave-One-Subject-Out (LOSO) cross-validation (CV) and Leave-One-Institution-Out (LOIO) CV on four datasets from the US, Singapore, and India. The DLDS achieved the best overall results: LOIO CV mean balanced accuracy (BAC) of 71.9%, 75.5%, and 82.0% at channel-, segment- and EEG-level, and LOSO CV mean BAC of 73.6%, 77.2%, and 81.8% at channel-, segment-, and EEG-level. The channel- and segment-level performance is comparable to the intra-rater agreement (IRA) of an expert of 72.4% and 82%. The DLDS can process a 30 min EEG in 4 s and can be deployed to assist clinicians in interpreting EEGs.

scholarly journals EEG-Based Automatic Sleep Staging Using Ontology and Weighting Feature Analysis

2018 ◽  
Vol 2018 ◽  
pp. 1-16 ◽  
Author(s):  
Bingtao Zhang ◽  
Tao Lei ◽  
Hong Liu ◽  
Hanshu Cai
Keyword(s):  
Visual Inspection ◽  
Sleep Stages ◽  
Subjective Time ◽  
Sleep Staging ◽  
Large Bulk ◽  
State Classification ◽  
Eeg Data ◽  
Electroencephalogram Eeg ◽  
Eeg Features

Sleep staging is considered as an effective indicator for auxiliary diagnosis of sleep diseases and related psychiatric diseases, so it attracts a lot of attention from sleep researchers. Nevertheless, sleep staging based on visual inspection of tradition is subjective, time-consuming, and error-prone due to the large bulk of data which have to be processed. Therefore, automatic sleep staging is essential in order to solve these problems. In this article, an electroencephalogram- (EEG-) based scheme that is able to automatically classify sleep stages is proposed. Firstly, EEG data are preprocessed to remove artifacts, extract features, and normalization. Secondly, the normalized features and other context information are stored using an ontology-based model (OBM). Thirdly, an improved method of self-adaptive correlation analysis is designed to select the most effective EEG features. Based on these EEG features and weighting features analysis, the improved random forest (RF) is considered as the classifier to achieve the classification of sleep stages. To investigate the classification ability of the proposed method, several sets of experiments are designed and conducted to classify the sleep stages into two, three, four, and five states. The accuracy of five-state classification is 89.37%, which is improved compared to the accuracy using unimproved RF (84.37%) or previously reported classifiers. In addition, a set of controlled experiments is executed to verify the effect of the number of sleep segments (epochs) on the classification, and the results demonstrate that the proposed scheme is less affected by the sleep segments.

Automated classification of neurological disorders of gait using spatio-temporal gait parameters

2015 ◽  
Vol 25 (2) ◽  
pp. 413-422 ◽  
Author(s):  
Cauchy Pradhan ◽  
Max Wuehr ◽  
Farhoud Akrami ◽  
Maximilian Neuhaeusser ◽  
Sabrina Huth ◽  
...  
Keyword(s):  
Neurological Disorders ◽  
Automated Classification ◽  
Gait Parameters ◽  
Spatio Temporal

Automated Classification of Focal and Non-Focal EEG Signals Based on Bivariate Empirical Mode Decomposition

2018 ◽  
pp. 13-33 ◽  
Author(s):  
Rajeev Sharma ◽  
Ram Bilas Pachori
Keyword(s):  
Empirical Mode Decomposition ◽  
Support Vector ◽  
Automated Classification ◽  
Intrinsic Mode Functions ◽  
Eeg Signals ◽  
Mode Decomposition ◽  
Electroencephalogram Eeg ◽  
Aided Diagnosis ◽  
Bivariate Empirical Mode Decomposition

The chapter presents a new approach of computer aided diagnosis of focal electroencephalogram (EEG) signals by applying bivariate empirical mode decomposition (BEMD). Firstly, the focal and non-focal EEG signals are decomposed using the BEMD, which results in intrinsic mode functions (IMFs) corresponding to each signal. Secondly, bivariate bandwidths namely, amplitude bandwidth, precession bandwidth, and deformation bandwidth are computed for each obtained IMF. Interquartile range (IQR) values of bivariate bandwidths of IMFs are employed as the features for classification. In order to perform classification least squares support vector machine (LS-SVM) is used. The results of the experiment suggest that the computed bivariate bandwidths are significantly useful to discriminate focal EEG signals. The resultant classification accuracy obtained using proposed methodology, applied on the Bern-Barcelona EEG database, is 84.01%. The obtained results are encouraging and the proposed methodology can be helpful for identification of epileptogenic focus.

scholarly journals EyeBallGUI: A Tool for Visual Inspection and Binary Marking of Multi-channel Bio-signals

2017 ◽  
Author(s):  
Kieran S. Mohr ◽  
Bahman Nasseroleslami ◽  
Parameswaran M. Iyer ◽  
Orla Hardiman ◽  
Edmund C. Lalor
Keyword(s):  
Visual Inspection ◽  
Binary Classification ◽  
Analysis Tool ◽  
Data Retention ◽  
Wide Range ◽  
Sample Data ◽  
Electroencephalogram Eeg ◽  
Free Open Source ◽  
Selection Of

AbstractA wide range of studies in human neuroscience rely on the analysis of electrophysiological bio-signals such as electroencephalogram (EEG) where customized data analysis may require supervised artefact rejection, binary marking through visual inspection, selection of noise and artefact samples for pre-processing algorithms, and selection of clinically-relevant signal segments in neurological conditions. Nevertheless, the existing preprocessing tools do not provide the needed flexibility to handle such tasks efficiently. We therefore developed a free open-source Graphical User Interface (GUI), EyeBallGUI, that allows visualization and flexible, manual marking (binary classification) of multi-channel bio-signal data. EyeBallGUI, developed for MATLAB®, allows the user to interactively and accurately inspect and mark multi-channel digitized data with no restriction on marking periods of data in subsets of channels (a restriction in place in existing tools). The new tool facilitates precise, manual marking of bio-signals by allowing any desired segment of data to be marked in any subset of channels. It is therefore of utility in circumstances where such flexibility is essential. The developed GUI is an auxiliary analysis tool that shall facilitate neural signal (pre-)processing applications where it is desirable to perform accurate supervised artefact rejection, flexible data marking for increased data retention yield, extraction of specific signal segments by expert users from sample data, or labeling of data for clinical and scientific research purposes.

scholarly journals Extracting Time-Frequency Features of Images for Robust LSTM-based Classification of H&E Stained Tissue

2020 ◽  
Author(s):  
Tuan Pham
Keyword(s):  
Short Term Memory ◽  
Digital Pathology ◽  
Support Vector ◽  
Automated Classification ◽  
Time Frequency ◽  
Statistical Measures ◽  
Vector Machines ◽  
Histopathological Images ◽  
Frequency Features

The importance of automated classification of histopathological images has been increasingly recognized for effective processing of large volumes of data in the era of digital pathology for new discovery of disease mechanism. This paper presents a deep-learning approach that extracts time-frequency features of H&E stained tissue images for classification by long short-term memory networks. Using two large public databases of colorectal-cancer and heart-failure H&E stained tissue images, the proposed approach outperforms several state-of-the-art benchmark classification methods, including support vector machines and convolutional neural networks in terms of several statistical measures.

70. Computer aided detection system for the automated classification of clustered microcalcifications in digital mammograms

2018 ◽  
Vol 56 ◽  
pp. 106-107
Author(s):  
R. Massafra ◽  
A. Fanizzi ◽  
T. Basile ◽  
R. Bellotti ◽  
R. Carbonara ◽  
...  
Keyword(s):  
Detection System ◽  
Automated Classification ◽  
Computer Aided Detection ◽  
Computer Aided

scholarly journals Extracting Time-Frequency Features of Images for Robust LSTM-based Classification of H&E Stained Tissue

2020 ◽  
Author(s):  
Tuan Pham
Keyword(s):  
Short Term Memory ◽  
Digital Pathology ◽  
Support Vector ◽  
Automated Classification ◽  
Time Frequency ◽  
Statistical Measures ◽  
Vector Machines ◽  
Histopathological Images ◽  
Frequency Features

The importance of automated classification of histopathological images has been increasingly recognized for effective processing of large volumes of data in the era of digital pathology for new discovery of disease mechanism. This paper presents a deep-learning approach that extracts time-frequency features of H&E stained tissue images for classification by long short-term memory networks. Using two large public databases of colorectal-cancer and heart-failure H&E stained tissue images, the proposed approach outperforms several state-of-the-art benchmark classification methods, including support vector machines and convolutional neural networks in terms of several statistical measures.

CLASSIFICATION OF FOCAL AND NONFOCAL EEG SIGNALS USING FEATURES DERIVED FROM FOURIER-BASED RHYTHMS

2017 ◽  
Vol 17 (07) ◽  
pp. 1740002 ◽  
Author(s):  
PUSHPENDRA SINGH ◽  
RAM BILAS PACHORI
Keyword(s):  
Filter Bank ◽  
Support Vector ◽  
Svm Classifier ◽  
Automated Classification ◽  
Eeg Signals ◽  
Input Feature ◽  
The Mean ◽  
A New Technique ◽  
Electroencephalogram Eeg

We propose a new technique for the automated classification of focal and nonfocal electroencephalogram (EEG) signals using Fourier-based rhythms in this paper. The EEG rhythms, namely, delta, theta, alpha, beta and gamma, are obtained using the discrete Fourier transform (DFT)-based filter bank applied on EEG signals. The mean-frequency (MF) and root-mean-square (RMS) bandwidth features are derived using DFT-based computation on rhythms of EEG signals and their envelopes. These derived features, namely, MF and RMS bandwidths have been provided as an input feature set for the classification of focal and nonfocal EEG signals using a least-squares support vector machine (LS-SVM) classifier. We present experimental results obtained from the publicly available database in order to demonstrate the effectiveness of the proposed feature sets for the automated classification of the focal and nonfocal classes of EEG signals. The obtained classification accuracy in this dataset for the automated classification of focal and nonfocal 50 pairs and 750 pairs of EEG signals are 89.7% and 89.52%, respectively.

scholarly journals Minireview of Epilepsy Detection Techniques Based on Electroencephalogram Signals

2021 ◽  
Vol 15 ◽  
Author(s):  
Guangda Liu ◽  
Ruolan Xiao ◽  
Lanyu Xu ◽  
Jing Cai
Keyword(s):  
Neurological Disorders ◽  
Development Trend ◽  
Seizure Prediction ◽  
Eeg Signals ◽  
Detection Techniques ◽  
Detection Technology ◽  
Electroencephalogram Eeg ◽  
New Algorithms

Epilepsy is one of the most common neurological disorders typically characterized by recurrent and uncontrollable seizures, which seriously affects the quality of life of epilepsy patients. The effective tool utilized in the clinical diagnosis of epilepsy is the Electroencephalogram (EEG). The emergence of machine learning promotes the development of automated epilepsy detection techniques. New algorithms are continuously introduced to shorten the detection time and improve classification accuracy. This minireview summarized the latest research of epilepsy detection techniques that focused on acquiring, preprocessing, feature extraction, and classification of epileptic EEG signals. The application of seizure prediction and localization based on EEG signals in the diagnosis of epilepsy was also introduced. And then, the future development trend of epilepsy detection technology has prospected at the end of the article.

Sign in / Sign up

Export Citation Format

Share Document