1
|
Sopic D, Teijeiro T, Atienza D, Aminifar A, Ryvlin P. Personalized seizure signature: An interpretable approach to false alarm reduction for long-term epileptic seizure detection. Epilepsia 2023; 64 Suppl 4:S23-S33. [PMID: 35113451 DOI: 10.1111/epi.17176] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2021] [Revised: 01/13/2022] [Accepted: 01/14/2022] [Indexed: 11/28/2022]
Abstract
OBJECTIVE Long-term automatic detection of focal seizures remains one of the major challenges in epilepsy due to the unacceptably high number of false alarms from state-of-the-art methods. Our aim was to investigate to what extent a new patient-specific approach based on similarly occurring morphological electroencephalographic (EEG) signal patterns could be used to distinguish seizures from nonseizure events, as well as to estimate its maximum performance. METHODS We evaluated our approach on >5500 h of long-term EEG recordings using two public datasets: the PhysioNet.org Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) Scalp EEG database and the EPILEPSIAE European epilepsy database. We visually identified a set of similarly occurring morphological patterns (seizure signature) seen simultaneously over two different EEG channels, and within two randomly selected seizures from each individual. The same seizure signature was then searched for in the entire recording from the same patient using dynamic time warping (DTW) as a similarity metric, with a threshold set to reflect the maximum sensitivity our algorithm could achieve without false alarm. RESULTS At a DTW threshold providing no false alarm during the entire recordings, the mean seizure detection sensitivity across patients was 84%, including 96% for the CHB-MIT database and 74% for the European epilepsy database. A 100% sensitivity was reached in 50% of patients, including 79% from the CHB-MIT database and 27% from the European epilepsy database. The median latency from seizure onset to its detection was 17 ± 10 s, with 84% of seizures being detected within 40 s. SIGNIFICANCE Personalized EEG signature combined with DTW appears to be a promising method to detect ictal events from a limited number of EEG channels with high sensitivity despite low rate of false alarms, high degree of interpretability, and low computational complexity, compatible with its future use in wearable devices.
Collapse
Affiliation(s)
- Dionisije Sopic
- Embedded Systems Laboratory, Swiss Federal Institute of Technology Lausanne (EPFL), Lausanne, Switzerland
| | - Tomas Teijeiro
- Embedded Systems Laboratory, Swiss Federal Institute of Technology Lausanne (EPFL), Lausanne, Switzerland
| | - David Atienza
- Embedded Systems Laboratory, Swiss Federal Institute of Technology Lausanne (EPFL), Lausanne, Switzerland
| | - Amir Aminifar
- Department of Electrical and Information Technology, Lund University, Lund, Sweden
| | - Philippe Ryvlin
- Department of Clinical Neurosciences, Neurology Service, Lausanne University Hospital (Vaud University Hospital Center), University of Lausanne, Lausanne, Switzerland
| |
Collapse
|
2
|
Zhao L, Zhang Y, Yu X, Wu H, Wang L, Li F, Duan M, Lai Y, Liu T, Dong L, Yao D. Quantitative signal quality assessment for large-scale continuous scalp electroencephalography from a big data perspective. Physiol Meas 2023; 44. [PMID: 35952665 DOI: 10.1088/1361-6579/ac890d] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2021] [Accepted: 08/11/2022] [Indexed: 11/12/2022]
Abstract
Objective. Despite electroencephalography (EEG) being a widely used neuroimaging technique with an excellent temporal resolution, in practice, the signals are heavily contaminated by artifacts masking responses of interest in an experiment. It is thus essential to guarantee a prompt and effective detection of artifacts that provides quantitative quality assessment (QA) on raw EEG data. This type of pipeline is crucial for large-scale EEG studies. However, current EEG QA studies are still limited.Approach. In this study, combined from a big data perspective, we therefore describe a quantitative signal quality assessment pipeline, a stable and general threshold-based QA pipeline that automatically integrates artifact detection and new QA measures to assess continuous resting-state raw EEG data. One simulation dataset and two resting-state EEG datasets from 42 healthy subjects and 983 clinical patients were utilized to calibrate the QA pipeline.Main Results. The results demonstrate that (1) the QA indices selected are sensitive: they almost strictly and linearly decrease as the noise level increases; (2) stable, replicable QA thresholds are valid for other experimental and clinical EEG datasets; and (3) use of the QA pipeline on these datasets reveals that high-frequency noises are the most common noises in EEG practice. The QA pipeline is also deployed in the WeBrain cloud platform (https://webrain.uestc.edu.cn/, the Chinese EEG Brain Consortium portal).Significance. These findings suggest that the proposed QA pipeline may be a stable and promising approach for quantitative EEG signal quality assessment in large-scale EEG studies.
Collapse
Affiliation(s)
- Lingling Zhao
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, People's Republic of China
| | - Yufan Zhang
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, People's Republic of China
| | - Xue Yu
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, People's Republic of China
| | - Hanxi Wu
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China
| | - Lei Wang
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China
| | - Fali Li
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,Research Unit of NeuroInformation, Chinese Academy of Medical Sciences, 2019RU035, Chengdu, People's Republic of China
| | - Mingjun Duan
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,Sichuan Institute for Brain Science and Brain-Inspired Intelligence, Chengdu 611731, People's Republic of China
| | - Yongxiu Lai
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,Research Unit of NeuroInformation, Chinese Academy of Medical Sciences, 2019RU035, Chengdu, People's Republic of China
| | - Tiejun Liu
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,Research Unit of NeuroInformation, Chinese Academy of Medical Sciences, 2019RU035, Chengdu, People's Republic of China.,Sichuan Institute for Brain Science and Brain-Inspired Intelligence, Chengdu 611731, People's Republic of China
| | - Li Dong
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,Research Unit of NeuroInformation, Chinese Academy of Medical Sciences, 2019RU035, Chengdu, People's Republic of China.,Sichuan Institute for Brain Science and Brain-Inspired Intelligence, Chengdu 611731, People's Republic of China
| | - Dezhong Yao
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.,Research Unit of NeuroInformation, Chinese Academy of Medical Sciences, 2019RU035, Chengdu, People's Republic of China.,Sichuan Institute for Brain Science and Brain-Inspired Intelligence, Chengdu 611731, People's Republic of China
| |
Collapse
|
3
|
Xiao X, Fang Y. Motor Imagery EEG Signal Recognition Using Deep Convolution Neural Network. Front Neurosci 2021; 15:655599. [PMID: 33841094 PMCID: PMC8027090 DOI: 10.3389/fnins.2021.655599] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2021] [Accepted: 03/03/2021] [Indexed: 11/21/2022] Open
Abstract
Brain computer interaction (BCI) based on EEG can help patients with limb dyskinesia to carry out daily life and rehabilitation training. However, due to the low signal-to-noise ratio and large individual differences, EEG feature extraction and classification have the problems of low accuracy and efficiency. To solve this problem, this paper proposes a recognition method of motor imagery EEG signal based on deep convolution network. This method firstly aims at the problem of low quality of EEG signal characteristic data, and uses short-time Fourier transform (STFT) and continuous Morlet wavelet transform (CMWT) to preprocess the collected experimental data sets based on time series characteristics. So as to obtain EEG signals that are distinct and have time-frequency characteristics. And based on the improved CNN network model to efficiently recognize EEG signals, to achieve high-quality EEG feature extraction and classification. Further improve the quality of EEG signal feature acquisition, and ensure the high accuracy and precision of EEG signal recognition. Finally, the proposed method is validated based on the BCI competiton dataset and laboratory measured data. Experimental results show that the accuracy of this method for EEG signal recognition is 0.9324, the precision is 0.9653, and the AUC is 0.9464. It shows good practicality and applicability.
Collapse
Affiliation(s)
- Xiongliang Xiao
- College of Electronic Science and Engineering, Hunan University of Information Technology, Changsha, China
| | - Yuee Fang
- College of Electric Power Engineering, Hunan Polytechnic of Water Resources and Electric Power, Changsha, China
| |
Collapse
|
4
|
EEG Data Quality: Determinants and Impact in a Multicenter Study of Children, Adolescents, and Adults with Attention-Deficit/Hyperactivity Disorder (ADHD). Brain Sci 2021; 11:brainsci11020214. [PMID: 33578741 PMCID: PMC7916500 DOI: 10.3390/brainsci11020214] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2020] [Revised: 01/15/2021] [Accepted: 01/22/2021] [Indexed: 11/16/2022] Open
Abstract
Electroencephalography (EEG) represents a widely established method for assessing altered and typically developing brain function. However, systematic studies on EEG data quality, its correlates, and consequences are scarce. To address this research gap, the current study focused on the percentage of artifact-free segments after standard EEG pre-processing as a data quality index. We analyzed participant-related and methodological influences, and validity by replicating landmark EEG effects. Further, effects of data quality on spectral power analyses beyond participant-related characteristics were explored. EEG data from a multicenter ADHD-cohort (age range 6 to 45 years), and a non-ADHD school-age control group were analyzed (ntotal = 305). Resting-state data during eyes open, and eyes closed conditions, and task-related data during a cued Continuous Performance Task (CPT) were collected. After pre-processing, general linear models, and stepwise regression models were fitted to the data. We found that EEG data quality was strongly related to demographic characteristics, but not to methodological factors. We were able to replicate maturational, task, and ADHD effects reported in the EEG literature, establishing a link with EEG-landmark effects. Furthermore, we showed that poor data quality significantly increases spectral power beyond effects of maturation and symptom severity. Taken together, the current results indicate that with a careful design and systematic quality control, informative large-scale multicenter trials characterizing neurophysiological mechanisms in neurodevelopmental disorders across the lifespan are feasible. Nevertheless, results are restricted to the limitations reported. Future work will clarify predictive value.
Collapse
|
6
|
Liu D, Wang Q, Zhang Y, Liu X, Lu J, Sun J. A study on quality assessment of the surface EEG signal based on fuzzy comprehensive evaluation method. Comput Assist Surg (Abingdon) 2019; 24:167-173. [PMID: 30620225 DOI: 10.1080/24699322.2018.1557888] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022] Open
Abstract
Surface EEG (Electroencephalography) signal is vulnerable to interference due to its characteristics and sampling methods. So it is of great importance to evaluate the collected EEG signal prior to use. Traditional methods usually use the impedance between skin and electrode to estimate the quality of the EEG signal, which has shortcomings such as monotonous features, high false positive rates, and poor real-time capability. Aiming at addressing these issues, this paper presents a novel model of EEG quality assessment based on Fuzzy Comprehensive Evaluation method. The developed model employs amplitude, power frequency ratio, and alpha band PSD (Power Spectral Density) ratio of resting EEG signal as evaluation factors, and performs a quantitative assessment of the signal quality. Experiments show that the proposed model can significantly determine the EEG signal quality. In addition, the model is simple in implementation with low computational complexity, and is able to present the EEG quality evaluation results in real time. Before the formal measurement, collecting short-term resting EEG data, and evaluating the EEG signal quality and current signal acquisition environment using the model, the collection efficiency of qualified EEG signals can be greatly improved.
Collapse
Affiliation(s)
- Dan Liu
- School of Electrical Engineering & Automation, Harbin Institute of Technology , Harbin , China
| | - Qisong Wang
- School of Electrical Engineering & Automation, Harbin Institute of Technology , Harbin , China
| | - Yan Zhang
- School of Electrical Engineering & Automation, Harbin Institute of Technology , Harbin , China
| | - Xin Liu
- School of Transportation Science and Engineering, Harbin Institute of Technology , Harbin , China
| | - Jingyang Lu
- Intelligent Fusion Technology, Inc. , Germantown , MD , USA
| | - Jinwei Sun
- School of Electrical Engineering & Automation, Harbin Institute of Technology , Harbin , China
| |
Collapse
|
8
|
A fresh look at functional link neural network for motor imagery-based brain-computer interface. J Neurosci Methods 2018; 305:28-35. [PMID: 29733940 DOI: 10.1016/j.jneumeth.2018.05.001] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2017] [Revised: 04/18/2018] [Accepted: 05/03/2018] [Indexed: 11/24/2022]
Abstract
BACKGROUND Artificial neural networks (ANNs) are one of the widely used classifiers in the brain-computer interface (BCI) systems-based on noninvasive electroencephalography (EEG) signals. Among the different ANN architectures, the most commonly applied for BCI classifiers is the multilayer perceptron (MLP). When appropriately designed with optimal number of neuron layers and number of neurons per layer, the ANN can act as a universal approximator. However, due to the low signal-to-noise ratio of EEG signal data, overtraining problem may become an inherent issue, causing these universal approximators to fail in real-time applications. NEW METHOD In this study we introduce a higher order neural network, namely the functional link neural network (FLNN) as a classifier for motor imagery (MI)-based BCI systems, to remedy the drawbacks in MLP. RESULTS We compare the proposed method with competing classifiers such as linear decomposition analysis, naïve Bayes, k-nearest neighbours, support vector machine and three MLP architectures. Two multi-class benchmark datasets from the BCI competitions are used. Common spatial pattern algorithm is utilized for feature extraction to build classification models. COMPARISON WITH EXISTING METHOD(S) FLNN reports the highest average Kappa value over multiple subjects for both the BCI competition datasets, under similarly preprocessed data and extracted features. Further, statistical comparison results over multiple subjects show that the proposed FLNN classification method yields the best performance among the competing classifiers. CONCLUSIONS Findings from this study imply that the proposed method, which has less computational complexity compared to the MLP, can be implemented effectively in practical MI-based BCI systems.
Collapse
|