1
|
Zhao W, Wang WF, Patnaik LM, Zhang BC, Weng SJ, Xiao SX, Wei DZ, Zhou HF. Residual and bidirectional LSTM for epileptic seizure detection. Front Comput Neurosci 2024; 18:1415967. [PMID: 38952709 PMCID: PMC11215953 DOI: 10.3389/fncom.2024.1415967] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2024] [Accepted: 05/28/2024] [Indexed: 07/03/2024] Open
Abstract
Electroencephalogram (EEG) plays a pivotal role in the detection and analysis of epileptic seizures, which affects over 70 million people in the world. Nonetheless, the visual interpretation of EEG signals for epilepsy detection is laborious and time-consuming. To tackle this open challenge, we introduce a straightforward yet efficient hybrid deep learning approach, named ResBiLSTM, for detecting epileptic seizures using EEG signals. Firstly, a one-dimensional residual neural network (ResNet) is tailored to adeptly extract the local spatial features of EEG signals. Subsequently, the acquired features are input into a bidirectional long short-term memory (BiLSTM) layer to model temporal dependencies. These output features are further processed through two fully connected layers to achieve the final epileptic seizure detection. The performance of ResBiLSTM is assessed on the epileptic seizure datasets provided by the University of Bonn and Temple University Hospital (TUH). The ResBiLSTM model achieves epileptic seizure detection accuracy rates of 98.88-100% in binary and ternary classifications on the Bonn dataset. Experimental outcomes for seizure recognition across seven epilepsy seizure types on the TUH seizure corpus (TUSZ) dataset indicate that the ResBiLSTM model attains a classification accuracy of 95.03% and a weighted F1 score of 95.03% with 10-fold cross-validation. These findings illustrate that ResBiLSTM outperforms several recent deep learning state-of-the-art approaches.
Collapse
Affiliation(s)
- Wei Zhao
- Chengyi College, Jimei University, Xiamen, China
| | - Wen-Feng Wang
- Shanghai Institute of Technology, Shanghai, China
- London Institute of Technology, International Academy of Visual Arts and Engineering, London, United Kingdom
| | | | | | - Su-Jun Weng
- Chengyi College, Jimei University, Xiamen, China
| | | | - De-Zhi Wei
- Chengyi College, Jimei University, Xiamen, China
| | - Hai-Feng Zhou
- Marine Engineering Institute, Jimei University, Xiamen, China
| |
Collapse
|
2
|
Antonoudiou P, Basu T, Maguire J. Semi-automated seizure detection using interpretable machine learning models. RESEARCH SQUARE 2024:rs.3.rs-4361048. [PMID: 38854086 PMCID: PMC11160878 DOI: 10.21203/rs.3.rs-4361048/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2024]
Abstract
Despite the vast number of seizure detection publications there are no validated open-source tools for automating seizure detection based on electrographic recordings. Researchers instead rely on manual curation of seizure detection that is highly laborious, inefficient, error prone, and heavily biased. Here we developed an open-source software called SeizyML that uses sensitive machine learning models coupled with manual validation of detected events reducing bias and promoting efficient and accurate detection of electrographic seizures. We compared the validity of four interpretable machine learning models (decision tree, gaussian naïve bayes, passive aggressive classifier, and stochastic gradient descent classifier) on an extensive electrographic seizure dataset that we collected from chronically epileptic mice. We find that the gaussian naïve bayes and stochastic gradient descent models achieved the highest precision and f1 scores, while also detecting all seizures in our mouse dataset and only require a small amount of data to train the model and achieve good performance. Further, we demonstrate the utility of this approach to detect electrographic seizures in a human EEG dataset. This approach has the potential to be a transformative research tool overcoming the analysis bottleneck that slows research progress.
Collapse
|
3
|
Yuan Z, Zhou Q, Wang B, Zhang Q, Yang Y, Zhao Y, Guo Y, Zhou J, Wang C. PSAEEGNet: pyramid squeeze attention mechanism-based CNN for single-trial EEG classification in RSVP task. Front Hum Neurosci 2024; 18:1385360. [PMID: 38756843 PMCID: PMC11097777 DOI: 10.3389/fnhum.2024.1385360] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2024] [Accepted: 04/08/2024] [Indexed: 05/18/2024] Open
Abstract
Introduction Accurate classification of single-trial electroencephalogram (EEG) is crucial for EEG-based target image recognition in rapid serial visual presentation (RSVP) tasks. P300 is an important component of a single-trial EEG for RSVP tasks. However, single-trial EEG are usually characterized by low signal-to-noise ratio and limited sample sizes. Methods Given these challenges, it is necessary to optimize existing convolutional neural networks (CNNs) to improve the performance of P300 classification. The proposed CNN model called PSAEEGNet, integrates standard convolutional layers, pyramid squeeze attention (PSA) modules, and deep convolutional layers. This approach arises the extraction of temporal and spatial features of the P300 to a finer granularity level. Results Compared with several existing single-trial EEG classification methods for RSVP tasks, the proposed model shows significantly improved performance. The mean true positive rate for PSAEEGNet is 0.7949, and the mean area under the receiver operating characteristic curve (AUC) is 0.9341 (p < 0.05). Discussion These results suggest that the proposed model effectively extracts features from both temporal and spatial dimensions of P300, leading to a more accurate classification of single-trial EEG during RSVP tasks. Therefore, this model has the potential to significantly enhance the performance of target recognition systems based on EEG, contributing to the advancement and practical implementation of target recognition in this field.
Collapse
Affiliation(s)
- Zijian Yuan
- School of Intelligent Medicine and Biotechnology, Guilin Medical University, Guangxi, China
- Beijing Institute of Basic Medical Sciences, Beijing, China
| | - Qian Zhou
- Beijing Institute of Basic Medical Sciences, Beijing, China
| | - Baozeng Wang
- Beijing Institute of Basic Medical Sciences, Beijing, China
| | - Qi Zhang
- Beijing Institute of Basic Medical Sciences, Beijing, China
| | - Yang Yang
- Beijing Institute of Basic Medical Sciences, Beijing, China
| | - Yuwei Zhao
- Beijing Institute of Basic Medical Sciences, Beijing, China
| | - Yong Guo
- School of Intelligent Medicine and Biotechnology, Guilin Medical University, Guangxi, China
| | - Jin Zhou
- Beijing Institute of Basic Medical Sciences, Beijing, China
- Chinese Institute for Brain Research, Beijing, China
| | - Changyong Wang
- Beijing Institute of Basic Medical Sciences, Beijing, China
| |
Collapse
|
4
|
Fussner S, Boyne A, Han A, Nakhleh LA, Haneef Z. Differentiating Epileptic and Psychogenic Non-Epileptic Seizures Using Machine Learning Analysis of EEG Plot Images. SENSORS (BASEL, SWITZERLAND) 2024; 24:2823. [PMID: 38732929 PMCID: PMC11086151 DOI: 10.3390/s24092823] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/29/2024] [Revised: 04/22/2024] [Accepted: 04/28/2024] [Indexed: 05/13/2024]
Abstract
The treatment of epilepsy, the second most common chronic neurological disorder, is often complicated by the failure of patients to respond to medication. Treatment failure with anti-seizure medications is often due to the presence of non-epileptic seizures. Distinguishing non-epileptic from epileptic seizures requires an expensive and time-consuming analysis of electroencephalograms (EEGs) recorded in an epilepsy monitoring unit. Machine learning algorithms have been used to detect seizures from EEG, typically using EEG waveform analysis. We employed an alternative approach, using a convolutional neural network (CNN) with transfer learning using MobileNetV2 to emulate the real-world visual analysis of EEG images by epileptologists. A total of 5359 EEG waveform plot images from 107 adult subjects across two epilepsy monitoring units in separate medical facilities were divided into epileptic and non-epileptic groups for training and cross-validation of the CNN. The model achieved an accuracy of 86.9% (Area Under the Curve, AUC 0.92) at the site where training data were extracted and an accuracy of 87.3% (AUC 0.94) at the other site whose data were only used for validation. This investigation demonstrates the high accuracy achievable with CNN analysis of EEG plot images and the robustness of this approach across EEG visualization software, laying the groundwork for further subclassification of seizures using similar approaches in a clinical setting.
Collapse
Affiliation(s)
- Steven Fussner
- Department of Neurology, Baylor College of Medicine, Houston, TX 77030, USA
| | - Aidan Boyne
- Undergraduate Medical Education, Baylor College of Medicine, Houston, TX 77030, USA
| | - Albert Han
- Undergraduate Medical Education, Baylor College of Medicine, Houston, TX 77030, USA
| | - Lauren A. Nakhleh
- Undergraduate Medical Education, Baylor College of Medicine, Houston, TX 77030, USA
| | - Zulfi Haneef
- Department of Neurology, Baylor College of Medicine, Houston, TX 77030, USA
- Neurology Care Line, Michael E. DeBakey VA Medical Center, Houston, TX 77030, USA
| |
Collapse
|
5
|
Guo Z, Wang J, Jing T, Fu L. Investigating the interpretability of schizophrenia EEG mechanism through a 3DCNN-based hidden layer features aggregation framework. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 247:108105. [PMID: 38447316 DOI: 10.1016/j.cmpb.2024.108105] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Revised: 02/07/2024] [Accepted: 02/26/2024] [Indexed: 03/08/2024]
Abstract
BACKGROUND AND OBJECTIVE Electroencephalogram (EEG) signals record brain activity, with growing interest in quantifying neural activity through complexity analysis as a potential biological marker for schizophrenia. Presently, EEG complexity analysis primarily relies on manual feature extraction, which is subjective and yields varied findings in studies involving schizophrenia and healthy controls. METHODS This study aims to leverage deep learning methods for enhanced EEG complexity exploration, aiding early schizophrenia screening and diagnosis. Our proposed approach utilizes a three-dimensional Convolutional Neural Network (3DCNN) to extract enhanced data features for early schizophrenia identification and subsequent complexity analysis. Leveraging the spatiotemporal capabilities of 3DCNN, we extract advanced latent features and employ knowledge distillation to reintegrate these features into the original channels, creating feature-enhanced data. RESULTS We employ a 10-fold cross-validation strategy, achieving the average accuracies of 99.46% and 98.06% in subject-dependent experiments on Dataset 1(14SZ and 14HC) and Dataset 2 (45SZ and 39HC). The average accuracy for subject-independent is 96.04% and 92.67% on both datasets. Feature extraction and classification are conducted on both the re-aggregated data and the original data. Our results demonstrate that re-aggregated data exhibit superior classification performance and a more stable training process after feature extraction. In the complexity analysis of re-aggregated data, we observe lower entropy features in schizophrenic patients compared to healthy controls, with more pronounced differences in the temporal and frontal lobes. Analyzing Katz's Fractal Dimension (KFD) across three sub-bands of lobe channels reveals the lowest α band KFD value in schizophrenia patients. CONCLUSIONS This emphasizes the ability of our method to enhance the discrimination and interpretability in schizophrenia detection and analysis. Our approach enhances the potential for EEG-based schizophrenia diagnosis by leveraging deep learning, offering superior discrimination capabilities and richer interpretive insights.
Collapse
Affiliation(s)
- Zhifen Guo
- College of Information Science and Engineering, Northeastern University, Shenyang, China.
| | - Jiao Wang
- College of Information Science and Engineering, Northeastern University, Shenyang, China.
| | - Tianyu Jing
- College of Information Science and Engineering, Northeastern University, Shenyang, China.
| | - Longyue Fu
- College of Information Science and Engineering, Northeastern University, Shenyang, China.
| |
Collapse
|
6
|
Yoo S, Kim M, Choi C, Kim DH, Cha GD. Soft Bioelectronics for Neuroengineering: New Horizons in the Treatment of Brain Tumor and Epilepsy. Adv Healthc Mater 2023:e2303563. [PMID: 38117136 DOI: 10.1002/adhm.202303563] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2023] [Revised: 11/23/2023] [Indexed: 12/21/2023]
Abstract
Soft bioelectronic technologies for neuroengineering have shown remarkable progress, which include novel soft material technologies and device design strategies. Such technological advances that are initiated from fundamental brain science are applied to clinical neuroscience and provided meaningful promises for significant improvement in the diagnosis efficiency and therapeutic efficacy of various brain diseases recently. System-level integration strategies in consideration of specific disease circumstances can enhance treatment effects further. Here, recent advances in soft implantable bioelectronics for neuroengineering, focusing on materials and device designs optimized for the treatment of intracranial disease environments, are reviewed. Various types of soft bioelectronics for neuroengineering are categorized and exemplified first, and then details for the sensing and stimulating device components are explained. Next, application examples of soft implantable bioelectronics to clinical neuroscience, particularly focusing on the treatment of brain tumor and epilepsy are reviewed. Finally, an ideal system of soft intracranial bioelectronics such as closed-loop-type fully-integrated systems is presented, and the remaining challenges for their clinical translation are discussed.
Collapse
Affiliation(s)
- Seungwon Yoo
- Center for Nanoparticle Research, Institute for Basic Science (IBS), Seoul, 08826, Republic of Korea
- School of Chemical and Biological Engineering, Institute of Chemical Processes, Seoul National University, Seoul, 08826, Republic of Korea
| | - Minjeong Kim
- Center for Nanoparticle Research, Institute for Basic Science (IBS), Seoul, 08826, Republic of Korea
- School of Chemical and Biological Engineering, Institute of Chemical Processes, Seoul National University, Seoul, 08826, Republic of Korea
| | - Changsoon Choi
- Center for Opto-Electronic Materials and Devices, Post-silicon Semiconductor Institute, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea
| | - Dae-Hyeong Kim
- Center for Nanoparticle Research, Institute for Basic Science (IBS), Seoul, 08826, Republic of Korea
- School of Chemical and Biological Engineering, Institute of Chemical Processes, Seoul National University, Seoul, 08826, Republic of Korea
- Department of Materials Science and Engineering, Seoul National University, Seoul, 08826, Republic of Korea
| | - Gi Doo Cha
- Department of Systems Biotechnology, Chung-Ang University, Anseong-si, Gyeonggi-do, 17546, Republic of Korea
| |
Collapse
|
7
|
Briden M, Norouzi N. Toward metacognition: subject-aware contrastive deep fusion representation learning for EEG analysis. BIOLOGICAL CYBERNETICS 2023; 117:363-372. [PMID: 37402000 PMCID: PMC10600301 DOI: 10.1007/s00422-023-00967-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/30/2022] [Accepted: 05/26/2023] [Indexed: 07/05/2023]
Abstract
We propose a subject-aware contrastive learning deep fusion neural network framework for effectively classifying subjects' confidence levels in the perception of visual stimuli. The framework, called WaveFusion, is composed of lightweight convolutional neural networks for per-lead time-frequency analysis and an attention network for integrating the lightweight modalities for final prediction. To facilitate the training of WaveFusion, we incorporate a subject-aware contrastive learning approach by taking advantage of the heterogeneity within a multi-subject electroencephalogram dataset to boost representation learning and classification accuracy. The WaveFusion framework demonstrates high accuracy in classifying confidence levels by achieving a classification accuracy of 95.7% while also identifying influential brain regions.
Collapse
Affiliation(s)
- Michael Briden
- Baskin Engineering, UC Santa Cruz, 1156 High Street, Santa Cruz, CA 95064 USA
| | - Narges Norouzi
- Electrical Engineering and Computer Sciences Department, UC Berkeley, Soda Hall, Berkeley, CA 94709 USA
| |
Collapse
|
8
|
Molnár L, Ferando I, Liu B, Mokhtar P, Domokos J, Mody I. Capturing the power of seizures: an empirical mode decomposition analysis of epileptic activity in the mouse hippocampus. Front Mol Neurosci 2023; 16:1121479. [PMID: 37256078 PMCID: PMC10225690 DOI: 10.3389/fnmol.2023.1121479] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2022] [Accepted: 04/28/2023] [Indexed: 06/01/2023] Open
Abstract
Introduction Various methods have been used to determine the frequency components of seizures in scalp electroencephalography (EEG) and in intracortical recordings. Most of these methods rely on subjective or trial-and-error criteria for choosing the appropriate bandwidth for filtering the EEG or local field potential (LFP) signals to establish the frequency components that contribute most to the initiation and maintenance of seizure activity. The empirical mode decomposition (EMD) with the Hilbert-Huang transform is an unbiased method to decompose a time and frequency variant signal into its component non-stationary frequencies. The resulting components, i.e., the intrinsic mode functions (IMFs) objectively reflect the various non-stationary frequencies making up the original signal. Materials and methods We employed the EMD method to analyze the frequency components and relative power of spontaneous electrographic seizures recorded in the dentate gyri of mice during the epileptogenic period. Epilepsy was induced in mice following status epilepticus induced by suprahippocampal injection of kainic acid. The seizures were recorded as local field potentials (LFP) with electrodes implanted in the dentate gyrus. We analyzed recording segments that included a seizure (mean duration 28 s) and an equivalent time period both before and after the seizure. Each segment was divided into non-overlapping 1 s long epochs which were then analyzed to obtain their IMFs (usually 8-10), the center frequencies of the respective IMF and their spectral root-mean-squared (RMS) power. Results Our analysis yielded unbiased identification of the spectral components of seizures, and the relative power of these components during this pathological brain activity. During seizures, the power of the mid frequency components increased while the center frequency of the first IMF (with the highest frequency) dramatically decreased, providing mechanistic insights into how local seizures are generated. Discussion We expect this type of analysis to provide further insights into the mechanisms of seizure generation and potentially better seizure detection.
Collapse
Affiliation(s)
- László Molnár
- Department of Electrical Engineering, Sapientia Hungarian University of Transylvania, Târgu-Mures, Romania
| | - Isabella Ferando
- Department of Neurology, The David Geffen School of Medicine at UCLA, Los Angeles, CA, United States
- Department of Neurology, School of Medicine at University of Florida, Miami, FL, United States
| | - Benjamin Liu
- Department of Neurology, The David Geffen School of Medicine at UCLA, Los Angeles, CA, United States
| | - Parsa Mokhtar
- Department of Neurology, The David Geffen School of Medicine at UCLA, Los Angeles, CA, United States
| | - József Domokos
- Department of Electrical Engineering, Sapientia Hungarian University of Transylvania, Târgu-Mures, Romania
| | - Istvan Mody
- Department of Neurology, The David Geffen School of Medicine at UCLA, Los Angeles, CA, United States
| |
Collapse
|
9
|
Ein Shoka AA, Dessouky MM, El-Sayed A, Hemdan EED. EEG seizure detection: concepts, techniques, challenges, and future trends. MULTIMEDIA TOOLS AND APPLICATIONS 2023:1-31. [PMID: 37362745 PMCID: PMC10071471 DOI: 10.1007/s11042-023-15052-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Revised: 08/07/2022] [Accepted: 02/27/2023] [Indexed: 06/28/2023]
Abstract
A central nervous system disorder is usually referred to as epilepsy. In epilepsy brain activity becomes abnormal, leading to times of abnormal behavior or seizures, and at times loss of awareness. Consequently, epilepsy patients face problems in daily life due to precautions they must take to adapt to this condition, particularly when they use heavy equipment, e.g., vehicle derivation. Epilepsy studies rely primarily on electroencephalography (EEG) signals to evaluate brain activity during seizures. It is troublesome and time-consuming to manually decide the location of seizures in EEG signals. The automatic detection framework is one of the principal tools to help doctors and patients take appropriate precautions. This paper reviews the epilepsy mentality disorder and the types of seizure, preprocessing operations that are performed on EEG data, a generally extracted feature from the signal, and a detailed view on classification procedures used in this problem and provide insights on the difficulties and future research directions in this innovative theme. Therefore, this paper presents a review of work on recent methods for the epileptic seizure process along with providing perspectives and concepts to researchers to present an automated EEG-based epileptic seizure detection system using IoT and machine learning classifiers for remote patient monitoring in the context of smart healthcare systems. Finally, challenges and open research points in EEG seizure detection are investigated.
Collapse
Affiliation(s)
- Athar A. Ein Shoka
- Faculty of Electronic Engineering, Computer Science and Engineering Department, Menoufia University, Menouf, Egypt
| | - Mohamed M. Dessouky
- Faculty of Electronic Engineering, Computer Science and Engineering Department, Menoufia University, Menouf, Egypt
- Department of Computer Science & Artificial Intelligence, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia
| | - Ayman El-Sayed
- Faculty of Electronic Engineering, Computer Science and Engineering Department, Menoufia University, Menouf, Egypt
| | - Ezz El-Din Hemdan
- Faculty of Electronic Engineering, Computer Science and Engineering Department, Menoufia University, Menouf, Egypt
| |
Collapse
|
10
|
Khare SK, Bajaj V, Acharya UR. SchizoNET: a robust and accurate Margenau-Hill time-frequency distribution based deep neural network model for schizophrenia detection using EEG signals. Physiol Meas 2023; 44. [PMID: 36787641 DOI: 10.1088/1361-6579/acbc06] [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: 10/12/2022] [Accepted: 02/14/2023] [Indexed: 02/16/2023]
Abstract
Objective.Schizophrenia (SZ) is a severe chronic illness characterized by delusions, cognitive dysfunctions, and hallucinations that impact feelings, behaviour, and thinking. Timely detection and treatment of SZ are necessary to avoid long-term consequences. Electroencephalogram (EEG) signals are one form of a biomarker that can reveal hidden changes in the brain during SZ. However, the EEG signals are non-stationary in nature with low amplitude. Therefore, extracting the hidden information from the EEG signals is challenging.Approach.The time-frequency domain is crucial for the automatic detection of SZ. Therefore, this paper presents the SchizoNET model combining the Margenau-Hill time-frequency distribution (MH-TFD) and convolutional neural network (CNN). The instantaneous information of EEG signals is captured in the time-frequency domain using MH-TFD. The time-frequency amplitude is converted to two-dimensional plots and fed to the developed CNN model.Results.The SchizoNET model is developed using three different validation techniques, including holdout, five-fold cross-validation, and ten-fold cross-validation techniques using three separate public SZ datasets (Dataset 1, 2, and 3). The proposed model achieved an accuracy of 97.4%, 99.74%, and 96.35% on Dataset 1 (adolescents: 45 SZ and 39 HC subjects), Dataset 2 (adults: 14 SZ and 14 HC subjects), and Dataset 3 (adults: 49 SZ and 32 HC subjects), respectively. We have also evaluated six performance parameters and the area under the curve to evaluate the performance of our developed model.Significance.The SchizoNET is robust, effective, and accurate, as it performed better than the state-of-the-art techniques. To the best of our knowledge, this is the first work to explore three publicly available EEG datasets for the automated detection of SZ. Our SchizoNET model can help neurologists detect the SZ in various scenarios.
Collapse
Affiliation(s)
- Smith K Khare
- Electrical and Computer Engineering Department, Aarhus University, Denmark
| | - Varun Bajaj
- Discipline of Electronics and Communication Engineering, Indian Institute of Information Technology, Design, and Manufacturing (IIITDM) Jabalpur, India
| | - U Rajendra Acharya
- School of Mathematics, Physics, and Computing, University of Southern Queensland, Springfield, Australia.,Department of Biomedical Engineering, School of Science and Technology, University of Social Sciences, Singapore.,Department of Biomedical Informatics and Medical Engineering, Asia University, Taiwan.,Distinguished Professor, Kumamoto University, Japan.,Adjunct Professor, University of Malaya, Malaysia
| |
Collapse
|
11
|
XAI4EEG: spectral and spatio-temporal explanation of deep learning-based seizure detection in EEG time series. Neural Comput Appl 2022. [DOI: 10.1007/s00521-022-07809-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2022]
Abstract
AbstractIn clinical practice, algorithmic predictions may seriously jeopardise patients’ health and thus are required to be validated by medical experts before a final clinical decision is met. Towards that aim, there is need to incorporate explainable artificial intelligence techniques into medical research. In the specific field of epileptic seizure detection there are several machine learning algorithms but less methods on explaining them in an interpretable way. Therefore, we introduce XAI4EEG: an application-aware approach for an explainable and hybrid deep learning-based detection of seizures in multivariate EEG time series. In XAI4EEG, we combine deep learning models and domain knowledge on seizure detection, namely (a) frequency bands, (b) location of EEG leads and (c) temporal characteristics. XAI4EEG encompasses EEG data preparation, two deep learning models and our proposed explanation module visualizing feature contributions that are obtained by two SHAP explainers, each explaining the predictions of one of the two models. The resulting visual explanations provide an intuitive identification of decision-relevant regions in the spectral, spatial and temporal EEG dimensions. To evaluate XAI4EEG, we conducted a user study, where users were asked to assess the outputs of XAI4EEG, while working under time constraints, in order to emulate the fact that clinical diagnosis is done - more often than not - under time pressure. We found that the visualizations of our explanation module (1) lead to a substantially lower time for validating the predictions and (2) leverage an increase in interpretability, trust and confidence compared to selected SHAP feature contribution plots.
Collapse
|
12
|
Ray J, Wijesekera L, Cirstea S. Machine learning and clinical neurophysiology. J Neurol 2022; 269:6678-6684. [PMID: 35907045 DOI: 10.1007/s00415-022-11283-9] [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: 06/13/2022] [Revised: 07/05/2022] [Accepted: 07/09/2022] [Indexed: 11/29/2022]
Abstract
Clinical neurophysiology constructs a wealth of dynamic information pertaining to the integrity and function of both central and peripheral nervous systems. As with many technological fields, there has been an explosion of data in neurophysiology over recent years, and this requires considerable analysis by experts. Computational algorithms and especially advances in machine learning (ML) have the ability to assist with this task and potentially reveal hidden insights. In this update article, we will provide a brief overview where such technology is being applied in clinical neurophysiology and possible future directions.
Collapse
Affiliation(s)
- Julian Ray
- Department of Clinical Neurophysiology, Addenbrooke's Hospital, Cambridge University Hospitals Neurosciences, Cambridge, UK.
| | - Lokesh Wijesekera
- Department of Clinical Neurophysiology, Addenbrooke's Hospital, Cambridge University Hospitals Neurosciences, Cambridge, UK
| | - Silvia Cirstea
- Department of Clinical Neurophysiology, Addenbrooke's Hospital, Cambridge University Hospitals Neurosciences, Cambridge, UK
| |
Collapse
|
13
|
Song Z, Deng B, Wang J, Yi G. An EEG-based systematic explainable detection framework for probing and localizing abnormal patterns in Alzheimer's disease. J Neural Eng 2022; 19. [PMID: 35453136 DOI: 10.1088/1741-2552/ac697d] [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: 11/15/2021] [Accepted: 04/22/2022] [Indexed: 11/12/2022]
Abstract
OBJECTIVE Electroencephalography (EEG) is a potential source of downstream biomarkers for the early diagnosis of Alzheimer's disease (AD) due to its low-cost, non-invasive, and portable advantages. Accurately detecting AD-induced patterns from EEG signals is essential for understanding AD-related neurodegeneration at the EEG level and further evaluating the risk of AD at an early stage. This paper proposes a deep learning-based, functional explanatory framework that probes AD abnormalities from short-sequence EEG data. APPROACH The framework is a learning-based automatic detection system consisting of three encoding pathways that analyze EEG signals in frequency, complexity, and synchronous domains. We integrated the proposed EEG descriptors with the neural network components into one learning system to detect AD patterns. A transfer learning-based model was used to learn the deep representations, and a modified generative adversarial module was attached to the model to overcome feature sparsity. Furthermore, we utilized activation mapping to obtain the AD-related neurodegeneration at brain rhythm, dynamic complexity, and functional connectivity levels. MAIN RESULTS The proposed framework can accurately (100%) detect AD patterns based on our raw EEG recordings without delicate preprocessing. Meanwhile, the system indicates that 1) the power of different brain rhythms exhibits abnormal in the frontal lobes of AD patients, and such abnormality spreads to central lobes in the alpha and beta rhythms, 2) the difference in nonlinear complexity varies with the temporal scales, and 3) all the connections of pair-wise brain regions except bilateral temporal connectivity are weak in AD patterns. The proposed method outperforms other related methods in detection performance. SIGNIFICANCE We provide a new method for revealing abnormalities and corresponding localizations in different feature domains of EEG from AD patients. This study is a significant foundation for our future work on identifying individuals at high risk of AD at an early stage.
Collapse
Affiliation(s)
- Zhenxi Song
- Tianjin University, No.92 Weijin Road, Nankai District, Tianjin 300072, China, Tianjin, 300072, CHINA
| | - Bin Deng
- Tianjin University, No.92 Weijin Road, Nankai District, Tianjin 300072, China, Tianjin, Tianjin, 300072, CHINA
| | - Jiang Wang
- School of Electrical Engineering and Automation, Tianjin University, No.92 Weijin Road, Nankai District, Tianjin 300072, China, P. R. China, Tianjin, Tianjin, 300072, CHINA
| | - Guosheng Yi
- School of Electrical and Information Engineering, Tianjin University, No.92 Weijin Road, Nankai District, Tianjin 300072, China, Tianjin, Tianjin, 300072, CHINA
| |
Collapse
|
14
|
Yang CY, Huang YZ. Parkinson’s Disease Classification Using Machine Learning Approaches and Resting-State EEG. J Med Biol Eng 2022. [DOI: 10.1007/s40846-022-00695-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
15
|
Hussain H, Tamizharasan PS, Rahul CS. Design possibilities and challenges of DNN models: a review on the perspective of end devices. Artif Intell Rev 2022. [DOI: 10.1007/s10462-022-10138-z] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/03/2023]
|
16
|
Cherian R, Kanaga EG. Theoretical and Methodological Analysis of EEG based Seizure Detection and Prediction: An Exhaustive Review. J Neurosci Methods 2022; 369:109483. [DOI: 10.1016/j.jneumeth.2022.109483] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2021] [Revised: 01/13/2022] [Accepted: 01/13/2022] [Indexed: 02/07/2023]
|
17
|
Salafian B, Fishel Ben E, Shlezinger N, de Ribaupierre S, Farsad N. Efficient Epileptic Seizure Detection Using CNN-Aided Factor Graphs. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021; 2021:424-429. [PMID: 34891324 DOI: 10.1109/embc46164.2021.9629917] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
We propose a computationally efficient algorithm for seizure detection. Instead of using a purely data-driven approach, we develop a hybrid model-based/data-driven method, combining convolutional neural networks with factor graph inference. On the CHB-MIT dataset, we demonstrate that the proposed method can generalize well in a 6 fold leave-4-patient-out evaluation. Moreover, it is shown that our algorithm can achieve as much as 5% absolute improvement in performance compared to previous data-driven methods. This is achieved while the computational complexity of the proposed technique is a fraction of the complexity of prior work, making it suitable for real-time seizure detection.
Collapse
|
18
|
Roig PJ, Alcaraz S, Gilly K, Bernad C, Juiz C. Modeling of a Generic Edge Computing Application Design. SENSORS 2021; 21:s21217276. [PMID: 34770582 PMCID: PMC8587040 DOI: 10.3390/s21217276] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/30/2021] [Revised: 10/25/2021] [Accepted: 10/27/2021] [Indexed: 12/29/2022]
Abstract
Edge computing applications leverage advances in edge computing along with the latest trends of convolutional neural networks in order to achieve ultra-low latency, high-speed processing, low-power consumptions scenarios, which are necessary for deploying real-time Internet of Things deployments efficiently. As the importance of such scenarios is growing by the day, we propose to undertake two different kind of models, such as an algebraic models, with a process algebra called ACP and a coding model with a modeling language called Promela. Both approaches have been used to build models considering an edge infrastructure with a cloud backup, which has been further extended with the addition of extra fog nodes, and after having applied the proper verification techniques, they have all been duly verified. Specifically, a generic edge computing design has been specified in an algebraic manner with ACP, being followed by its corresponding algebraic verification, whereas it has also been specified by means of Promela code, which has been verified by means of the model checker Spin.
Collapse
Affiliation(s)
- Pedro Juan Roig
- Computer Engineering Department, Miguel Hernández University, 03202 Elche, Spain; (S.A.); (C.B.)
- Correspondence: (P.J.R.); (K.G.); Tel.: +34-966658388 (P.J.R.); +34-966658565 (K.G.)
| | - Salvador Alcaraz
- Computer Engineering Department, Miguel Hernández University, 03202 Elche, Spain; (S.A.); (C.B.)
| | - Katja Gilly
- Computer Engineering Department, Miguel Hernández University, 03202 Elche, Spain; (S.A.); (C.B.)
- Correspondence: (P.J.R.); (K.G.); Tel.: +34-966658388 (P.J.R.); +34-966658565 (K.G.)
| | - Cristina Bernad
- Computer Engineering Department, Miguel Hernández University, 03202 Elche, Spain; (S.A.); (C.B.)
| | - Carlos Juiz
- Mathematics and Computer Science Department, University of the Balearic Islands, 07022 Palma de Mallorca, Spain;
| |
Collapse
|
19
|
Shankar A, Dandapat S, Barma S. Seizure Type Classification Using EEG Based on Gramian Angular Field Transformation and Deep Learning. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021; 2021:3340-3343. [PMID: 34891955 DOI: 10.1109/embc46164.2021.9629791] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
classification of seizure types plays a crucial role in diagnosis and prognosis of epileptic patients which has not been addressed properly, while most of the works are surrounded by seizure detection only. However, in recent times, few works have been attempted on the classification of seizure types using deep learning (DL). In this work, a novel approach based on DL has been proposed to classify four types of seizures - complex partial seizure, generalized non-specific seizure, simple partial seizure, tonic-clonic seizure, and seizure-free. Certainly, one of the most efficient classes of DL, convolution neural network (CNN) has achieved exemplary success in the field of image recognition. Therefore, CNN has been employed to perform both automatic feature extraction and classification tasks after generating 2D images from 1D electroencephalogram (EEG) signal by employing an efficient technique, called gramian angular summation field. Next, these images fed into CNN to perform binary and multiclass classification tasks. For experimental evaluation, the Temple University Hospital (TUH, v1.5.2) EEG dataset has been taken into consideration. The proposed method has achieved classification accuracy for binary and multiclass - 3, 4, and 5 up to 96.01%, 89.91%, 84.19%, and 84.20% respectively. The results display the potentiality of the proposed method in seizure type classification.Clinical relevance-gramian angular summation field, seizure types, convolution neural network.
Collapse
|
20
|
Saminu S, Xu G, Shuai Z, Abd El Kader I, Jabire AH, Ahmed YK, Karaye IA, Ahmad IS. A Recent Investigation on Detection and Classification of Epileptic Seizure Techniques Using EEG Signal. Brain Sci 2021; 11:668. [PMID: 34065473 PMCID: PMC8160878 DOI: 10.3390/brainsci11050668] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2021] [Revised: 05/14/2021] [Accepted: 05/16/2021] [Indexed: 02/07/2023] Open
Abstract
The benefits of early detection and classification of epileptic seizures in analysis, monitoring and diagnosis for the realization and actualization of computer-aided devices and recent internet of medical things (IoMT) devices can never be overemphasized. The success of these applications largely depends on the accuracy of the detection and classification techniques employed. Several methods have been investigated, proposed and developed over the years. This paper investigates various seizure detection algorithms and classifications in the last decade, including conventional techniques and recent deep learning algorithms. It also discusses epileptiform detection as one of the steps towards advanced diagnoses of disorders of consciousness (DOCs) and their understanding. A performance comparison was carried out on the different algorithms investigated, and their advantages and disadvantages were explored. From our survey, much attention has recently been paid to exploring the efficacy of deep learning algorithms in seizure detection and classification, which are employed in other areas such as image processing and classification. Hybrid deep learning has also been explored, with CNN-RNN being the most popular.
Collapse
Affiliation(s)
- Sani Saminu
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China; (Z.S.); (I.A.E.K.); (I.A.K.); (I.S.A.)
- Biomedical Engineering Department, University of Ilorin, P.M.B 1515, Ilorin 240003, Nigeria;
| | - Guizhi Xu
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China; (Z.S.); (I.A.E.K.); (I.A.K.); (I.S.A.)
| | - Zhang Shuai
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China; (Z.S.); (I.A.E.K.); (I.A.K.); (I.S.A.)
| | - Isselmou Abd El Kader
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China; (Z.S.); (I.A.E.K.); (I.A.K.); (I.S.A.)
| | - Adamu Halilu Jabire
- Department of Electrical and Electronics Engineering, Taraba State University, Jalingo 660242, Nigeria;
| | - Yusuf Kola Ahmed
- Biomedical Engineering Department, University of Ilorin, P.M.B 1515, Ilorin 240003, Nigeria;
| | - Ibrahim Abdullahi Karaye
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China; (Z.S.); (I.A.E.K.); (I.A.K.); (I.S.A.)
| | - Isah Salim Ahmad
- State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China; (Z.S.); (I.A.E.K.); (I.A.K.); (I.S.A.)
| |
Collapse
|
21
|
Nasseri M, Pal Attia T, Joseph B, Gregg NM, Nurse ES, Viana PF, Schulze-Bonhage A, Dümpelmann M, Worrell G, Freestone DR, Richardson MP, Brinkmann BH. Non-invasive wearable seizure detection using long-short-term memory networks with transfer learning. J Neural Eng 2021; 18. [PMID: 33730713 DOI: 10.1088/1741-2552/abef8a] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2020] [Accepted: 03/17/2021] [Indexed: 11/12/2022]
Abstract
Objective. The detection of seizures using wearable devices would improve epilepsy management, but reliable detection of seizures in an ambulatory environment remains challenging, and current studies lack concurrent validation of seizures using electroencephalography (EEG) data.Approach. An adaptively trained long-short-term memory deep neural network was developed and trained using a modest number of seizure data sets from wrist-worn devices. Transfer learning was used to adapt a classifier that was initially trained on intracranial electroencephalography (iEEG) signals to facilitate classification of non-EEG physiological datasets comprising accelerometry, blood volume pulse, skin electrodermal activity, heart rate, and temperature signals. The algorithm's performance was assessed with and without pre-training on iEEG signals and transfer learning. To assess the performance of the seizure detection classifier using long-term ambulatory data, wearable devices were used for multiple months with an implanted neurostimulator capable of recording iEEG signals, which provided independent electrographic seizure detections that were reviewed by a board-certified epileptologist.Main results. For 19 motor seizures from 10 in-hospital patients, the algorithm yielded a mean area under curve (AUC), a sensitivity, and an false alarm rate per day (FAR/day) of 0.98, 0.93, and 2.3, respectively. Additionally, for eight seizures with probable motor semiology from two ambulatory patients, the classifier achieved a mean AUC of 0.97 and an FAR of 2.45 events/day at a sensitivity of 0.9. For all seizure types in the ambulatory setting, the classifier had a mean AUC of 0.82 with a sensitivity of 0.47 and an FAR of 7.2 events/day.Significance. The performance of the algorithm was evaluated using motor and non-motor seizures during in-hospital and ambulatory use. The classifier was able to detect multiple types of motor and non-motor seizures, but performed significantly better on motor seizures.
Collapse
Affiliation(s)
- Mona Nasseri
- Bioelectronics Neurology and Engineering Laboratory, Department of Neurology, Mayo Clinic, Alfred 9-441C, 200 First Street SW, Rochester, MN 55905, United States of America.,School of Engineering, University of North Florida, Jacksonville, FL, United States of America
| | - Tal Pal Attia
- Bioelectronics Neurology and Engineering Laboratory, Department of Neurology, Mayo Clinic, Alfred 9-441C, 200 First Street SW, Rochester, MN 55905, United States of America
| | - Boney Joseph
- Bioelectronics Neurology and Engineering Laboratory, Department of Neurology, Mayo Clinic, Alfred 9-441C, 200 First Street SW, Rochester, MN 55905, United States of America
| | - Nicholas M Gregg
- Bioelectronics Neurology and Engineering Laboratory, Department of Neurology, Mayo Clinic, Alfred 9-441C, 200 First Street SW, Rochester, MN 55905, United States of America
| | - Ewan S Nurse
- Seer Medical Pty Ltd, Melbourne, VIC, Australia.,Department of Medicine, St. Vincent's Hospital Melbourne, University of Melbourne, Melbourne, VIC, Australia
| | - Pedro F Viana
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom.,Faculty of Medicine, University of Lisbon, Lisboa, Portugal
| | - Andreas Schulze-Bonhage
- Department of Neurosurgery, Epilepsy Center, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Matthias Dümpelmann
- Department of Neurosurgery, Epilepsy Center, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Gregory Worrell
- Bioelectronics Neurology and Engineering Laboratory, Department of Neurology, Mayo Clinic, Alfred 9-441C, 200 First Street SW, Rochester, MN 55905, United States of America
| | - Dean R Freestone
- Seer Medical Pty Ltd, Melbourne, VIC, Australia.,Department of Medicine, St. Vincent's Hospital Melbourne, University of Melbourne, Melbourne, VIC, Australia
| | - Mark P Richardson
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
| | - Benjamin H Brinkmann
- Bioelectronics Neurology and Engineering Laboratory, Department of Neurology, Mayo Clinic, Alfred 9-441C, 200 First Street SW, Rochester, MN 55905, United States of America
| |
Collapse
|
22
|
Martini ML, Valliani AA, Sun C, Costa AB, Zhao S, Panov F, Ghatan S, Rajan K, Oermann EK. Deep anomaly detection of seizures with paired stereoelectroencephalography and video recordings. Sci Rep 2021; 11:7482. [PMID: 33820942 PMCID: PMC8021582 DOI: 10.1038/s41598-021-86891-y] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2021] [Accepted: 03/16/2021] [Indexed: 01/30/2023] Open
Abstract
Real-time seizure detection is a resource intensive process as it requires continuous monitoring of patients on stereoelectroencephalography. This study improves real-time seizure detection in drug resistant epilepsy (DRE) patients by developing patient-specific deep learning models that utilize a novel self-supervised dynamic thresholding approach. Deep neural networks were constructed on over 2000 h of high-resolution, multichannel SEEG and video recordings from 14 DRE patients. Consensus labels from a panel of epileptologists were used to evaluate model efficacy. Self-supervised dynamic thresholding exhibited improvements in positive predictive value (PPV; difference: 39.0%; 95% CI 4.5–73.5%; Wilcoxon–Mann–Whitney test; N = 14; p = 0.03) with similar sensitivity (difference: 14.3%; 95% CI − 21.7 to 50.3%; Wilcoxon–Mann–Whitney test; N = 14; p = 0.42) compared to static thresholds. In some models, training on as little as 10 min of SEEG data yielded robust detection. Cross-testing experiments reduced PPV (difference: 56.5%; 95% CI 25.8–87.3%; Wilcoxon–Mann–Whitney test; N = 14; p = 0.002), while multimodal detection significantly improved sensitivity (difference: 25.0%; 95% CI 0.2–49.9%; Wilcoxon–Mann–Whitney test; N = 14; p < 0.05). Self-supervised dynamic thresholding improved the efficacy of real-time seizure predictions. Multimodal models demonstrated potential to improve detection. These findings are promising for future deployment in epilepsy monitoring units to enable real-time seizure detection without annotated data and only minimal training time in individual patients.
Collapse
Affiliation(s)
- Michael L Martini
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Aly A Valliani
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Claire Sun
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA.,Department of Neurosciences, Friedman Brain Institute, Icahn School of Medicine at Mount Sinai, One Gustave Levy Place, New York, NY, 10029, USA
| | - Anthony B Costa
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Shan Zhao
- Department of Anesthesiology, Icahn School of Medicine At Mount Sinai, New York, NY, 10029, USA
| | - Fedor Panov
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Saadi Ghatan
- Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Kanaka Rajan
- Department of Neurosciences, Friedman Brain Institute, Icahn School of Medicine at Mount Sinai, One Gustave Levy Place, New York, NY, 10029, USA.
| | - Eric Karl Oermann
- Department of Neurosurgery, New York University Langone Medical Center, New York University, Skirball, Suite 8S, 530 First Avenue, New York, NY, 10016, USA. .,Department of Radiology, New York University Langone Medical Center, New York, NY, 10016, USA. .,NYU Center for Data Science, New York University, New York, NY, 10011, USA.
| |
Collapse
|
23
|
Gómez C, Arbeláez P, Navarrete M, Alvarado-Rojas C, Le Van Quyen M, Valderrama M. Automatic seizure detection based on imaged-EEG signals through fully convolutional networks. Sci Rep 2020; 10:21833. [PMID: 33311533 PMCID: PMC7732993 DOI: 10.1038/s41598-020-78784-3] [Citation(s) in RCA: 33] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2020] [Accepted: 11/26/2020] [Indexed: 02/06/2023] Open
Abstract
Seizure detection is a routine process in epilepsy units requiring manual intervention of well-trained specialists. This process could be extensive, inefficient and time-consuming, especially for long term recordings. We proposed an automatic method to detect epileptic seizures using an imaged-EEG representation of brain signals. To accomplish this, we analyzed EEG signals from two different datasets: the CHB-MIT Scalp EEG database and the EPILEPSIAE project that includes scalp and intracranial recordings. We used fully convolutional neural networks to automatically detect seizures. For our best model, we reached average accuracy and specificity values of 99.3% and 99.6%, respectively, for the CHB-MIT dataset, and corresponding values of 98.0% and 98.3% for the EPILEPSIAE patients. For these patients, the inclusion of intracranial electrodes together with scalp ones increased the average accuracy and specificity values to 99.6% and 58.3%, respectively. Regarding the other metrics, our best model reached average precision of 62.7%, recall of 58.3%, F-measure of 59.0% and AP of 54.5% on the CHB-MIT recordings, and comparatively lowers performances for the EPILEPSIAE dataset. For both databases, the number of false alarms per hour reached values less than 0.5/h for 92% of the CHB-MIT patients and less than 1.0/h for 80% of the EPILEPSIAE patients. Compared to recent studies, our lightweight approach does not need any estimation of pre-selected features and demonstrates high performances with promising possibilities for the introduction of such automatic methods in the clinical practice.
Collapse
Affiliation(s)
- Catalina Gómez
- Department of Biomedical Engineering, Universidad de los Andes, Bogotá, Colombia
- Center for Research and Formation in Artificial Intelligence (CINFONIA), Universidad de los Andes, Bogotá, Colombia
| | - Pablo Arbeláez
- Department of Biomedical Engineering, Universidad de los Andes, Bogotá, Colombia
- Center for Research and Formation in Artificial Intelligence (CINFONIA), Universidad de los Andes, Bogotá, Colombia
| | - Miguel Navarrete
- Department of Biomedical Engineering, Universidad de los Andes, Bogotá, Colombia
- School of Psychology, Brain Research Imaging Centre, Cardiff University, Cardiff, UK
| | | | - Michel Le Van Quyen
- Laboratoire d'Imagerie Biomédicale (LIB), Inserm U1146 / Sorbonne Université UMCR2 / UMR7371 CNRS, 15 rue de l'Ecole de Médecine, 75006, Paris, France
| | - Mario Valderrama
- Department of Biomedical Engineering, Universidad de los Andes, Bogotá, Colombia.
| |
Collapse
|
24
|
GRP-DNet: A gray recurrence plot-based densely connected convolutional network for classification of epileptiform EEG. J Neurosci Methods 2020; 347:108953. [PMID: 33007344 DOI: 10.1016/j.jneumeth.2020.108953] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2020] [Revised: 09/16/2020] [Accepted: 09/16/2020] [Indexed: 12/27/2022]
Abstract
BACKGROUND The classification of epileptiform electroencephalogram (EEG) signals has been treated as an important but challenging issue for realizing epileptic seizure detection. In this work, combing gray recurrence plot (GRP) and densely connected convolutional network (DenseNet), we developed a novel classification system named GRP-DNet to identify seizures and epilepsy from single-channel, long-term EEG signals. NEW METHODS The proposed GRP-DNet classification system includes three main modules: 1) input module takes an input long-term EEG signal and divides it into multiple short segments using a fixed-size non-overlapping sliding window (FNSW); 2) conversion module transforms short segments into GRPs and passes them to the DenseNet; 3) fusion and decision, the predicted label of each GRP is fused using a majority voting strategy to make the final decision. RESULTS Six different classification experiments were designed based on a publicly available benchmark database to evaluate the effectiveness of our system. Experimental results showed that the proposed GRP-DNet achieved an excellent classification accuracy of 100 % in each classification experiment, Furthermore, GRP-DNet gave excellent computational efficiency, which indicates its tremendous potential for developing an EEG-based online epilepsy diagnosis system. COMPARISON WITH EXISTING METHODS Our GRP-DNet system was superior to the existing competitive classification systems using the same database. CONCLUSIONS The GRP-DNet is a potentially powerful system for identifying and classifying EEG signals recorded from different brain states.
Collapse
|
25
|
Abstract
Comparison of Different Input Modalities and Network Structures for Deep
Learning-Based Seizure Detection Cho KO, Jang HJ. Sci Rep. 2020;10(1):1-11. doi: 10.1038/s41598-019-56958-y The manual review of an electroencephalogram (EEG) for seizure detection is a
laborious and error-prone process. Thus, automated seizure detection based on machine
learning has been studied for decades. Recently, deep learning has been adopted in
order to avoid manual feature extraction and selection. In the present study, we
systematically compared the performance of different combinations of input modalities
and network structures on a fixed window size and data set to ascertain an optimal
combination of input modalities and network structures. The raw time series EEG,
periodogram of the EEG, 2-dimensional [2D] images of short-time Fourier transform
results, and 2D images of raw EEG waveforms were obtained from 5-second segments of
intracranial EEGs recorded from a mouse model of epilepsy. A fully connected neural
network (FCNN), recurrent neural network (RNN), and convolutional neural network (CNN)
were implemented to classify the various inputs. The classification results for the
test data set showed that CNN performed better than FCNN and RNN, with the area under
the curve (AUC) for the receiver operating characteristics curves ranging from 0.983
to 0.984, from 0.985 to 0.989, and from 0.989 to 0.993 for FCNN, RNN, and CNN,
respectively. As for input modalities, 2D images of raw EEG waveforms yielded the best
result with an AUC of 0.993. Thus, CNN can be the most suitable network structure for
automated seizure detection when applied to the images of raw EEG waveforms, since CNN
can effectively learn a general spatially invariant representation of seizure patterns
in 2D representations of raw EEG.
Collapse
|
26
|
Fumeaux NF, Ebrahim S, Coughlin BF, Kadambi A, Azmi A, Xu JX, Jaoude MA, Nagaraj SB, Thomson KE, Newell TG, Metcalf CS, Wilcox KS, Kimchi EY, Moraes MFD, Cash SS. Accurate detection of spontaneous seizures using a generalized linear model with external validation. Epilepsia 2020; 61:1906-1918. [PMID: 32761902 PMCID: PMC7953845 DOI: 10.1111/epi.16628] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2019] [Revised: 07/02/2020] [Accepted: 07/02/2020] [Indexed: 01/15/2023]
Abstract
OBJECTIVE Seizure detection is a major facet of electroencephalography (EEG) analysis in neurocritical care, epilepsy diagnosis and management, and the instantiation of novel therapies such as closed-loop stimulation or optogenetic control of seizures. It is also of increased importance in high-throughput, robust, and reproducible pre-clinical research. However, seizure detectors are not widely relied upon in either clinical or research settings due to limited validation. In this study, we create a high-performance seizure-detection approach, validated in multiple data sets, with the intention that such a system could be available to users for multiple purposes. METHODS We introduce a generalized linear model trained on 141 EEG signal features for classification of seizures in continuous EEG for two data sets. In the first (Focal Epilepsy) data set consisting of 16 rats with focal epilepsy, we collected 1012 spontaneous seizures over 3 months of 24/7 recording. We trained a generalized linear model on the 141 features representing 20 feature classes, including univariate and multivariate, linear and nonlinear, time, and frequency domains. We tested performance on multiple hold-out test data sets. We then used the trained model in a second (Multifocal Epilepsy) data set consisting of 96 rats with 2883 spontaneous multifocal seizures. RESULTS From the Focal Epilepsy data set, we built a pooled classifier with an Area Under the Receiver Operating Characteristic (AUROC) of 0.995 and leave-one-out classifiers with an AUROC of 0.962. We validated our method within the independently constructed Multifocal Epilepsy data set, resulting in a pooled AUROC of 0.963. We separately validated a model trained exclusively on the Focal Epilepsy data set and tested on the held-out Multifocal Epilepsy data set with an AUROC of 0.890. Latency to detection was under 5 seconds for over 80% of seizures and under 12 seconds for over 99% of seizures. SIGNIFICANCE This method achieves the highest performance published for seizure detection on multiple independent data sets. This method of seizure detection can be applied to automated EEG analysis pipelines as well as closed loop interventional approaches, and can be especially useful in the setting of research using animals in which there is an increased need for standardization and high-throughput analysis of large number of seizures.
Collapse
Affiliation(s)
- Nicolas F. Fumeaux
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Senan Ebrahim
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Brian F. Coughlin
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Adesh Kadambi
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Aafreen Azmi
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Jen X. Xu
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Maurice Abou Jaoude
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Sunil B. Nagaraj
- Clinical Pharmacy and Pharmacology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Kyle E. Thomson
- Department of Pharmacology, University of Utah, Salt Lake City, UT, USA
| | - Thomas G. Newell
- Department of Pharmacology, University of Utah, Salt Lake City, UT, USA
| | | | - Karen S. Wilcox
- Department of Pharmacology, University of Utah, Salt Lake City, UT, USA
| | - Eyal Y. Kimchi
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | | | - Sydney S. Cash
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| |
Collapse
|
27
|
An S, Kang C, Lee HW. Artificial Intelligence and Computational Approaches for Epilepsy. J Epilepsy Res 2020; 10:8-17. [PMID: 32983950 PMCID: PMC7494883 DOI: 10.14581/jer.20003] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2020] [Revised: 06/18/2020] [Accepted: 07/14/2020] [Indexed: 12/30/2022] Open
Abstract
Studies on treatment of epilepsy have been actively conducted in multiple avenues, but there are limitations in improving its efficacy due to between-subject variability in which treatment outcomes vary from patient to patient. Accordingly, there is a growing interest in precision medicine that provides accurate diagnosis for seizure types and optimal treatment for an individual epilepsy patient. Among these approaches, computational studies making this feasible are rapidly progressing in particular and have been widely applied in epilepsy. These computational studies are being conducted in two main streams: 1) artificial intelligence-based studies implementing computational machines with specific functions, such as automatic diagnosis and prognosis prediction for an individual patient, using machine learning techniques based on large amounts of data obtained from multiple patients and 2) patient-specific modeling-based studies implementing biophysical in-silico platforms to understand pathological mechanisms and derive the optimal treatment for each patient by reproducing the brain network dynamics of the particular patient per se based on individual patient's data. These computational approaches are important as it can integrate multiple types of data acquired from patients and analysis results into a single platform. If these kinds of methods are efficiently operated, it would suggest a novel paradigm for precision medicine.
Collapse
Affiliation(s)
- Sora An
- Department of Neurology, Ewha Womans University School of Medicine and Ewha Medical Research Institute, Seoul, Korea.,Department of Medical Science, Ewha Womans University School of Medicine and Ewha Medical Research Institute, Seoul, Korea
| | - Chaewon Kang
- Department of Neurology, Ewha Womans University School of Medicine and Ewha Medical Research Institute, Seoul, Korea.,Department of Computational Medicine, Ewha Womans University School of Medicine and Ewha Medical Research Institute, Seoul, Korea
| | - Hyang Woon Lee
- Department of Neurology, Ewha Womans University School of Medicine and Ewha Medical Research Institute, Seoul, Korea.,Department of Medical Science, Ewha Womans University School of Medicine and Ewha Medical Research Institute, Seoul, Korea.,Department of Computational Medicine, Ewha Womans University School of Medicine and Ewha Medical Research Institute, Seoul, Korea
| |
Collapse
|