scholarly journals Multi-Head Self-Attention Model for Classification of Temporal Lobe Epilepsy Subtypes

2020 ◽  
Vol 11 ◽  
Author(s):  
Peipei Gu ◽  
Ting Wu ◽  
Mingyang Zou ◽  
Yijie Pan ◽  
Jiayang Guo ◽  
...  
Keyword(s):  
Temporal Lobe Epilepsy ◽  
Temporal Lobe ◽  
Clinical Symptoms ◽  
Brain Network ◽  
Optimal Number ◽  
The Self ◽  
Support Vector ◽  
Great Effort ◽  
Attention Model

As a long-standing chronic disease, Temporal Lobe Epilepsy (TLE), resulting from abnormal discharges of neurons and characterized by recurrent episodic central nervous system dysfunctions, has affected more than 70% of drug-resistant epilepsy patients across the world. As the etiology and clinical symptoms are complicated, differential diagnosis of TLE mainly relies on experienced clinicians, and specific diagnostic biomarkers remain unclear. Though great effort has been made regarding the genetics, pathology, and neuroimaging of TLE, an accurate and effective diagnosis of TLE, especially the TLE subtypes, remains an open problem. It is of a great importance to explore the brain network of TLE, since it can provide the basis for diagnoses and treatments of TLE. To this end, in this paper, we proposed a multi-head self-attention model (MSAM). By integrating the self-attention mechanism and multilayer perceptron method, the MSAM offers a promising tool to enhance the classification of TLE subtypes. In comparison with other approaches, including convolutional neural network (CNN), support vector machine (SVM), and random forest (RF), experimental results on our collected MEG dataset show that the MSAM achieves a supreme performance of 83.6% on accuracy, 90.9% on recall, 90.7% on precision, and 83.4% on F1-score, which outperforms its counterparts. Furthermore, effectiveness of varying head numbers of multi-head self-attention is assessed, which helps select the optimal number of multi-head. The self-attention aspect learns the weights of different signal locations which can effectively improve classification accuracy. In addition, the robustness of MSAM is extensively assessed with various ablation tests, which demonstrates the effectiveness and generalizability of the proposed approach.

scholarly journals Automatic Lateralization of Temporal Lobe Epilepsy Based on MEG Network Features Using Support Vector Machines

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Ting Wu ◽  
Duo Chen ◽  
Qiqi Chen ◽  
Rui Zhang ◽  
Wenyu Zhang ◽  
...  
Keyword(s):  
Temporal Lobe Epilepsy ◽  
Temporal Lobe ◽  
Betweenness Centrality ◽  
Binary Classification ◽  
Brain Network ◽  
Support Vector ◽  
Classification Problems ◽  
Healthy Control ◽  
Control Right ◽  
Network Metrics

Correct lateralization of temporal lobe epilepsy (TLE) is critical for improving surgical outcomes. As a relatively new noninvasive clinical recording system, magnetoencephalography (MEG) has rarely been applied for determining lateralization of unilateral TLE. Here we propose a framework for using resting-state brain-network features and support vector machine (SVM) for TLE lateralization based on MEG. We recruited 15 patients with left TLE, 15 patients with right TLE, and 15 age- and sex-matched healthy controls. The lateralization problem was then transferred into a series of binary classification problems, including left TLE versus healthy control, right TLE versus healthy control, and left TLE versus right TLE. Brain-network features were extracted for each participant using three network metrics (nodal degree, betweenness centrality, and nodal efficiency). A radial basis function kernel SVM (RBF-SVM) was employed as the classifier. The leave-one-subject-out cross-validation strategy was used to test the ability of this approach to overcome individual differences. The results revealed that the nodal degree performed best for left TLE versus healthy control and right TLE versus healthy control, with accuracy of 80.76% and 75.00%, respectively. Betweenness centrality performed best for left TLE versus right TLE with an accuracy of 88.10%. The proposed approach demonstrated that MEG is a good candidate for solving the lateralization problem in unilateral TLE using various brain-network features.

scholarly journals Individual Brain Metabolic Connectome Indicator Based on Jensen-Shannon Divergence Similarity Estimation Predicts Seizure Outcomes of Temporal Lobe Epilepsy

2022 ◽  
Vol 9 ◽  
Author(s):  
Zehua Zhu ◽  
Zhimin Zhang ◽  
Xin Gao ◽  
Li Feng ◽  
Dengming Chen ◽  
...  
Keyword(s):  
Temporal Lobe Epilepsy ◽  
Temporal Lobe ◽  
Age At Onset ◽  
Brain Network ◽  
Classification Performance ◽  
Imaging Biomarker ◽  
Support Vector ◽  
Similarity Estimation ◽  
Jensen Shannon Divergence

Objective: We aimed to use an individual metabolic connectome method, the Jensen-Shannon Divergence Similarity Estimation (JSSE), to characterize the aberrant connectivity patterns and topological alterations of the individual-level brain metabolic connectome and predict the long-term surgical outcomes in temporal lobe epilepsy (TLE).Methods: A total of 128 patients with TLE (63 females, 65 males; 25.07 ± 12.01 years) who underwent Positron emission tomography (PET) with 18F-fluorodeoxyglucose (FDG) imaging were enrolled. Patients were classified either as experiencing seizure recurrence (SZR) or seizure free (SZF) at least 1 year after surgery. Each individual’s metabolic brain network was ascertained using the proposed JSSE method. We compared the similarity and difference in the JSSE network and its topological measurements between the two groups. The two groups were then classified by combining the information from connection and topological metrics, which was conducted by the multiple kernel support vector machine. The validation was performed using the nested leave-one-out cross-validation strategy to confirm the performance of the methods.Results: With a median follow-up of 33 months, 50% of patients achieved SZF. No relevant differences in clinical features were found between the two groups except age at onset. The proposed JSSE method showed marked degree reductions in IFGoperc.R, ROL. R, IPL. R, and SMG. R; and betweenness reductions in ORBsup.R and IOG. R; meanwhile, it found increases in the degree analysis of CAL. L and PCL. L, and in the betweenness analysis of PreCG.R, IOG. R, PoCG.R, PCL. L and PCL.R. Exploring consensus significant metabolic connections, we observed that the most involved metabolic motor networks were the INS-TPOmid.L, MTG. R-SMG. R, and MTG. R-IPL.R pathways between the two groups, and yielded another detailed individual pathological connectivity in the PHG. R-CAU.L, PHG. R-HIP.L, TPOmid.L-LING.R, TPOmid.L-DCG.R, MOG. R-MTG.R, MOG. R-ANG.R, and IPL. R-IFGoperc.L pathways. These aberrant functional network measures exhibited ideal classification performance in predicting SZF individuals from SZR ones at a sensitivity of 75.00%, a specificity of 92.79%, and an accuracy of 83.59%.Conclusion: The JSSE method indicator can identify abnormal brain networks in predicting an individual’s long-term surgical outcome of TLE, thus potentially constituting a clinically applicable imaging biomarker. The results highlight the biological meaning of the estimated individual brain metabolic connectome.

scholarly journals Neuropathology of Temporal Lobe Epilepsy

2012 ◽  
Vol 2012 ◽  
pp. 1-13 ◽  
Author(s):  
Fahd Al Sufiani ◽  
Lee Cyn Ang
Keyword(s):  
Temporal Lobe Epilepsy ◽  
Temporal Lobe ◽  
Focal Cortical Dysplasia ◽  
Cortical Dysplasia ◽  
Wide Range ◽  
Pathologic Findings ◽  
Pathologic Lesions ◽  
Recent Classification ◽  
Associated Tumors

Pathologic findings in surgical resections from patients with temporal lobe epilepsy include a wide range of diagnostic possibilities that can be categorized into different groups on the basis of etiology. This paper outlines the various pathologic entities described in temporal lobe epilepsy, including some newly recognized epilepsy-associated tumors, and briefly touch on the recent classification of focal cortical dysplasia. This classification takes into account coexistent pathologic lesions in focal cortical dysplasia.

Individual-Specific Connectome Fingerprint Based Classification of Temporal Lobe Epilepsy

2021 ◽  
pp. 754-761
Author(s):  
Yao Meng ◽  
Jinming Xiao ◽  
Siqi Yang ◽  
Qiang Xu ◽  
Zhiqiang Zhang ◽  
...  
Keyword(s):  
Temporal Lobe Epilepsy ◽  
Temporal Lobe

scholarly journals Déjà Experiences in Temporal Lobe Epilepsy

2012 ◽  
Vol 2012 ◽  
pp. 1-15 ◽  
Author(s):  
Nathan A. Illman ◽  
Chris R. Butler ◽  
Celine Souchay ◽  
Chris J. A. Moulin
Keyword(s):  
Temporal Lobe Epilepsy ◽  
Cognitive Processing ◽  
Temporal Lobe ◽  
Seizure Activity ◽  
Memory Function ◽  
Future Research ◽  
Deja Vu ◽  
Déjà Vu ◽  
Patients Experience

Historically, déjà vu has been linked to seizure activity in temporal lobe epilepsy, and clinical reports suggest that many patients experience the phenomenon as a manifestation of simple partial seizures. We review studies on déjà vu in epilepsy with reference to recent advances in the understanding of déjà vu from a cognitive and neuropsychological standpoint. We propose a decoupled familiarity hypothesis, whereby déjà vu is produced by an erroneous feeling of familiarity which is not in keeping with current cognitive processing. Our hypothesis converges on a parahippocampal dysfunction as the locus of déjà vu experiences. However, several other temporal lobe structures feature in reports of déjà vu in epilepsy. We suggest that some of the inconsistency in the literature derives from a poor classification of the various types of déjà experiences. We propose déjà vu/déjà vécu as one way of understanding déjà experiences more fully. This distinction is based on current models of memory function, where déjà vu is caused by erroneous familiarity and déjà vécu by erroneous recollection. Priorities for future research and clinical issues are discussed.

scholarly journals Insect bite hypersensitivity in Belgian warmblood horses: prevalence and risk factors

2014 ◽  
Vol 83 (5) ◽  
pp. 240-249
Author(s):  
L. M. Peeters ◽  
S. Janssens ◽  
A. Coussé ◽  
N. Buys
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Model Selection ◽  
Allergic Reaction ◽  
Clinical Symptoms ◽  
The Self ◽  
Face To Face ◽  
Regression Framework ◽  
Insect Bite Hypersensitivity

Insect bite hypersensitivity (IBH) is an allergic reaction to the bites of certain Culicoides spp. or other insects. In this study, risk factors for IBH in Belgian warmblood horses stabled or grazing in Flanders (Belgium) were investigated. IBH records (n=3409) were collected in 2009 and 2011 using a questionnaire and face-to-face interviews. The classification of IBH-affected versus unaffected horses was based on the owner’s statement, and the reported IBH lifetime prevalence was 10%. Thirty eight percent of IBH affected horses had no clinical symptoms at the time of questioning. When only the presence or absence of clinical symptoms at the time of questioning was taken into account, the prevalence of IBH symptoms was 6.2%. Seventy percent of IBH-affected horses were treated with IBH measures to reduce clinical symptoms. Model selection was based on backwards elimination in a logistic regression framework starting with 17 factors. The age of the horse, vegetation of surrounding pasture and stud size were found to be significantly associated with the self-reported IBH status.

scholarly journals A study of brain functional network and alertness changes in temporal lobe epilepsy with and without focal to bilateral tonic–clonic seizures

BMC Neurology ◽  
2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Liluo Nie ◽  
Yanchun Jiang ◽  
Zongxia Lv ◽  
Xiaomin Pang ◽  
Xiulin Liang ◽  
...  
Keyword(s):  
Temporal Lobe Epilepsy ◽  
Temporal Lobe ◽  
Information Integration ◽  
Refractory Epilepsy ◽  
Brain Network ◽  
Clustering Coefficient ◽  
Global Network ◽  
Seizure Type ◽  
Topological Properties ◽  
Clonic Seizures

Abstract Background Temporal lobe epilepsy (TLE) is commonly refractory. Epilepsy surgery is an effective treatment strategy for refractory epilepsy, but patients with a history of focal to bilateral tonic-clonic seizures (FBTCS) have poor outcomes. Previous network studies on epilepsy have found that TLE and idiopathic generalized epilepsy with generalized tonic-clonic seizures (IGE-GTCS) showed altered global and nodal topological properties. Alertness deficits also were found in TLE. However, FBTCS is a common type of seizure in TLE, and the implications for alertness as well as the topological rearrangements associated with this seizure type are not well understood. Methods We obtained rs-fMRI data and collected the neuropsychological assessment data from 21 TLE patients with FBTCS (TLE- FBTCS), 18 TLE patients without FBTCS (TLE-non- FBTCS) and 22 controls, and constructed their respective functional brain networks. The topological properties were analyzed using the graph theoretical approach and correlations between altered topological properties and alertness were analyzed. Results We found that TLE-FBTCS patients showed more serious impairment in alertness effect, intrinsic alertness and phasic alertness than the patients with TLE-non-FBTCS. They also showed significantly higher small-worldness, normalized clustering coefficient (γ) and a trend of higher global network efficiency (gE) compared to TLE-non-FBTCS patients. The gE showed a significant negative correlation with intrinsic alertness for TLE-non-FBTCS patients. Conclusion Our findings show different impairments in brain network information integration, segregation and alertness between the patients with TLE-FBTCS and TLE-non-FBTCS, demonstrating that impairments of the brain network may underlie the disruptions in alertness functions.

scholarly journals Integrating Optimized Multiscale Entropy Model with Machine Learning for the Localization of Epileptogenic Hemisphere in Temporal Lobe Epilepsy Using Resting-State fMRI

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Xiaoxuan Fu ◽  
Youhua Wang ◽  
Abdelkader Nasreddine Belkacem ◽  
Qirui Zhang ◽  
Chong Xie ◽  
...  
Keyword(s):  
Machine Learning ◽  
Temporal Lobe Epilepsy ◽  
Temporal Lobe ◽  
Roc Curve ◽  
Resting State ◽  
Supervised Machine Learning ◽  
Multiscale Entropy ◽  
Support Vector ◽  
Brain Areas ◽  
Entropy Model

The bottleneck associated with the validation of the parameters of the entropy model has limited the application of this model to modern functional imaging technologies such as the resting-state functional magnetic resonance imaging (rfMRI). In this study, an optimization algorithm that could choose the parameters of the multiscale entropy (MSE) model was developed, while the optimized effectiveness for localizing the epileptogenic hemisphere was validated through the classification rate with a supervised machine learning method. The rfMRI data of 20 mesial temporal lobe epilepsy patients with positive indicators (the indicators of epileptogenic hemisphere in clinic) in the hippocampal formation on either left or right hemisphere (equally divided into two groups) on the structural MRI were collected and preprocessed. Then, three parameters in the MSE model were statistically optimized by both receiver operating characteristic (ROC) curve and the area under the ROC curve value in the sensitivity analysis, and the intergroup significance of optimized entropy values was utilized to confirm the biomarked brain areas sensitive to the epileptogenic hemisphere. Finally, the optimized entropy values of these biomarked brain areas were regarded as the feature vectors input for a support vector machine to classify the epileptogenic hemisphere, and the classification effectiveness was cross-validated. Nine biomarked brain areas were confirmed by the optimized entropy values, including medial superior frontal gyrus and superior parietal gyrus ( p  < .01). The mean classification accuracy was greater than 90%. It can be concluded that combination of the optimized MSE model with the machine learning model can accurately confirm the epileptogenic hemisphere by rfMRI. With the powerful information interaction capabilities of 5G communication, the epilepsy side-fixing algorithm that requires computing power can be integrated into a cloud platform. The demand side only needs to upload patient data to the service platform to realize the preoperative assessment of epilepsy.

Sign in / Sign up

Export Citation Format

Share Document