scholarly journals Time–Frequency Decomposition of Scalp Electroencephalograms Improves Deep Learning-Based Epilepsy Diagnosis

2021 ◽  
pp. 2150032
Author(s):  
Prasanth Thangavel ◽  
John Thomas ◽  
Wei Yan Peh ◽  
Jin Jing ◽  
Rajamanickam Yuvaraj ◽  
...  
Keyword(s):  
Classification System ◽  
Area Under The Curve ◽  
Classification Performance ◽  
Eeg Classification ◽  
Time Frequency ◽  
Frequency Decomposition ◽  
Epileptiform Discharges ◽  
Interictal Epileptiform Discharges ◽  
Epilepsy Diagnosis ◽  
Human Effort

Epilepsy diagnosis based on Interictal Epileptiform Discharges (IEDs) in scalp electroencephalograms (EEGs) is laborious and often subjective. Therefore, it is necessary to build an effective IED detector and an automatic method to classify IED-free versus IED EEGs. In this study, we evaluate features that may provide reliable IED detection and EEG classification. Specifically, we investigate the IED detector based on convolutional neural network (ConvNet) with different input features (temporal, spectral, and wavelet features). We explore different ConvNet architectures and types, including 1D (one-dimensional) ConvNet, 2D (two-dimensional) ConvNet, and noise injection at various layers. We evaluate the EEG classification performance on five independent datasets. The 1D ConvNet with preprocessed full-frequency EEG signal and frequency bands (delta, theta, alpha, beta) with Gaussian additive noise at the output layer achieved the best IED detection results with a false detection rate of 0.23/min at 90% sensitivity. The EEG classification system obtained a mean EEG classification Leave-One-Institution-Out (LOIO) cross-validation (CV) balanced accuracy (BAC) of 78.1% (area under the curve (AUC) of 0.839) and Leave-One-Subject-Out (LOSO) CV BAC of 79.5% (AUC of 0.856). Since the proposed classification system only takes a few seconds to analyze a 30-min routine EEG, it may help in reducing the human effort required for epilepsy diagnosis.

Time-frequency decomposition-based weighted ensemble learning for motor imagery EEG classification

2021 ◽  
Author(s):  
Liangsheng Zheng ◽  
Yue Ma ◽  
Mengyao Li ◽  
Yang Xiao ◽  
Wei Feng ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Motor Imagery ◽  
Eeg Classification ◽  
Time Frequency ◽  
Frequency Decomposition

scholarly journals Sleep spindles, ripples, and interictal epileptiform discharges in the human anterior and mediodorsal thalamus

2021 ◽  
Author(s):  
Orsolya Szalardy ◽  
Peter Simor ◽  
Peter Przemyslaw Ujma ◽  
Zsofia Jordan ◽  
Laszlo Halasz ◽  
...  
Keyword(s):  
Neural Plasticity ◽  
Nrem Sleep ◽  
Cortical Activity ◽  
Sleep Spindles ◽  
Time Frequency ◽  
Scalp Eeg ◽  
Epileptiform Discharges ◽  
Interictal Epileptiform Discharges ◽  
Human Thalamus ◽  
Result Show

Sleep spindles are major oscillatory components of Non-Rapid Eye Movement (NREM) sleep, reflecting hyperpolarization-rebound sequences of thalamocortical neurons, the inhibition of which is caused by the NREM-dependent activation of GABAergic neurons in the reticular thalamic nucleus. Reports suggest a link between sleep spindles and several forms of interictal epileptic discharges (IEDs) which are considered as expressions of pathological off-line neural plasticity in the central nervous system. Here we investigated the relationship between thalamic sleep spindles, IEDs and ripples in the anterior and mediodorsal nuclei (ANT and MD) of epilepsy patients. Whole-night LFP from the ANT and MD were co-registered with scalp EEG/polysomnography by using externalized leads in 15 epilepsy patients undergoing Deep Brain Stimulation protocol. Slow (~12 Hz) and fast (~14 Hz) sleep spindles were present in the human ANT and MD. Roughly, one third of thalamic sleep spindles were associated with IEDs or ripples. Both IED- and ripple-associated spindles were longer than pure spindles. IED-associated thalamic sleep spindles were characterized by broadband increase in thalamic and cortical activity, both below and above the spindle frequency range, whereas ripple-associated thalamic spindles exceeded pure spindles in terms of 80-200 Hz thalamic, but not cortical activity as indicated by time-frequency analysis. These result show that thalamic spindles coupled with IEDs are reflected at the scalp slow and beta-gamma oscillation as well. IED density during sleep spindles in the MD, but not in the ANT was identified as correlates of years spent with epilepsy, whereas no signs of pathological processes were correlated with measures of ripple and spindle association. Furthermore, the density of ripple-associated sleep spindles in the ANT showed a positive correlation with general intelligence. Our findings indicate the complex and multifaceted role of the human thalamus in sleep spindle-related physiological and pathological neural plasticity.

scholarly journals Comparison of Attention-based Deep LearningModels for EEG Classification

2021 ◽  
Author(s):  
Giulia Cisotto ◽  
Alessio Zanga ◽  
Joanna Chlebus ◽  
Italo Zoppis ◽  
Sara Manzoni ◽  
...  
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Classification Performance ◽  
Classification Problems ◽  
Large Variability ◽  
Eeg Classification ◽  
Time Frequency ◽  
Promising Strategy ◽  
Complex Reasoning

Abstract Deep Learning (DL) has recently shown promising classification performance in Electroencephalography (EEG) in many different scenarios. However, the complex reasoning of such models often prevent the user to explain their classification abilities. Attention, one of the most recent and influential ideas in DL, allows the models to learn which portions of the data are relevant to the final classification output. In this work, we compared three attention-enhanced DL models, the brand-new InstaGATs , an LSTM with attention and a CNN with attention. We used these models to classify normal and abnormal, including artifactual and pathological, EEG patterns in three different datasets. We achieved the state of the art in all classification problems, regardless the large variability of the datasets and the simple architecture of the attention-enhanced models. Additionally, we proved that, depending on how the attention mechanism is applied and where the attention layer is located in the model, we can alternatively leverage the information contained in the time, frequency or space domain of the EEG dataset. Therefore, attention represents a promising strategy to evaluate the quality of the EEG information, and its relevance for classification, in different real-world scenarios.

scholarly journals Higher-order tensor decomposition based scalp-to-intracranial EEG projection for detection of interictal epileptiform discharges

2021 ◽  
Author(s):  
Bahman Abdi Sargezeh ◽  
Antonio Valentin ◽  
Gonzalo Alarcon ◽  
David Martin-Lopez ◽  
Saeid Sanei
Keyword(s):  
Model Performance ◽  
High Sensitivity ◽  
Subject Classification ◽  
Tensor Factorization ◽  
Intracranial Eeg ◽  
Time Frequency ◽  
Mapping Model ◽  
Epileptiform Discharges ◽  
Interictal Epileptiform Discharges ◽  
Mapping Models

Abstract Objective. Interictal epileptiform discharges (IEDs) occur between two seizures onsets. IEDs are mainly captured by intracranial recordings and are often invisible over the scalp. This study proposes a model based on tensor factorization to map the time-frequency (TF) features of scalp EEG (sEEG) to the TF features of intracranial EEG (iEEG) in order to detect IEDs from over the scalp with high sensitivity. Approach. Continuous wavelet transform is employed to extract the TF features. Time, frequency, and channel modes of IED segments from iEEG recordings are concatenated into a four-way tensor. Tucker and CANDECOMP/PARAFAC decomposition techniques are employed to decompose the tensor into temporal, spectral, spatial, and segmental factors. Finally, TF features of both IED and non-IED segments from scalp recordings are projected onto the temporal components for classification. Main results. The model performance is obtained in two different approaches: within- and between-subject classification approaches. Our proposed method is compared with four other methods, namely a tensor-based spatial component analysis method, TF-based method, linear regression mapping model, and asymmetric-symmetric autoencoder mapping model followed by convolutional neural networks. Our proposed method outperforms all these methods in both within- and between-subject classification approaches by respectively achieving 84.2% and 72.6% accuracy values. Significance. The findings show that mapping sEEG to iEEG improves the performance of the scalp-based IED detection model. Furthermore, the tensor-based mapping model outperforms the autoencoder- and regression-based mapping models.

scholarly journals Incorporating Uncertainty in Data Labeling into Automatic Detection of Interictal Epileptiform Discharges from Concurrent Scalp-EEG via Multi-way Analysis

2021 ◽  
pp. 2150019
Author(s):  
Bahman Abdi-Sargezeh ◽  
Antonio Valentin ◽  
Gonzalo Alarcon ◽  
Saeid Sanei
Keyword(s):  
State Of The Art ◽  
Detection System ◽  
Superior Performance ◽  
Tensor Factorization ◽  
Time Frequency ◽  
Scalp Eeg ◽  
Epileptiform Discharges ◽  
Interictal Epileptiform Discharges ◽  
The Brain ◽  
Frequency Features

Interictal epileptiform discharges (IEDs) are elicited from an epileptic brain, whereas they can also be due to other neurological abnormalities. The diversity in their morphologies, their strengths, and their sources within the brain cause a great deal of uncertainty in their labeling by clinicians. The aim of this study is therefore to exploit and incorporate this uncertainty (the probability of the waveform being an IED) in the IED detection system which combines spatial component analysis (SCA) with the IED probabilities referred to as SCA-IEDP-based method. For comparison, we also propose and study SCA-based method in which probability of the waveform being an IED is ignored. The proposed models are employed to detect IEDs in two different classification approaches: (1) subject-dependent and (2) subject-independent classification approaches. The proposed methods are compared with two other state-of-the-art methods namely, time–frequency features and tensor factorization methods. The proposed SCA-IEDP model has achieved superior performance in comparison with the traditional SCA and other competing methods. It achieved 79.9% and 63.4% accuracy values in subject-dependent and subject-independent classification approaches, respectively. This shows that considering the IED probabilities in designing an IED detection system can boost its performance.

Prevalence of Interictal Epileptiform Discharges in Children Less Than One Year of Age Referred for Polysomnography

2015 ◽  
Vol 55 (2) ◽  
pp. 122-132
Author(s):  
Adetayo Adeleye ◽  
Alice W. Ho ◽  
Alberto Nettel-Aguirre ◽  
Valerie Kirk ◽  
Jeffrey Buchhalter
Keyword(s):  
Epileptiform Discharges ◽  
Interictal Epileptiform Discharges ◽  
One Year

scholarly journals Zero-crossing patterns reveal subtle epileptiform discharges in the scalp EEG

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jan Pyrzowski ◽  
Jean- Eudes Le Douget ◽  
Amal Fouad ◽  
Mariusz Siemiński ◽  
Joanna Jędrzejczak ◽  
...  
Keyword(s):  
Normal Subjects ◽  
Intracranial Eeg ◽  
Zero Crossing ◽  
Temporal Precision ◽  
Scalp Eeg ◽  
Epileptiform Discharges ◽  
Interictal Epileptiform Discharges ◽  
Eeg Recordings ◽  
Patients With Epilepsy ◽  
Low Amplitude

AbstractClinical diagnosis of epilepsy depends heavily on the detection of interictal epileptiform discharges (IEDs) from scalp electroencephalographic (EEG) signals, which by purely visual means is far from straightforward. Here, we introduce a simple signal analysis procedure based on scalp EEG zero-crossing patterns which can extract the spatiotemporal structure of scalp voltage fluctuations. We analyzed simultaneous scalp and intracranial EEG recordings from patients with pharmacoresistant temporal lobe epilepsy. Our data show that a large proportion of intracranial IEDs manifest only as subtle, low-amplitude waveforms below scalp EEG background and could, therefore, not be detected visually. We found that scalp zero-crossing patterns allow detection of these intracranial IEDs on a single-trial level with millisecond temporal precision and including some mesial temporal discharges that do not propagate to the neocortex. Applied to an independent dataset, our method discriminated accurately between patients with epilepsy and normal subjects, confirming its practical applicability.

scholarly journals Raman Spectral Signatures of Serum-Derived Extracellular Vesicle-Enriched Isolates May Support the Diagnosis of CNS Tumors

Cancers ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 1407
Author(s):  
Matyas Bukva ◽  
Gabriella Dobra ◽  
Juan Gomez-Perez ◽  
Krisztian Koos ◽  
Maria Harmati ◽  
...  
Keyword(s):  
Lumbar Disc ◽  
Area Under The Curve ◽  
Principal Component ◽  
Extracellular Vesicle ◽  
Classification Performance ◽  
Cns Tumors ◽  
Clinical Samples ◽  
Support Vector ◽  
Serum Samples ◽  
Raman Spectroscopic

Investigating the molecular composition of small extracellular vesicles (sEVs) for tumor diagnostic purposes is becoming increasingly popular, especially for diseases for which diagnosis is challenging, such as central nervous system (CNS) malignancies. Thorough examination of the molecular content of sEVs by Raman spectroscopy is a promising but hitherto barely explored approach for these tumor types. We attempt to reveal the potential role of serum-derived sEVs in diagnosing CNS tumors through Raman spectroscopic analyses using a relevant number of clinical samples. A total of 138 serum samples were obtained from four patient groups (glioblastoma multiforme, non-small-cell lung cancer brain metastasis, meningioma and lumbar disc herniation as control). After isolation, characterization and Raman spectroscopic assessment of sEVs, the Principal Component Analysis–Support Vector Machine (PCA–SVM) algorithm was performed on the Raman spectra for pairwise classifications. Classification accuracy (CA), sensitivity, specificity and the Area Under the Curve (AUC) value derived from Receiver Operating Characteristic (ROC) analyses were used to evaluate the performance of classification. The groups compared were distinguishable with 82.9–92.5% CA, 80–95% sensitivity and 80–90% specificity. AUC scores in the range of 0.82–0.9 suggest excellent and outstanding classification performance. Our results support that Raman spectroscopic analysis of sEV-enriched isolates from serum is a promising method that could be further developed in order to be applicable in the diagnosis of CNS tumors.

Sign in / Sign up

Export Citation Format

Share Document