Deep Learning Approach for Epileptic Focus Localization

The task of epileptic focus localization receives great attention due to its role in an effective epileptic surgery. The clinicians highly depend on the intracranial EEG data to make a surgical decision related to epileptic subjects suffering from uncontrollable seizures. This surgery usually aims to remove the epileptogenic region which requires precise characterization of that area using the EEG recordings. In this paper, we propose two methods based on deep learning targeting accurate automatic epileptic focus localization using the non-stationary EEG recordings. Our first proposed method is based on semi-supervised learning, in which a deep convolutional autoencoder is trained and then the pre-trained encoder is used with multi-layer perceptron as a classifier. The goal is to determine the location of the EEG signal that is responsible for the epileptic activity. In the second proposed method, unsupervised learning scheme is implemented by merging deep convolutional variational autoencoder and K-means algorithm for clustering the iEEG signals into two distinct clusters based on the seizure source. The proposed methods automate and integrate the features extraction and classification processes instead of manually extracting the features as done in the previous studies. Dimensionality reduction is achieved using the autoencoder, while the important spatio-temporal features are extracted from the EEG recordings using the convolutional layers. Moreover, we implemented the inf...
Source: IEEE Transactions on Biomedical Circuits and Systems - Category: Biomedical Engineering Source Type: research

Related Links:

Authors: Zhang B, Wang W, Xiao Y, Xiao S, Chen S, Chen S, Xu G, Che W Abstract Electroencephalography (EEG) plays an import role in monitoring the brain activities of patients with epilepsy and has been extensively used to diagnose epilepsy. Clinically reading tens or even hundreds of hours of EEG recordings is very time consuming. Therefore, automatic detection of seizure is of great importance. But the huge diversity of EEG signals belonging to different patients makes the task of seizure detection much challenging, for both human experts and automation methods. We propose three deep transfer convolutional neural...
Source: Computational and Mathematical Methods in Medicine - Category: Statistics Tags: Comput Math Methods Med Source Type: research
Authors: Bi A, Ying W, Zhao L Abstract The diagnosis and treatment of epilepsy is a significant direction for both machine learning and brain science. This paper newly proposes a fast enhanced exemplar-based clustering (FEEC) method for incomplete EEG signal. The algorithm first compresses the potential exemplar list and reduces the pairwise similarity matrix. By processing the most complete data in the first stage, FEEC then extends the few incomplete data into the exemplar list. A new compressed similarity matrix will be constructed and the scale of this matrix is greatly reduced. Finally, FEEC optimizes the new ...
Source: Computational and Mathematical Methods in Medicine - Category: Statistics Tags: Comput Math Methods Med Source Type: research
Publication date: Available online 27 May 2020Source: NeurocomputingAuthor(s): S. Raghu, Natarajan Sriraam, Erik D Gommer, Danny M W Hilkman, Yasin Temel, Shyam Vasudeva Rao, Pieter L Kubben
Source: Neurocomputing - Category: Neuroscience Source Type: research
ConclusionsAcute symptomatic seizures are possible in patients with COVID-19 disease. These seizures are likely multifactorial in origin, including cortical irritation due to blood –brain barrier breakdown, precipitated by the cytokine reaction as a part of the viral infection. Patients with clinical signs of seizures or otherwise unexplained encephalopathy may benefit from electroencephalography monitoring and/or empiric anti-epileptic therapy. Further studies are needed to elucidate the risk of seizures and benefit of monitoring in this population.
Source: Neurocritical Care - Category: Neurology Source Type: research
Jul 24, 2020. . Sponsored by RME Collaborative (Rural Medical Education)
Source: Rural events via the Rural Assistance Center - Category: Rural Health Source Type: events
Publication date: September 2020Source: Epilepsy &Behavior, Volume 110Author(s): Andrija Javor, Laura Zamarian, Gerhard Ransmayr, Manuela Prieschl, Melanie Bergmann, Gerald Walser, Gerhard Luef, Wolfgang Prokop, Margarete Delazer, Iris Unterberger
Source: Epilepsy and Behavior - Category: Neurology Source Type: research
AbstractDeficiency of the endoplasmic reticulum transmembrane proteinARV1 leads to epileptic encephalopathy in humans and in mice.ARV1 is highly conserved, but its function in human cells is unknown. Studies of yeastarv1 null mutants indicate that it is involved in a number of biochemical processes including the synthesis of sphingolipids and glycosylphosphatidylinositol (GPI), a glycolipid anchor that is attached to the C-termini of many membrane bound proteins. GPI anchors are post-translational modifications, enabling proteins to travel from the endoplasmic reticulum (ER) through the Golgi and to attach to plasma membra...
Source: Neurogenetics - Category: Genetics & Stem Cells Source Type: research
We describe the epidemiology of early and late seizures follow...
Source: SafetyLit - Category: International Medicine & Public Health Tags: Ergonomics, Human Factors, Anthropometrics, Physiology Source Type: news
Spinocerebellar ataxia type 10 (SCA10), one of the autosomal dominant ataxias, is characterized by slowly progressive gait ataxia, dysarthria, nystagmus, epilepsy as well as non-motor symptoms [1]. The latter include dysautonomia, cognitive deficits, chronic pain, psychiatric comorbidities and sleep disorders [ [1,2]]. SCA10 is caused by expansion of ATTCT pentanucleotide repeats in the ATXN10 gene – which codes for ataxin 10 [ [1–3]]. Recent experimental data suggested a possible relationship between SCA10 and development of cancer [4].
Source: Parkinsonism and Related Disorders - Category: Neurology Authors: Tags: Correspondence Source Type: research
ConclusionsOur study first described the ophthalmic and neurologic characteristics of a small cohort of unrelated mainland Chinese patients with sialidosis type 1. We found that c.544A>G (p. S182G) might be a hotspot variant in Chinese patients. The accumulation of metabolic products in the nerve fiber and ganglion cell layers is a characteristic ocular finding that could be sensitively detected by OCT and FAF imaging.
Source: Molecular Genetics & Genomic Medicine - Category: Genetics & Stem Cells Authors: Tags: ORIGINAL ARTICLE Source Type: research
More News: Biomedical Engineering | Epilepsy | Learning | Study | Universities & Medical Training