Publication

Interpreting deep learning models for epileptic seizure detection on EEG signals

Related concepts (33)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Seizure

An epileptic seizure, informally known as a seizure, is a period of symptoms due to abnormally excessive or synchronous neuronal activity in the brain. Outward effects vary from uncontrolled shaking movements involving much of the body with loss of consciousness (tonic-clonic seizure), to shaking movements involving only part of the body with variable levels of consciousness (focal seizure), to a subtle momentary loss of awareness (absence seizure). Most of the time these episodes last less than two minutes and it takes some time to return to normal.

Epilepsy

Epilepsy is a group of non-communicable neurological disorders characterized by recurrent epileptic seizures. An epileptic seizure is the clinical manifestation of an abnormal, excessive, purposeless and synchronized electrical discharge in the brain cells called neurons. The occurrence of two or more unprovoked seizures defines epilepsy. The occurrence of just one seizure may warrant the definition (set out by the International League Against Epilepsy) in a more clinical usage where recurrence may be able to be prejudged.

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

Electroencephalography

Electroencephalography (EEG) is a method to record an electrogram of the spontaneous electrical activity of the brain. The biosignals detected by EEG have been shown to represent the postsynaptic potentials of pyramidal neurons in the neocortex and allocortex. It is typically non-invasive, with the EEG electrodes placed along the scalp (commonly called "scalp EEG") using the International 10–20 system, or variations of it. Electrocorticography, involving surgical placement of electrodes, is sometimes called "intracranial EEG".

Artificial neural network

Artificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.

Seizure types

In the field of neurology, seizure types are categories of seizures defined by seizure behavior, symptoms, and diagnostic tests. The International League Against Epilepsy (ILAE) 2017 classification of seizures is the internationally recognized standard for identifying seizure types. The ILAE 2017 classification of seizures is a revision of the prior ILAE 1981 classification of seizures. Distinguishing between seizure types is important since different types of seizures may have different causes, outcomes, and treatments.

Causes of seizures

Generally, seizures are observed in patients who do not have epilepsy. There are many causes of seizures. Organ failure, medication and medication withdrawal, cancer, imbalance of electrolytes, hypertensive encephalopathy, may be some of its potential causes. The factors that lead to a seizure are often complex and it may not be possible to determine what causes a particular seizure, what causes it to happen at a particular time, or how often seizures occur. Malnutrition and overnutrition may increase the risk of seizures.

Psychogenic non-epileptic seizure

Psychogenic non-epileptic seizures (PNES), which have been more recently classified as functional seizures, are events resembling an epileptic seizure, but without the characteristic electrical discharges associated with epilepsy. PNES fall under the category of disorders known as functional neurological disorders (FND), also known as conversion disorders. These are typically treated by psychologists or psychiatrists. PNES has previously been called pseudoseizures, psychogenic seizures, and hysterical seizures, but these terms have fallen out of favor.

Neural network

A neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.