Neurologists are getting help from motion recognition technology as they study the behaviour of patients during seizure.
As reported, the tech would help by providing clues on the sub-type of epilepsy the patient has and identifying the unusual seizure movements that require further investigation.
Analysis of movements during seizures provides clues as to where the focus of the epilepsy may be, which in turn allows for a successful surgery.
The Problem
This is critical since 30% of people with epilepsy did not respond to medication and surgery presents an opportunity at acquiring seizure freedom.
A Queensland University of Technology PhD researcher from the School of Electrical Engineering and Computer Science said that diagnosis and localisation of the brain networks affected by epilepsy involved the following:
- A clinical history
- Neuro-imaging using MRI, CT scans and functional MRI
- A non-invasive scalp EEG where electrodes are applied to the patient’s scalp to record the brain electrical activity while the patient is being recorded on video over 24 hours
- Intracranial recording methods that are employing electrodes, which are placed surgically
Epilepsy has multiple types and all of them have different symptomatology. Many forms of epilepsy have characteristic movements during a seizure, allowing an understanding of underlying networks.
Epileptologists spend a lot of time analysing videos and EEGs to unravel the underlying epileptic network, which require years of training and experience.
Having objective quantitative information would assist in developing and formulating a diagnosis in situations where this expertise in unavailable.
Doctors must be able to accurately pinpoint the epileptogenic region prior to operating because surgery on the brain is highly complex.
The Solution
An artificial intelligence (AI) and video analytics technology, developed by the University, was used in conjunction with Queensland’s only tertiary referral public epilepsy surgery centre.
The tech analysed hospital monitoring videos of 39 patients and 161 seizures.
The aim was to address the problem of modelling the patient’s behaviour with objective and quantitative motion analysis.
The research was expanded to include identification of aberrant or unusual movements that did not fit the typical features associated with the most common forms of epilepsy.
The common forms are the mesial temporal and extratemporal lobe epilepsy.
The program recognises the most common types of movements and would alert doctors if it finds activities that do not fit the known categories.
This technology is unique and provides important supplementary and unbiased data to defining the underlying epileptic network.
It is a significant complementary resource in the era of seizure-based detection through electrophysiological data.
Future Plans
The next stage of the research will see exploration of methodologies that could jointly learn across visually observed motions and brain electrical activity to provide precise localisation of epilepsy.
These techniques can be used to support neurologists in identifying the type of epilepsy, as well as in understanding the temporal evolution of seizures, from their onset through to termination.
Moreover, the technology could be potentially useful in the evaluation of broader neurological diseases that experience movement disorders such as stroke and dementia.