Sunday, September 25, 2022
HomeEntertainmentBrain Anomaly Detection AI Algorithm May Aid In the Treatment of Epilepsy

Brain Anomaly Detection AI Algorithm May Aid In the Treatment of Epilepsy

- Advertisement -
- Advertisement -

Brain Anomaly Detection AI Algorithm May Aid In the Treatment of Epilepsy

The findings showed that in 67 percent of the cohort instances, the AI system was successful in detecting the FCD.


• Finding hidden lesions may be made simpler using the MELD algorithm.
• Epilepsy affects about 600,000 persons in the UK.
• Epilepsy that is drug-resistant is commonly brought on by brain regions called FCDs.

Today I am going to write about technology updates today: A brain anomaly-detecting AI programme might aid in the treatment of epilepsy. Read the full article to know more about this news.

An artificial intelligence (AI) algorithm that can spot tiny brain irregularities that cause epileptic seizures has been developed by a multidisciplinary research team headed by UCL.

More than 1,000 patient MRI images from 22 international epilepsy centers were used to construct the algorithm for the Multicentre Epilepsy Lesion Detection project (MELD), which reports the locations of abnormalities in patients of drug-resistant focal cortical dysplasia (FCD), a significant cause of epilepsy.

Also Read: Residents Protest After Five Weeks of Strict Zero Covid Measures in Shanghai

FCDs are Areas of The Brain Anomaly Detection AI Algorithm  that have wrongly developed and Frequently Cause Drug-Resistant Epilepsy:

Brain Anomaly Detection
Medical Buyer

Surgery is typically used to treat it, but because MRI scans for FCDs might look normal, detecting the lesions on an MRI is a continuing challenge for clinicians.

About 300,000 locations in the brain were used by the researchers to measure cortical features obtained from the MRI images, such as how thick or folded the cortex/brain surface was.

On the basis of their patterns and characteristics, cases that experienced radiologists had diagnosed as either having FCD or being a healthy brain were used to train the algorithm.

According to the findings, which were published in Brain, the algorithm was generally successful in recognizing the FCD in 67 percent of occurrences in the cohort (538 participants).

On the Basis of Their MRI Findings, Radiologists had previously been unable to identify the Anomalies in 178 of the Patients

Brain Anomaly Detection
Gadgets 360

However, in 63 percent of these instances, the MELD algorithm was successful in identifying the FCD.

It is important to do this because, if medical professionals can locate the aberration in the brain scan, surgery to remove it might lead to a recovery.

A Co-First Author from the UCL Great Ormond Street Institute of Child Health, Mathilde Ripart, Said

Brain Anomaly Detection
Interesting Engineering

“Our main goal was to create an interpretable AI system that could help doctors with their decision-making. The doctors being shown how the MELD algorithm produced its forecasts was a vital step in the process.

A senior author from the UCL Queen Square Institute of Neurology, Dr. Konrad Wagstyl, added: “Children and adults with epilepsy may be more likely to have these hidden lesions found thanks to this algorithm, increasing the number of patients who could potentially benefit from brain surgery to treat their condition and enhance cognitive function.

In England, roughly 440 children may benefit from epilepsy surgery each year.

One percent of the world’s population suffers from epilepsy, a serious neurological condition characterised by recurring seizures.

The affected population in the UK is about 600,000. Pharmaceuticals can be used to treat the majority of epilepsy patients, albeit 20–30% of them do not respond well to them.

FCD is the third most common cause in both adults and children who have undergone surgery to manage their epilepsy.

Furthermore, in persons with brain abnormalities that cannot be observed on an MRI scan, FCD is the most common cause of epilepsy.

Helmholtz Munich Co-First Author Dr. Hannah Spitzer Said

“Our algorithm detects lesions by itself using tens of thousands of patient MRI data. It can correctly identify lesions of various types, shapes, and sizes, including some that radiologists had previously missed.

Dr. Sophie Adler, a co-senior author from the Great Ormond Street Institute of Child Health at University College London, added: “We think that this technology could help to find abnormalities that are now being missed and lead to epilepsy. Long-term, it might enable more epilepsy sufferers to get potentially curative brain surgery.

This FCD detection study is able to recognize all FCD subtypes since it uses the largest MRI cohort of FCDs to date.

Study Restrictions

The 22 hospitals involved in the study used a range of MRI scanners from different countries, which strengthened the algorithm but may have also impacted its sensitivity and specificity.

For more such news related to technology updates today and all important global news do visit on our website.

- Advertisement -
- Advertisment -

Most Popular

Recent Comments

%d bloggers like this: