The children and young people's epilepsy charity
A- A A+
Donate Shop Careers Main Number: 01342 832243 (Mon-Fri, 8:30am-5pm)
Helpline: 01342 831342 (Mon-Fri, 9am-3pm)

picture of an MRI scan

New technology offers new hope for children with drug-resistant epilepsy

  • New research has found subtle epileptic brain abnormalities on MRI scans can be automatically detected in children.
  • Young Epilepsy hails research as ‘hugely significant’ for paediatric neurology.
  • These brain abnormalities can be difficult for trained radiologists to see.
  • This advance could lead to more children with drug-resistant epilepsy being offered the option of surgery.
  • A major cause of epilepsy in children is Focal Cortical Dysplasia, where an area of the brain has formed abnormally. These abnormalities are small and subtle and therefore notoriously difficult to accurately visualise on MRI. They are often missed on normal MRI scans and are especially difficult to spot in children as their brains are still rapidly developing.

    Research conducted collaboratively by Young Epilepsy, UCL Great Ormond Street Institute of Child Health and the University of Cambridge, has been developing more accurate imaging techniques to identify these abnormalities in children.

    A paediatric neuroradiologist identified these subtle abnormalities in all patients included in our study. The team then calculated a range of features from 3D reconstructions of the patient’s brains, such as the thickness and folding of the brain as well as the intensity of the MRI scan. These features were used to train a computer to identify abnormal brain tissue.

    The computer classifier was correctly able to identify the brain abnormality in 73% of patients. Importantly, the algorithm can be applied to new patients to help radiologists identify abnormalities in difficult cases.

    Sophie Adler, who conducted the research at UCL GOS Institute of Child Health, says:

    Our computerised classifier was able to correctly detect the epileptic abnormalities in 73 percent of the patients. It even worked in the very young patients. This shows great technological progress and now we’re planning to go one step further by testing the programme on new patients with abnormalities that the neuroradiologist can’t currently identify. The hope is that more children with drug-resistant epilepsy will be able to be considered for epilepsy surgery, and the surgery itself will have greater accuracy and therefore higher chances of freedom from seizures.

    Professor Helen Cross, the Prince of Wales's Chair of Childhood Epilepsy, says:

    This work will significantly contribute to determining further children with drug resistant epilepsy who may be suitable for resective surgery and consequent cure of their epilepsy.

    Rosemarie Pardington, the Director of Integrated Care for Young Epilepsy, says:

    This research is hugely significant for the field of paediatric neurology. More young people could now receive a life-changing opportunity to spend their adulthoods without epilepsy. Young Epilepsy’s research partnership with Great Ormond Street Hospital and UCL GOS Institute of Child Health works to deliver ground-breaking results like this, to continually improve support, treatment and outcomes for children and young people with epilepsy.

    What is the next step for this research

    The next step is to test the classifier on new, more complex patients’ scans and work out how best to incorporate these types of technologies in to clinical practice.

    Read the article in the Huffington Post

    Read the full research study

    Share with friends

    Cyber EssentialsFundraising RegulatorYoung Epilepsy is the operating name of The National Centre for Young People with Epilepsy Charitable Trust.
    Registered Charity number 311877 (England and Wales)

    We use cookies to improve our website and your experience when using it. Cookies used for the essential operation of the site have already been set. To find out more about the cookies we use and how to delete them, see our Privacy Policy.

    I accept cookies from this site
    EU Cookie Directive plugin by