Epilepsy is the fourth most common neuropathy associated with sporadic, recurrent, and abnormal electrical activity in the brain called seizures. It affects people of all ages at every stage of life. About 2.5 million people are diagnosed with epilepsy each year. As of today, the drug does not help completely cure epilepsy. If the drug doesn’t work, your doctor will have to have epilepsy surgery. Only 80% of patients have some control and treatment of seizures with the best available treatments. The remaining patients continue to experience seizures despite medication, surgery, or diet. Epilepsy diagnosis must be made in a timely manner in order to initiate treatment that reduces the risk of future seizures.
EEG is an effective method commonly used for monitoring the brain activity diagnosis of epilepsy.But, visual inspection of EEG for seizure detection by expert neurologists is a timeconsuming as well as laborious process and the diagnosis may not be accurate because of the massive amounts of EEG data and the discrepant clinical judgment standards of different neurologists. So, rapid recognition of seizures through automated systems could potentially decrease morbidity and mortality in epilepsy.
- Study and explore the existing epilepsy detection techniques
- Develop a new deep learning based automatic Epilepsy Detection system
- Evaluate and validate the proposed deep learning framework
- Develop a website that will ease the burden of the neurologists and help the patients in alarming them before the seizure occurs.