EEG-Based Brain Disorders Diagnosis through Deep Neural Networks
Abstract. In most cases, the diagnosis of brain disorders such as epilepsy or a brain tumor is slow and requires endless visits to doctors and electroencephalogram (EEG) technicians. This project aims to automate brain disorder diagnosis by using Artificial Intelligence and deep learning. There are many brain disorders can be detected by reading an Electroencephalography. Using an EEG device and collecting the electrical signals directly from the brain with a noninvasive procedure gives significant information about its health. Classifying and detecting anomalies on these signals is what doctors currently do when reading an Electroencephalography. With the right amount of data and the use of machine learning models, it could be possible to learn and classify these signals into groups like (i.e: anxiety, epilepsy spikes, abnormal tumor activity, etc). Subsequently, a trained Neural Network would interpret those signals and identify evidence of a disorder to automate the detection and classification of those disorders found. Results are promising, with classification accuracy of 99.69% for epilepsy and 85.04% for brain tumo.
paper: https://github.com/gmaggiotti/brain-disorders-prediction/blob/master/doc/Automated%20Brain%20Disorders%20Diagnosis.pdf
poster: https://github.com/gmaggiotti/brain-disorders-prediction/blob/master/doc/mlss-A0.pdf