Open AccessOn The Use of Machine Learning Algorithms to Classify Focal Cortical Dysplasia on MRI
Author(s) -
João Guilherme Nunes Pereira,
Matheus de Freitas Oliveira Baffa,
Fabrício Henrique Simozo,
Leonardo Murta,
Joaquim Cezar Felipe
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/sbcas.2021.16063
Subject(s) - cortical dysplasia , c4.5 algorithm , epilepsy , computer science , artificial intelligence , decision tree , artificial neural network , perspective (graphical) , pattern recognition (psychology) , machine learning , medicine , psychiatry , naive bayes classifier , support vector machine
Refractory epilepsy is a condition characterized by epileptic seizure occurrence which cannot be controlled with antiepileptic drugs. This condition is associated with an excessive neuronal discharge produced by a group of neurons in a certain epileptogenic zone. Focal Cortical Dysplasia (FCD), usually found in these zones, was detected as one of the main causes of refractory epilepsy. In these cases, surgical intervention is necessary to minimize or eliminate the seizure occurrences. However, surgical treatment is only indicated in cases where there is complete certainty of the FCD. In order to assist neurosurgeons to detect precisely these regions, this paper aims to develop a classication method to detect FCD on MRI based on morphological and textural features from a voxel-level perspective. Multiple classiers were tested throughout the extracted features, the best results achieved an accuracy of 91.76% using a Deep Neural Network classier and 96.15% with J48 Decision Tree. The set of evaluating metrics showed that the results are promising.