Detection of Lesions Underlying Intractable Epilepsy on T1-Weighted MRI as an Outlier Detection Problem

• Published in: PloS one Vol. 11; no. 9; p. e0161498
• Main Authors: El Azami, Meriem, Hammers, Alexander, Jung, Julien, Costes, Nicolas, Bouet, Romain, Lartizien, Carole
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 07.09.2016; Public Library of Science (PLoS)
• Subjects: Abnormalities; Algorithms; Biology and Life Sciences; Brain; Brain damage; Brain research; Classification; Computer and Information Sciences; Computer simulation; Data analysis; Deviation; Diagnosis; Diagnosis, Computer-Assisted; Drug Resistant Epilepsy - diagnosis; Drug Resistant Epilepsy - diagnostic imaging; Drug Resistant Epilepsy - physiopathology; Engineering and Technology; Epilepsy; Female; Humans; Image detection; Image Interpretation, Computer-Assisted; Learning algorithms; Lesions; Life Sciences; Machine learning; Magnetic resonance; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical imaging; Medicine and Health Sciences; Methods; Multivariate analysis; Neural networks; Neurosciences; NMR; Nuclear magnetic resonance; Outliers (statistics); Patients; Pattern recognition; Pattern Recognition, Automated; Research and Analysis Methods; Science; Statistical analysis; Substantia alba; Support Vector Machine; Support vector machines; Systematic review; France

Pattern recognition methods, such as computer aided diagnosis (CAD) systems, can help clinicians in their diagnosis by marking abnormal regions in an image. We propose a machine learning system based on a one-class support vector machine (OC-SVM) classifier for the detection of abnormalities in magn...