Abstract
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 magnetic resonance images (MRI) applied to patients with intractable epilepsy. The system learns the features associated with healthy control subjects, allowing a voxelwise assessment of the deviation of a test subject pattern from the learned patterns. While any number of various features can be chosen and learned, here we focus on two texture parameters capturing image patterns associated with epileptogenic lesions on T1-weighted brain MRI e.g. heterotopia and blurred junction between the grey and white matter. The CAD output consists of patient specific 3D maps locating clusters of suspicious voxels ranked by size and degree of deviation from control patterns. System performance was evaluated using realistic simulations of challenging detection tasks as well as clinical data of 77 healthy control subjects and of eleven patients (13 lesions). It was compared to that of a mass univariate statistical parametric mapping (SPM) single subject analysis based on the same set of features. For all simulations, OC-SVM yielded significantly higher values of the area under the ROC curve (AUC) and higher sensitivity at low false positive rate. For the clinical data, both OC-SVM and SPM successfully detected 100% of the lesions in the MRI positive cases (3/13). For the MRI negative cases (10/13), OC-SVM detected 7/10 lesions and SPM analysis detected 5/10 lesions. In all experiments, OC-SVM produced fewer false positive detections than SPM. OC-SVM may be a versatile system for unbiased lesion detection.
Highlights
Malformative brain lesions occurring during cortical development are regularly associated with pharmacoresistant focal epilepsy
We propose a machine learning system based on a one-class support vector machine (OC-support vector machines (SVM)) classifier for the detection of abnormalities in magnetic resonance images (MRI) applied to patients with intractable epilepsy
The alternate solution is to perform comparisons between a patient and a cohort of normal subjects [16, 18, 19]. In these studies of focal cortical dysplasias (FCDs) mapping, discriminant features were extracted at the voxel level from structural magnetic resonance imaging (MRI) and fed into a mass univariate statistical analysis based on a general linear model (GLM)
Summary
Malformative brain lesions occurring during cortical development are regularly associated with pharmacoresistant focal epilepsy. The alternate solution is to perform comparisons between a patient and a cohort of normal subjects [16, 18, 19] In these studies of FCD mapping, discriminant features were extracted at the voxel level from structural MRI and fed into a mass univariate statistical analysis based on a general linear model (GLM). We propose a novel flexible classification method combining textural maps [23] relevant for FCD and heterotopia associated abnormalities and a one-class support vector machine (OC-SVM) [24] that is trained with ‘negative’ (normal) examples from a control database only. We assumed that the OC-SVM score distribution of any given test patient can be represented by this normative score distribution considering that it is not influenced by the small fraction of outlier examples (
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
