Discovering brain regions relevant to obsessive–compulsive disorder identification through bagging and transduction

• Published in: Medical image analysis 2014-04, Vol.18 (3), p.435-448
• Main Authors: Parrado-Hernández, Emilio, Gómez-Verdejo, Vanessa, Martínez-Ramón, Manel, Shawe-Taylor, John, Alonso, Pino, Pujol, Jesús, Menchón, José M., Cardoner, Narcis, Soriano-Mas, Carles
• Format: Article
• Language: English
• Subjects: Adult; Algorithms; Artificial Intelligence; Brain - pathology; Brain Mapping - methods; Female; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Machine learning; Magnetic Resonance Imaging - methods; Male; MRI; Nerve Net - pathology; Obsessive-Compulsive Disorder - pathology; Obsessive–compulsive disorder; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; Transduction; Voxel selection
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2014.01.006

[Display omitted] •We apply Machine learning techniques to identify subjects with OCD on the basis of their brain anatomy.•The goal of OCD identification consists of automatically identifying brain regions related to the presence of the disorder.•The voxels relevant for the disease identification are structured in small volume clusters.•The areas are automatically found and they are in high agreement with previous works.•This work can be easily extended to the characterization of other psychiatric disorders. In the present study we applied a multivariate feature selection method based on the analysis of the sign consistency of voxel weights across bagged linear Support Vector Machines (SVMs) with the aim of detecting brain regions relevant for the discrimination of subjects with obsessive–compulsive disorder (OCD, n=86) from healthy controls (n=86). Each participant underwent a structural magnetic resonance imaging (sMRI) examination that was pre-processed in Statistical Parametric Mapping (SPM8) using the standard pipeline of voxel-based morphometry (VBM) studies. Subsequently, we applied our multivariate feature selection algorithm, which also included an L2 norm regularization to account for the clustering nature of MRI data, and a transduction-based refinement to further control overfitting. Our approach proved to be superior to two state-of-the-art feature selection methods (i.e., mass-univariate t-Test selection and recursive feature elimination), since, following the application of transductive refinement, we obtained a lower test error rate of the final classifier. Importantly, the regions identified by our method have been previously reported to be altered in OCD patients in studies using traditional brain morphometry methods. By contrast, the discrimination patterns obtained with the t-Test and the recursive feature elimination approaches extended across fewer brain regions and included fewer voxels per cluster. These findings suggest that the feature selection method presented here provides a more comprehensive characterization of the disorder, thus yielding not only a superior identification of OCD patients on the basis of their brain anatomy, but also a discrimination map that incorporates most of the alterations previously described to be associated with the disorder.