Impact of Circularity Analysis on Classification Results: A Case Study in the Detection of Cocaine Addiction Using Structural MRI

• Published in: Advanced Techniques for Knowledge Engineering and Innovative Applications pp. 101 - 114
• Main Authors: Termenon, Maite, Fernández, Elsa, Graña, Manuel, Barrós-Loscertales, Alfonso, Bustamante, Juan C., Ávila, César
• Format: Book Chapter
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2013
• Series: Communications in Computer and Information Science
• Subjects: Circularity; Classification; Computer Aided Diagnosis; Double Dipping; ELM; Machine Learning; MRI; Pattern Recognition; SVM
• ISBN: 9783642420160; 3642420168
• ISSN: 1865-0929; 1865-0937
• DOI: 10.1007/978-3-642-42017-7_8

Due to the high dimensionality of the neuroimaging data, it is common to select a subset of relevant information from the whole dataset. The inclusion of information of the complete dataset during that selection of a subset, can drive to some bias in the results, often leading to optimistic conclusions. In this study, the differences in results obtained performing an experiment free of circularity and repeating the process including a circularity effect (Double-Dipping (DD)) are shown. Discriminant features (based on voxel’s intensity values) are obtained from structural Magnetic Resonance Imaging (MRI) to train and test classifiers that are able to discriminate cocaine dependent patients from healthy subjects. Feature selection is done by computing Pearson’s correlation between voxel values across subjects with the subject class as control variable. As classifiers, several machine learning techniques are used: k-Nearest Neighbor (k-NN), Support Vector Machines (SVM), Extreme Learning Machines (ELM) and Learning Vector Quantization (LVQ). Feature selection process with DD obtains, in general, higher accuracy, sensitivity and specificity values.