Dimensionality of ICA in resting-state fMRI investigated by feature optimized classification of independent components with SVM

• Published in: Frontiers in human neuroscience Vol. 9; p. 259
• Main Authors: Wang, Yanlu, Li, Tie-Qiang
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 08.05.2015; Frontiers Media S.A
• Subjects: Accuracy; Algorithms; Artificial intelligence; Automation; Classification; Datasets; Functional magnetic resonance imaging; Functional Neuroimaging; image processing; Independent Component Analysis; Learning algorithms; Machine learning; Magnetic Resonance Imaging; Mimicry; Neuroscience; Noise; Pattern Classification; Physiology; Principal components analysis; Signal processing; Studies; Sweden; image processing; pattern classification; independent component analysis; magnetic resonance imaging; signal processing; functional neuroimaging; machine learning
• DOI: 10.3389/fnhum.2015.00259
• ISSN: 1662-5161

Different machine learning algorithms have recently been used for assisting automated classification of independent component analysis (ICA) results from resting-state fMRI data. The success of this approach relies on identification of artifact components and meaningful functional networks. A limiting factor of ICA is the uncertainty of the number of independent components (NIC). We aim to develop a framework based on support vector machines (SVM) and optimized feature-selection for automated classification of independent components (ICs) and use the framework to investigate the effects of input NIC on the ICA results. Seven different resting-state fMRI datasets were studied. 18 features were devised by mimicking the empirical criteria for manual evaluation. The five most significant (p < 0.01) features were identified by general linear modeling and used to generate a classification model for the framework. This feature-optimized classification of ICs with SVM (FOCIS) framework was used to classify both group and single subject ICA results. The classification results obtained using FOCIS and previously published FSL-FIX were compared against manually evaluated results. On average the false negative rate in identifying artifact contaminated ICs for FOCIS and FSL-FIX were 98.27 and 92.34%, respectively. The number of artifact and functional network components increased almost linearly with the input NIC. Through tracking, we demonstrate that incrementing NIC affects most ICs when NIC < 33, whereas only a few limited ICs are affected by direct splitting when NIC is incremented beyond NIC > 40. For a given IC, its changes with increasing NIC are individually specific irrespective whether the component is a potential resting-state functional network or an artifact component. Using FOCIS, we investigated experimentally the ICA dimensionality of resting-state fMRI datasets and found that the input NIC can critically affect the ICA results of resting-state fMRI data.