Spatially regularized machine learning for task and resting-state fMRI

• Published in: Journal of neuroscience methods Vol. 257; pp. 214 - 228
• Main Authors: Song, Xiaomu, Panych, Lawrence P., Chen, Nan-kuei
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.01.2016
• Subjects: Brain - physiology; Brain Mapping - methods; Computer Simulation; Datasets as Topic; Fingers - physiology; Humans; Linear Models; Magnetic Resonance Imaging - methods; Mental Processes - physiology; Models, Neurological; Motor Activity - physiology; Neural Pathways - physiology; Neuropsychological Tests; Outlier detection; Quantitative fMRI; Reproducibility of Results; Rest; Spatial regularization; Support Vector Machine; Visual Perception - physiology; Outlier detection; Spatial regularization; Support vector machine; Quantitative fMRI
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2015.10.001

•A quantitative method is developed for task- and resting-state fMRI data analysis.•The brain functional mapping is formulated as an outlier detection process.•Support vector machines are used to implement a semi-supervised learning.•Spatial constraints are integrated into the support vector learning.•Salient features are identified for the brain mapping in task- and resting-state. Reliable mapping of brain function across sessions and/or subjects in task- and resting-state has been a critical challenge for quantitative fMRI studies although it has been intensively addressed in the past decades. A spatially regularized support vector machine (SVM) technique was developed for the reliable brain mapping in task- and resting-state. Unlike most existing SVM-based brain mapping techniques, which implement supervised classifications of specific brain functional states or disorders, the proposed method performs a semi-supervised classification for the general brain function mapping where spatial correlation of fMRI is integrated into the SVM learning. The method can adapt to intra- and inter-subject variations induced by fMRI nonstationarity, and identify a true boundary between active and inactive voxels, or between functionally connected and unconnected voxels in a feature space. The method was evaluated using synthetic and experimental data at the individual and group level. Multiple features were evaluated in terms of their contributions to the spatially regularized SVM learning. Reliable mapping results in both task- and resting-state were obtained from individual subjects and at the group level. A comparison study was performed with independent component analysis, general linear model, and correlation analysis methods. Experimental results indicate that the proposed method can provide a better or comparable mapping performance at the individual and group level. The proposed method can provide accurate and reliable mapping of brain function in task- and resting-state, and is applicable to a variety of quantitative fMRI studies.