This article aims to design a regression model to successfully predict clinical scores based on features provided by multimodal magnetic resonance (MR) images. We propose a multimodal MR predictive analysis pipeline with nonlinear support vector regression (SVR). Firstly, feature selection methods are elaborately chosen according to different feature characteristics for each modality. For features extracted from structural MR images and diffusion MR images, Support Vector Machine-Recursive Feature Elimination with Correlation Bias Reduction (SVMRFE+CBR) is applied to select predictive features and eliminate the high intra-correlations exist in the original features. For functional features, sparse coding (SC) considers multiple features’ combination for group predictiveness but cost less computation. After feature selection, the single radial bias function (RBF) kernels are calculated based on the modalities’ respectively selected features. A multi-RBF kernel is calculated by weighted-sum of single RBF kernels, and the kernel finally serves for the multimodal SVR model. Our proposed framework is tested on an online schizophrenia (SZ) dataset with 171 subjects from two study cohorts using 10-fold cross-validation (CV). The models are trained by the subjects’ clinicalrelated scores in Positive and Negative Syndrome Scale (PANSS) to be able to give the estimated scores as precisely as possible. The experimental results show that our proposed model can successfully predict clinical scores. Further comparative test results show that the proposed multimodal model can improve predictiveness compared with single modal ones, and our choice of feature selection methods plays an important role in the good performance.
Schizophrenia (SZ) is one of the important brain diseases. Multimodal magnetic resonance (MR) images provide the important imaging biomarkers to detect the pathological changes in both brain function and anatomy for SZ diagnosis. In this paper, we propose a multi-modal image classification algorithm based on sparse coding and random forest to combine the structural and functional MR brain image analysis for SZ diagnosis. First, the structural and functional MR images are processed to extract the anatomical features and functional connectivity measures for representation. Second, for each modality, sparse coding is used for initial feature selection and the selected features are used as input for random forest (RF) models to calculate a proximity matrix for each modality. Third, the features from the two modalities are combined by linear combination of two proximity matrices into one matrix and the classical multidimensional scaling (MDS) is applied to the proximity matrix for dimensionality reduction. Finally, the reduced matrices are served as inputs for the RF models for multi-modal classification. Our proposed algorithm is tested on the structural and functional MRIs for classification of SZ and healthy controls. Both sparse coding and RF have capability of estimating the potential relationship among various features to reach an ideal group discriminating performance. Experimental results show the effectiveness of the proposed multimodal classification method for SZ diagnosis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.