Fusing datasets from different brain signal modalities improves accuracy in finding biomarkers of neuropsychiatric diseases. Several approaches, such as joint independent component analysis (ICA) and independent vector analysis (IVA), are useful but fall short of exploring multiple associations between different modalities, especially for the case where one underlying component in one modality might have multiple associations with others in another modality. This relationship is possible since one component in a given modality might have associations such as subject covariation with multiple components in another modality. We show that the consecutive independence and correlation transform (C-ICT) model, which successively performs ICA and canonical correlation analysis, is able to discover such multiple associations. C-ICT has been demonstrated to be useful for the fusion of functional magnetic resonance imaging (fMRI) and electroencephalography data but has not been tested for other data combinations. In this study, we apply the C-ICT to fuse fMRI and MRI-based diffusion tensor imaging (DTI) datasets collected from healthy controls and patients with schizophrenia. In addition to independent components that show significant differences between the two groups in the fMRI and DTI datasets separately, we find multiple associations between these components from the two modalities, which provide a unique potential biomarker for schizophrenia.