Combination of Resting State fMRI, DTI, and sMRI Data to Discriminate Schizophrenia by N-way MCCA + jICA

Abstract

Multimodal brain imaging data have shown increasing utility in answering both scientifically interesting and clinically relevant questions. Each brain imaging technique provides a different view of brain function or structure, while multimodal fusion capitalizes on the strength of each and may uncover hidden relationships that can merge findings from separate neuroimaging studies. However, most current approaches have focused on pair-wise fusion and there is still relatively little work on N-way data fusion and examination of the relationships among multiple data types. We recently developed an approach called "mCCA + jICA" as a novel multi-way fusion method which is able to investigate the disease risk factors that are either shared or distinct across multiple modalities as well as the full correspondence across modalities. In this paper, we applied this model to combine resting state fMRI (amplitude of low-frequency fluctuation, ALFF), gray matter (GM) density, and DTI (fractional anisotropy, FA) data, in order to elucidate the abnormalities underlying schizophrenia patients (SZs, n = 35) relative to healthy controls (HCs, n = 28). Both modality-common and modality-unique abnormal regions were identified in SZs, which were then used for successful classification for seven modality-combinations, showing the potential for a broad applicability of the mCCA + jICA model and its results. In addition, a pair of GM-DTI components showed significant correlation with the positive symptom subscale of Positive and Negative Syndrome Scale (PANSS), suggesting that GM density changes in default model network along with white-matter disruption in anterior thalamic radiation are associated with increased positive PANSS. Findings suggest the DTI anisotropy changes in frontal lobe may relate to the corresponding functional/structural changes in prefrontal cortex and superior temporal gyrus that are thought to play a role in the clinical expression of SZ.

Keywords: ALFF; DTI; GM; mCCA + jICA; multimodal fusion; resting state fMRI; sMRI; schizophrenia.

Figure 1

N-way mCCA + jICA fusion strategy of for real human data (n = 3 in this study).

Figure 2

Group-discriminating regions across three modalities, with a threshold of |Z| > 2.5. Two-sample t-tests were performed on mixing coefficients of each IC for each modality. If the components of the same index show group differences in more than one modality, they are called modality-common (or joint) group-discriminative ICs in green frames; otherwise, it is called a modality-unique group-discriminative IC, e.g., GM_IC5, ALFF_IC3 in red frames.

Figure 3

The scatter plots and linear trends of components with significant correlation between positive PANSS score and its loadings.

Figure 4

Classification accuracy based on selected group-discriminative components from mCCA + jICA for seven modal combinations.