Multimodal Neuroimaging in Schizophrenia: Description and Dissemination

Abstract

In this paper we describe an open-access collection of multimodal neuroimaging data in schizophrenia for release to the community. Data were acquired from approximately 100 patients with schizophrenia and 100 age-matched controls during rest as well as several task activation paradigms targeting a hierarchy of cognitive constructs. Neuroimaging data include structural MRI, functional MRI, diffusion MRI, MR spectroscopic imaging, and magnetoencephalography. For three of the hypothesis-driven projects, task activation paradigms were acquired on subsets of ~200 volunteers which examined a range of sensory and cognitive processes (e.g., auditory sensory gating, auditory/visual multisensory integration, visual transverse patterning). Neuropsychological data were also acquired and genetic material via saliva samples were collected from most of the participants and have been typed for both genome-wide polymorphism data as well as genome-wide methylation data. Some results are also presented from the individual studies as well as from our data-driven multimodal analyses (e.g., multimodal examinations of network structure and network dynamics and multitask fMRI data analysis across projects). All data will be released through the Mind Research Network's collaborative informatics and neuroimaging suite (COINS).

Keywords: COBRE; COINS; DTI; Genetics; ICA; MATRICS; MEG; Magnetoencephalography; Memory; Multimodal integration; Neuroimaging; Schizophrenia; Sensory gating; Spectroscopy; Transverse patterning; fMRI.

Fig. 1

Complementary networks investigated in the four projects. Project 1 (P1, red arrows) explored the functional connectivity between the superior temporal gyrus (STG), hippocampus and prefrontal cortex (PFC) during auditory sensory gating. Project 2 (P2, yellow) examined the integration of simultaneously presented visual and auditory information in primary sensory and secondary cortical regions such as the occipital lobe (Occ), superior and inferior parietal lobe (SPL and IPL, respectively), the STG and the superior temporal sulcus (STS). The coherence between PFC and a hippocampal circuit was studied in Project 3 during a visual transverse patterning task (P3, blue). Project 4 (P4, green) examined structural connectivity between the cingulate gyrus (CG), PFC and caudate-putamen (CP)

Fig. 2

Brain regions showing significant group differences between SP (warm colors) and HC (cool colors) during the attend-visual (AV) condition. Locations of the sagittal (X) and axial (Z) slices are given according to the Talairach atlas (Talairach and Tournoux 1988) for the left (L) and right (R) hemispheres. Adapted from Mayer et al.

Fig. 3

Upper left panel: Reaction times (RTs) to auditory, visual and AV stimuli in SP relative to HC from Stone et al. (2014). Lower left panel: Example of differences in gamma band power in SP vs. HC time-frequency maps. Frequency is represented on the y axis while time in ms is represented on the x axis. In this example gamma band power was greater in HC relative to SP (see black box). Upper right panel: Joint ICA component of fractional anisotropy (FA) consistent with the superior longitudinal fasciculus showed larger FA in HC vs. SP. Similarly, the MEG signal over occipital cortex was significantly greater in HC (red solid line) vs. SP (red dashed line). The joint component weighting factor positively predicted performance on the MATRICS cognitive battery suggesting that visual processing and structures that link visual cortex to frontal regions are important for cognitive performance

Fig. 4

a. Project 3 task relationships for the nonverbal TP task. The 6 images represent the 6 possible stimulus pairings per trial. Each pairing is presented randomly and sequentially to the participant. The participant was asked to choose the correct stimulus in each pairing using a mouse button press (asterisks indicate the stimulus choice). b. Hippocampal and PFC activation from the sLORETA analysis, plotted on one HC’s MRI for each version of TP. These images show the most common activation pattern for HC. c. Performance results for nonverbal and verbal versions of the TP and Elemental (EL; control) tasks. d. Red tracts indicate where FA values were lower for SP compared to HC in the uncinate fasciculus (green = the uncinate fasciculus skeleton)

Fig. 5

a. ¹HMRS slice location. b. A representative fit by LCModel to a spectrum from a voxel within primarily gray matter. C. Plots of first scan vs. second scan data for NAA and Glu for all voxels from all subjects with and without partial volume and relaxation correction, respectively. Adapted from Gasparovic et al.

Fig. 6

Left panel. Maps of the components identified as non-artifactual in static FNC or dynamic FNC analysis: Of the 75 components returned by the GICA, 45 were identified as non-artifactual components. Only 34 of these non-artifactual components showed static FNC or dynamic FNC effects; these 34 components were divided into groups based on their anatomical and functional properties and include visual network, thalamic network, cerebellar network, frontal network, attentional network, default mode network, sensory motor network, and auditory networks. Only 6 components, representing the thalamic (C12, C51) and auditory networks (C28, C38, C62, C71) are shown. Color bars at the right represent z-scores. Right panel. a. Static FNC matrix (lower part). Pairwise correlations of component pairs showed static FNC effects at α > 0.001 level. b. Dynamic FNC matrix (upper part). Pairwise correlations of component pairs showed dynamic FNC effects at the α ≤ 0.001 level. Thal = thalamus network, CR = Cerebellar network. Adapted from Cetin et al.

Fig. 7

a. Dashed red lines represent median values of Public and Private AUCs. Blue contours indicate the centration of entries. The 3 winning entries are shown as green squares at the upper right. 1st and 2nd place entries attained lower public AUCs because the official ranking optimized for extremes along the x-axis only. b. Overall AUC of all 2087 entries. Dashed red line indicates the median. Orange/yellow triangle indicates the competition benchmark (just above the median). No entry was able to attain an overall AUC of 0.9 or higher. Adapted from Silva et al.

Fig. 8

Summary of FNC group averages (SP and HC) for fMRI and MEG rendered on white matter surface. P = HC > SP and N = SP > HC. FNC is a measure of among- network connectivity; that is, pairwise correlations in network (ICA component) timecourses. Only those regions involved in significant group differences are included. Color bar values are the mean correlations for each component and group. Importantly, the MEG and fMRI results were quite different from one another (i.e., greater FNC was observed in HC visual networks for fMRI components while greater FNC was evident in SP frontal networks for MEG components (blue color), highlighting the complementary information embedded within these two modalities. We adjusted for multiple comparisons within each network matrix using the false discovery rate correction. Adapted from Houck et al.

Fig. 9

COINS webportal (coins.mrn.org/dx). Instructions for accessing data