Group ICA for identifying biomarkers in schizophrenia: 'Adaptive' networks via spatially constrained ICA show more sensitivity to group differences than spatio-temporal regression

Abstract

Brain functional networks identified from fMRI data can provide potential biomarkers for brain disorders. Group independent component analysis (GICA) is popular for extracting brain functional networks from multiple subjects. In GICA, different strategies exist for reconstructing subject-specific networks from the group-level networks. However, it is unknown whether these strategies have different sensitivities to group differences and abilities in distinguishing patients. Among GICA, spatio-temporal regression (STR) and spatially constrained ICA approaches such as group information guided ICA (GIG-ICA) can be used to propagate components (indicating networks) to a new subject that is not included in the original subjects. In this study, based on the same a priori network maps, we reconstructed subject-specific networks using these two methods separately from resting-state fMRI data of 151 schizophrenia patients (SZs) and 163 healthy controls (HCs). We investigated group differences in the estimated functional networks and the functional network connectivity (FNC) obtained by each method. The networks were also used as features in a cross-validated support vector machine (SVM) for classifying SZs and HCs. We selected features using different strategies to provide a comprehensive comparison between the two methods. GIG-ICA generally showed greater sensitivity in statistical analysis and better classification performance (accuracy 76.45 ± 8.9%, sensitivity 0.74 ± 0.11, specificity 0.79 ± 0.11) than STR (accuracy 67.45 ± 8.13%, sensitivity 0.65 ± 0.11, specificity 0.71 ± 0.11). Importantly, results were also consistent when applied to an independent dataset including 82 HCs and 82 SZs. Our work suggests that the functional networks estimated by GIG-ICA are more sensitive to group differences, and GIG-ICA is promising for identifying image-derived biomarkers of brain disease.

Keywords: Classification; Functional network; GIG-ICA; ICA; Schizophrenia; Spatio-temporal regression; fMRI.

Fig. 1

Method framework of (A) group-level ICA on all subjects' fMRI data to estimate the group-level networks, (B) group information guided ICA (GIG-ICA) and (C) spatio-temporal regression (STR). (B) and (C) are performed on each subject's fMRI data to estimate the subject-specific networks and time courses.

Fig. 2

Statistical analysis procedure on brain functional networks. For each network estimated by GIG-ICA and STR, three different strategies were employed to identify the voxels showing significant effect of diagnosis. In strategy 1, after both one-sample t-tests and two-sample t-tests, the common significant voxels between GIG-ICA and STR were considered. In strategy 2, common significant voxels between the two methods were not considered at any step (hence the comparison was independent between the methods). In strategy 3, the common significant voxels between the methods were considered after one-sample t-tests, but not after two-sample t-tests.

Fig. 3

Framework for SVM classification on GIG-ICA and STR estimated networks. (A) Classification framework using the (primary) FBIRN data with 100 times of 10-fold cross-validation. In each time, a random training set was selected, on which 3 strategies were used for feature selection. Three sets of selected features were used separately to train SVM models whose optimum parameters (C, γ) were determined by another 10-fold cross-validation within the training data. Then the model was used to predict the testing set using the same features. (B) Classification framework using the COBRE data, independent from the primary FBIRN data. Two different schemes were applied to evaluate the classification ability in COBRE data. In the first scheme, an SVM model was trained using all the subjects from the FBIRN dataset, and this model was used to predict the labels for each of the subjects in the COBRE dataset. In the second scheme, 10-fold cross-validation within COBRE dataset was performed.

Fig. 4

Composite view of 47 group-level networks grouped into functional domains: 5 subcortical (SC), 2 auditory (AUD), 10 visual (VIS), 6 sensorimotor (SM), 9 attention (ATT), 7 fronto-parietal (FRN), 6 default mode (DMN) and 2 cerebellar (CB) networks. Intensity of color represents z-scores. Component labels and peak activation coordinates can be found in previous work (Damaraju et al., 2014a) and Supplementary Table S1.

Fig. 5

Individual voxel-based group difference and permutation test results, showing scatterplot of t-stats obtained from two-sample t-test between HC and SZ on each significant voxel within each network for strategy 1, 2 and 3 as outlined in Section 2.2.4.1, in subfigures (A), (B) and (C) respectively. Permutation test was performed on voxels with positive t-stats and negative t-stats separately. For relevant networks, the red stars indicate that GIG-ICA shows significantly greater group difference than STR in the permutation test (p < 0.05), and the blue circles indicate that STR shows significantly greater group difference compared to GIG-ICA. The absence of such an indicator means that in that network there was no significant difference between GIG-ICA or STR estimated t-stats. The full form name of each network can be found in Supplementary Table S1.(For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)

Fig. 6

HC and SZ classification results obtained using networks estimated by GIG-ICA and STR methods from FBIRN data as features and SVM technique. Features were extracted from randomly selected training subjects using 3 different strategies and testing was performed on the remaining subjects. Classification with 10-fold cross-validation was repeated 100 times. Each dot represents accuracy in (A), sensitivity in (B) and specificity in (C), obtained in one of the 100 repeats. The horizontal line indicates mean result, darker box indicates 95% confidence interval of mean and lighter box indicates standard deviation of the results. The p-values obtained from two-sample t-tests between the GIG-ICA and STR measures for each strategy are mentioned below the x-axis.

Fig. 7

HC and SZ classification results obtained using networks estimated by GIG-ICA and STR methods from FBIRN data as features and SVM technique. Note: Different from Fig. 6, the subject-specific networks from STR were estimated by including all available 100 group-level ICs as input. All the notations are the same as in Fig. 6.

Fig. 8

HC and SZ classification results of the independent dataset (COBRE). Features were extracted from subjects from the FBIRN dataset using 3 different strategies. The black lines in (A)-(C) indicate results from the first scheme where all FBIRN data were used for training and all COBRE data were used for testing the SVM model. In the second scheme, the classification was performed using a 10-fold cross-validation framework and was repeated 10 times. Each dot represents accuracy in (A), sensitivity in (B) and specificity in (C), obtained in one of the 10 repeats. The horizontal line indicates mean result, darker box indicates 95% confidence interval of mean and the lighter box indicates standard deviation of the results in the second scheme.

Fig. 9

The mean FNC matrix across all subjects in FBIRN. (A) Mean FNC matrix estimated using GIG-ICA. (B) Mean FNC matrix estimated using STR. (C) Paired t-test result between the two methods based on the subject-specific FNC matrix.

Fig. 10

T-stats obtained from two-sample t-test between controls and patients in each element of the FNC matrix. (A) Group difference captured by GIG-ICA. (B) Group difference captured by STR. (C) Group difference captured by GIG-ICA, with t-stats thresholded at p < 0.05 after Bonferroni correction for multiple comparisons. (D) Group difference captured by STR, with t-stats thresholded at p < 0.05 after Bonferroni correction for multiple comparisons.

Fig. 11

Significant group differences in FNC thresholded at p < 10⁻⁵ after Bonferroni correction for multiple comparisons. (A) Group differences captured by both GIG-ICA and STR. (B) Group differences captured by GIG-ICA only. (C) Group differences captured by STR only.