Optimizing Within-Subject Experimental Designs for jICA of Multi-Channel ERP and fMRI

Disjoint subspaces for common and distinct component analysis: Application to the fusion of multi-task FMRI data

BACKGROUND

Data-driven methods such as independent component analysis (ICA) makes very few assumptions on the data and the relationships of multiple datasets, and hence, are attractive for the fusion of medical imaging data. Two important extensions of ICA for multiset fusion are the joint ICA (jICA) and the multiset canonical correlation analysis and joint ICA (MCCA-jICA) techniques. Both approaches assume identical mixing matrices, emphasizing components that are common across the multiple datasets. However, in general, one would expect to have components that are both common across the datasets and distinct to each dataset.

NEW METHOD

We propose a general framework, disjoint subspace analysis using ICA (DS-ICA), which identifies and extracts not only the common but also the distinct components across multiple datasets. A key component of the method is the identification of these subspaces and their separation before subsequent analyses, which helps establish better model match and provides flexibility in algorithm and order choice.

COMPARISON

We compare DS-ICA with jICA and MCCA-jICA through both simulations and application to multiset functional magnetic resonance imaging (fMRI) task data collected from healthy controls as well as patients with schizophrenia.

RESULTS

The results show DS-ICA estimates more components discriminative between healthy controls and patients than jICA and MCCA-jICA, and with higher discriminatory power showing activation differences in meaningful regions. When applied to a classification framework, components estimated by DS-ICA results in higher classification performance for different dataset combinations than the other two methods.

CONCLUSION

These results demonstrate that DS-ICA is an effective method for fusion of multiple datasets.

An Examination of the Association Between Subjective Distress and Functional Connectivity During Discarding Decisions in Hoarding Disorder

BACKGROUND

Individuals with hoarding disorder (HD) demonstrate exaggerated subjective distress and hyperactivation of cingulate and insular cortex regions when discarding personal possessions. No prior study has sought to determine whether this subjective distress is associated with specific profiles of abnormal brain function in individuals with HD.

METHODS

We used multimodal canonical correlation analysis plus joint independent component analysis to test whether five hoarding-relevant domains of subjective distress when deciding to discard possessions (anxiety, sadness, monetary value, importance, and sentimental attachment) are associated with functional magnetic resonance imaging-measured whole-brain functional connectivity in 72 participants with HD and 44 healthy controls.

RESULTS

Three extracted components differed between HD participants and healthy control subjects. Each of these components depicted an abnormal profile of functional connectivity in HD participants relative to control subjects during discarding decisions, and a specific distress response profile. One component pair showed a relationship between anxiety ratings during discarding decisions and connectivity among the pallidum, perirhinal ectorhinal cortex, and dorsolateral prefrontal cortex. Another component comprised sadness ratings during discarding decisions and connectivity in the pallidum, nucleus accumbens, amygdala, and dorsolateral prefrontal cortex. The third component linked HD brain connectivity in several dorsolateral prefrontal cortex regions with perceived importance ratings during discarding decisions.

CONCLUSIONS

The findings indicate that in patients with HD, the subjective intensity of anxiety, sadness, and perceived possession importance is related to abnormal functional connectivity in key frontal and emotional processing brain regions. The findings are discussed in terms of emerging neurobiological models of HD.