Limits...
Validation of Shared and Specific Independent Component Analysis (SSICA) for Between-Group Comparisons in fMRI

View Article: PubMed Central - PubMed

ABSTRACT

Independent component analysis (ICA) has been widely used to study functional magnetic resonance imaging (fMRI) connectivity. However, the application of ICA in multi-group designs is not straightforward. We have recently developed a new method named “shared and specific independent component analysis” (SSICA) to perform between-group comparisons in the ICA framework. SSICA is sensitive to extract those components which represent a significant difference in functional connectivity between groups or conditions, i.e., components that could be considered “specific” for a group or condition. Here, we investigated the performance of SSICA on realistic simulations, and task fMRI data and compared the results with one of the state-of-the-art group ICA approaches to infer between-group differences. We examined SSICA robustness with respect to the number of allowable extracted specific components and between-group orthogonality assumptions. Furthermore, we proposed a modified formulation of the back-reconstruction method to generate group-level t-statistics maps based on SSICA results. We also evaluated the consistency and specificity of the extracted specific components by SSICA. The results on realistic simulated and real fMRI data showed that SSICA outperforms the regular group ICA approach in terms of reconstruction and classification performance. We demonstrated that SSICA is a powerful data-driven approach to detect patterns of differences in functional connectivity across groups/conditions, particularly in model-free designs such as resting-state fMRI. Our findings in task fMRI show that SSICA confirms results of the general linear model (GLM) analysis and when combined with clustering analysis, it complements GLM findings by providing additional information regarding the reliability and specificity of networks.

No MeSH data available.


The SSICA algorithm schematic. There are three levels of data whitening and dimension reduction in SSICA. F, H, and G represent the projection matrices at the first (subject), second (within-group), and the third (between-group) levels of data reduction, respectively.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5037228&req=5

Figure 1: The SSICA algorithm schematic. There are three levels of data whitening and dimension reduction in SSICA. F, H, and G represent the projection matrices at the first (subject), second (within-group), and the third (between-group) levels of data reduction, respectively.

Mentions: In contrast to the regular gICA, SSICA employs a 3-step PCA data reduction and whitening procedure on, (1) each individual data, (2) each group's concatenated data, and (3) multi-group aggregate data, as illustrated in Figure 1. Although the first data reduction step is not necessary for the proper operation of SSICA, it is recommended in fMRI analysis due to the computational burden. The subject-level reduction step uses the same projection matrix, described above.


Validation of Shared and Specific Independent Component Analysis (SSICA) for Between-Group Comparisons in fMRI
The SSICA algorithm schematic. There are three levels of data whitening and dimension reduction in SSICA. F, H, and G represent the projection matrices at the first (subject), second (within-group), and the third (between-group) levels of data reduction, respectively.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5037228&req=5

Figure 1: The SSICA algorithm schematic. There are three levels of data whitening and dimension reduction in SSICA. F, H, and G represent the projection matrices at the first (subject), second (within-group), and the third (between-group) levels of data reduction, respectively.
Mentions: In contrast to the regular gICA, SSICA employs a 3-step PCA data reduction and whitening procedure on, (1) each individual data, (2) each group's concatenated data, and (3) multi-group aggregate data, as illustrated in Figure 1. Although the first data reduction step is not necessary for the proper operation of SSICA, it is recommended in fMRI analysis due to the computational burden. The subject-level reduction step uses the same projection matrix, described above.

View Article: PubMed Central - PubMed

ABSTRACT

Independent component analysis (ICA) has been widely used to study functional magnetic resonance imaging (fMRI) connectivity. However, the application of ICA in multi-group designs is not straightforward. We have recently developed a new method named “shared and specific independent component analysis” (SSICA) to perform between-group comparisons in the ICA framework. SSICA is sensitive to extract those components which represent a significant difference in functional connectivity between groups or conditions, i.e., components that could be considered “specific” for a group or condition. Here, we investigated the performance of SSICA on realistic simulations, and task fMRI data and compared the results with one of the state-of-the-art group ICA approaches to infer between-group differences. We examined SSICA robustness with respect to the number of allowable extracted specific components and between-group orthogonality assumptions. Furthermore, we proposed a modified formulation of the back-reconstruction method to generate group-level t-statistics maps based on SSICA results. We also evaluated the consistency and specificity of the extracted specific components by SSICA. The results on realistic simulated and real fMRI data showed that SSICA outperforms the regular group ICA approach in terms of reconstruction and classification performance. We demonstrated that SSICA is a powerful data-driven approach to detect patterns of differences in functional connectivity across groups/conditions, particularly in model-free designs such as resting-state fMRI. Our findings in task fMRI show that SSICA confirms results of the general linear model (GLM) analysis and when combined with clustering analysis, it complements GLM findings by providing additional information regarding the reliability and specificity of networks.

No MeSH data available.