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.


Similarity ratio probability histograms at different unbalance ratio levels. This figure shows the performance of SSICA when fewer specific components than the actual simulated components are extracted (M1 < Kg1 and M2 < Kg2). Similarity ratio is binned at three levels: low (0–0.2), middle (0.2–0.8), and high (0.8–1). Histograms are generated based a total of 480 extracted specific components (20 permutations × 4 anatomical noise levels × 6 SNR values) at each unbalance ratio level.
© Copyright Policy
Related In: Results  -  Collection

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

Figure 5: Similarity ratio probability histograms at different unbalance ratio levels. This figure shows the performance of SSICA when fewer specific components than the actual simulated components are extracted (M1 < Kg1 and M2 < Kg2). Similarity ratio is binned at three levels: low (0–0.2), middle (0.2–0.8), and high (0.8–1). Histograms are generated based a total of 480 extracted specific components (20 permutations × 4 anatomical noise levels × 6 SNR values) at each unbalance ratio level.

Mentions: We investigated the cases in which the number of specific components is set to less or more than its actual value. First, we evaluated whether the SSICA extracts one or a combination of specific components when M1 < Kg1 and M2 < Kg2, and if this selection is influenced by the relative strengths of the components. To do so, we generated 1920 (20 × 4 × 6 × 4) hybrid fMRI datasets by various combinations of 2 specific patches embedded per group (20 random permutations), at different anatomical noise levels (n = 0, 1, 2, 3 voxels), with different SNR values (0.5–1 in 0.1 steps), and using various unbalance ratios (1.5–3 in steps of 0.5) as described in Section Robustness of SSICA to the Number of Extracted Specific Components. Whereas, two specific patches were simulated, up to one specific component per group was allowed to be extracted with SSICA. Figure 5 shows the similarity ratio probability histogram (Equation 6) calculated based on the results of SSICA at different unbalance ratios.


Validation of Shared and Specific Independent Component Analysis (SSICA) for Between-Group Comparisons in fMRI
Similarity ratio probability histograms at different unbalance ratio levels. This figure shows the performance of SSICA when fewer specific components than the actual simulated components are extracted (M1 < Kg1 and M2 < Kg2). Similarity ratio is binned at three levels: low (0–0.2), middle (0.2–0.8), and high (0.8–1). Histograms are generated based a total of 480 extracted specific components (20 permutations × 4 anatomical noise levels × 6 SNR values) at each unbalance ratio level.
© Copyright Policy
Related In: Results  -  Collection

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

Figure 5: Similarity ratio probability histograms at different unbalance ratio levels. This figure shows the performance of SSICA when fewer specific components than the actual simulated components are extracted (M1 < Kg1 and M2 < Kg2). Similarity ratio is binned at three levels: low (0–0.2), middle (0.2–0.8), and high (0.8–1). Histograms are generated based a total of 480 extracted specific components (20 permutations × 4 anatomical noise levels × 6 SNR values) at each unbalance ratio level.
Mentions: We investigated the cases in which the number of specific components is set to less or more than its actual value. First, we evaluated whether the SSICA extracts one or a combination of specific components when M1 < Kg1 and M2 < Kg2, and if this selection is influenced by the relative strengths of the components. To do so, we generated 1920 (20 × 4 × 6 × 4) hybrid fMRI datasets by various combinations of 2 specific patches embedded per group (20 random permutations), at different anatomical noise levels (n = 0, 1, 2, 3 voxels), with different SNR values (0.5–1 in 0.1 steps), and using various unbalance ratios (1.5–3 in steps of 0.5) as described in Section Robustness of SSICA to the Number of Extracted Specific Components. Whereas, two specific patches were simulated, up to one specific component per group was allowed to be extracted with SSICA. Figure 5 shows the similarity ratio probability histogram (Equation 6) calculated based on the results of SSICA at different unbalance ratios.

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 &ldquo;shared and specific independent component analysis&rdquo; (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 &ldquo;specific&rdquo; 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.