Comparative analysis of group information-guided independent component analysis and independent vector analysis for
Junlin Jing1, Benjamin Klugah-Brown1, Shiyu Xia1
1The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China.
Introduction:
Group information-guided independent component analysis (GIG-ICA) and independent vector analysis (IVA) are two methods that improve estimation of subject-specific independent components in neuroimaging studies. These methods have shown better performance than traditional group independent component analysis (GICA) with respect to intersubject variability (ISV).
Methods:
In this study, we compared the patterns of community structure, spatial variance, and prediction performance of GIG-ICA and IVA-GL, respectively. The dataset was obtained from the publicly available Autism Brain Imaging Data Exchange (ABIDE) database, comprising 75 healthy controls (HC) and 102 Autism Spectrum Disorder (ASD) participants. The greedy rule was used to match components from IVA-GL and GIG-ICA in order to compare the similarities between the two methods.
Results:
Robust correspondence was observed between the two methods the following networks: cerebellum network (CRN; |r| = 0.7813), default mode network (DMN; |r| = 0.7263), self-reference network (SRN; |r| = 0.7818), ventral attention network (VAN; |r| = 0.7574), and visual network (VSN; |r| = 0.7503). Additionally, the Sensorimotor Network demonstrated the highest similarity between IVA-GL and GIG-ICA (SOM: |r| = 0.8125). Our findings revealed a significant difference in the number of modules identified by the two methods (HC: p < 0.001; ASD: p < 0.001). GIG-ICA identified significant differences in FNC between HC and ASD compared to IVA-GL. However, in correlation analysis, IVA-GL identified a statistically negative correlation between FNC of ASD and the social total subscore of the classic Autism Diagnostic Observation Schedule (ADOS: pi = -0.26, p = 0.0489). Moreover, both methods demonstrated similar prediction performances on age within specific networks, as indicated by GIG-ICA-CRN (R2 = 0.91, RMSE = 3.05) and IVA-VAN (R2 = 0.87, RMSE = 3.21).
Conclusion:
In summary, IVA-GL demonstrated lower modularity, suggesting greater sensitivity in estimating networks with higher intersubject variability. The improved age prediction of cerebellar-attention networks underscores their importance in the developmental progression of ASD. Overall, IVA-GL may be appropriate for investigating disorders with greater variability, while GIG-ICA identifies functional networks with distinct modularity patterns.
