Enhancing Performance of Linked Independent Component Analysis : Investigating the Influence of Subjects and Modalities
Xu, H., Li, H., Kärkkäinen, T., & Cong, F. (2023). Enhancing Performance of Linked Independent Component Analysis : Investigating the Influence of Subjects and Modalities. In CIPAE 2023 : 2023 International Conference on Computers, Information Processing and Advanced Education (pp. 726-732). IEEE. https://doi.org/10.1109/cipae60493.2023.00141
Date
2023Discipline
Human and Machine based Intelligence in LearningSecure Communications Engineering and Signal ProcessingTekniikkaHuman and Machine based Intelligence in LearningSecure Communications Engineering and Signal ProcessingEngineeringAccess restrictions
Embargoed until: 2025-08-26Request copy from author
Copyright
© 2023, IEEE
In recent years, neuroimaging studies have increasingly been acquiring multiple modalities of data. The benefit of integrating multiple modalities through fusion lies in its ability to combine the unique strengths of each modality when analyzed collectively, as opposed to examining each one individually. In 2011, Adrian R. Groves proposed the Linked independent component analysis (LICA) method, which simultaneously models and discovers common features across multiple modalities. LICA has emerged as a powerful technique for analyzing multivariate data, particularly in neuroimaging and biomedical signal processing. The performance of LICA can be affected by the number of subjects and modalities. However, the detailed influence of the number of subjects and modalities on its performance remains an open question. In this study, we test the effects of the number of subjects and modalities on the performance of LICA using both simulated multimodal MRI data and the real multimodal MRI datasets from Autism Brain Imaging Data Exchange II (ABIDE II). Simulated data were utilized to evaluate the influence of subjects and modalities' variabilities. Real multi-site MRI data were used to demonstrate the advantages of multimodal fusion in identifying site-related components and removing site effects. Based on the simulation results, we found that increasing the number of modalities and subjects can improve the results when LICA can not recover the spatial maps or subject courses well. The correlation among subject courses from various modalities, the number of modalities, and the choice of components for decomposition all affect the linking performance of LICA. Our results from real-world datasets also demonstrated the advantages of multimodal fusion by LICA: 1) identify more site-related components; 2) remove more site effects.
...
Publisher
IEEEParent publication ISBN
979-8-3503-4272-7Conference
International Conference on Computers, Information Processing and Advanced EducationIs part of publication
CIPAE 2023 : 2023 International Conference on Computers, Information Processing and Advanced EducationKeywords
Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/197363616
Metadata
Show full item recordCollections
Additional information about funding
This work was supported by STI 2030 - Major Projects 2022ZD0211500, Science and Technology Planning Project of Liaoning Provincial (no. 2022JH2/10700002 and 2021JH1/10400049), National Natural Science Foundation of China [grant numbers 91748105 & 81471742], National Foundation in China [grant number JCKY 2019110B009], and the scholarship from China Scholarship Council (No. 201806060167).License
Related items
Showing items with similar title or keywords.
-
Removal of site effects and enhancement of signal using dual projection independent component analysis for pooling multi‐site MRI data
Hao, Yuxing; Xu, Huashuai; Xia, Mingrui; Yan, Chenwei; Zhang, Yunge; Zhou, Dongyue; Kärkkäinen, Tommi; Nickerson, Lisa D.; Li, Huanjie; Cong, Fengyu (Wiley-Blackwell, 2023)Combining magnetic resonance imaging (MRI) data from multi-site studies is a popular approach for constructing larger datasets to greatly enhance the reliability and reproducibility of neuroscience research. However, the ... -
Snowball ICA : A Model Order Free Independent Component Analysis Strategy for Functional Magnetic Resonance Imaging Data
Hu, Guoqiang; Waters, Abigail B.; Aslan, Serdar; Frederick, Blaise; Cong, Fengyu; Nickerson, Lisa D. (Frontiers Media, 2020)In independent component analysis (ICA), the selection of model order (i.e., number of components to be extracted) has crucial effects on functional magnetic resonance imaging (fMRI) brain network analysis. Model order ... -
Denoising brain networks using a fixed mathematical phase change in independent component analysis of magnitude-only fMRI data
Zhang, Chao‐Ying; Lin, Qiu‐Hua; Niu, Yan‐Wei; Li, Wei‐Xing; Gong, Xiao‐Feng; Cong, Fengyu; Wang, Yu‐Ping; Calhoun, Vince D. (Wiley, 2023)Brain networks extracted by independent component analysis (ICA) from magnitude-only fMRI data are usually denoised using various amplitude-based thresholds. By contrast, spatial source phase (SSP) or the phase information ... -
Harmonization of multi-site functional MRI data with dual-projection based ICA model
Xu, Huashuai; Hao, Yuxing; Zhang, Yunge; Zhou, Dongyue; Kärkkäinen, Tommi; Nickerson, Lisa D.; Li, Huanjie; Cong, Fengyu (Frontiers Media SA, 2023)Modern neuroimaging studies frequently merge magnetic resonance imaging (MRI) data from multiple sites. A larger and more diverse group of participants can increase the statistical power, enhance the reliability and ... -
Multivariate Independent Component Analysis Identifies Patients in Newborn Screening Equally to Adjusted Reference Ranges
Kouři,l Štěpán; de Sousa, Julie; Fačevicová Kamila; Gardlo, Alžběta; Muehlmann, Christoph; Nordhausen, Klaus; Friedecký, David; Adam, Tomáš (MDPI, 2023)Newborn screening (NBS) of inborn errors of metabolism (IEMs) is based on the reference ranges established on a healthy newborn population using quantile statistics of molar concentrations of biomarkers and their ratios. ...