loading page

Site effects removing and signal enhancement using dual-projection based ICA model
  • +7
  • Yuxing Hao,
  • Huashuai Xu,
  • Mingrui Xia,
  • Chenwei Yan,
  • Yunge Zhang,
  • Dongyue Zhou,
  • Tommi Kärkkäinen,
  • Lisa Nickerson,
  • Huanjie Li,
  • Fengyu Cong
Yuxing Hao
Dalian University of Technology
Author Profile
Huashuai Xu
University of Jyväskylä
Author Profile
Mingrui Xia
Beijing Normal University
Author Profile
Chenwei Yan
Dalian University of Technology
Author Profile
Yunge Zhang
Dalian University of Technology
Author Profile
Dongyue Zhou
Dalian University of Technology
Author Profile
Tommi Kärkkäinen
University of Jyväskylä
Author Profile
Lisa Nickerson
Harvard Medical School
Author Profile
Huanjie Li
Dalian University of Technology

Corresponding Author:hj_li@dlut.edu.cn

Author Profile
Fengyu Cong
Dalian University of Technology
Author Profile

Abstract

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 scanner/site variability is a significant confound that complicates the interpretation of the results, so effective and complete removal of the scanner/site variability is necessary to realize the full advantages of pooling multi-site datasets. Independent component analysis (ICA) and general linear model (GLM) based harmonization methods are the two primary methods used to eliminate scanner/site-related effects. Unfortunately, there are challenges with both ICA-based and GLM-based harmonization methods to remove site effects completely when the signals of interest and scanner/site-related variables are correlated, which may occur in neuroscience studies. In this study, we propose an effective and powerful harmonization strategy that implements dual-projection (DP) theory based on ICA to remove the scanner/site-related effects more completely. This method can separate the signal effects correlated with site variables from the identified site-related effects for removal without losing signals of interest. Both simulations and vivo structural MRI datasets, including a dataset from Autism Brain Imaging Data Exchange II and a traveling subject dataset from the Strategic Research Program for Brain Sciences, were used to test the performance of DP-based ICA harmonization method. Results show that DP-based ICA harmonization has superior performance for removing site effects and enhancing the sensitivity to detect signal of interest as compared with GLM-based and conventional ICA harmonization methods.
21 May 2023Submitted to European Journal of Neuroscience
22 May 2023Submission Checks Completed
22 May 2023Assigned to Editor
22 May 2023Review(s) Completed, Editorial Evaluation Pending
23 May 2023Reviewer(s) Assigned
28 Jun 2023Editorial Decision: Revise Minor
16 Jul 20231st Revision Received
17 Jul 2023Submission Checks Completed
17 Jul 2023Assigned to Editor
17 Jul 2023Review(s) Completed, Editorial Evaluation Pending
17 Jul 2023Reviewer(s) Assigned
24 Jul 2023Editorial Decision: Revise Major
25 Jul 20232nd Revision Received
26 Jul 2023Review(s) Completed, Editorial Evaluation Pending
26 Jul 2023Submission Checks Completed
26 Jul 2023Assigned to Editor
26 Jul 2023Editorial Decision: Accept