Repeatability analysis of ICA-based harmonization for multi-site MRI data using dual projection models

NeuroImage, vol. 326, pp. 121686

Abstract

Integrating multi-site magnetic resonance imaging (MRI) datasets enhances statistical power and generalizability in neuroimaging research but introduces systematic variability, known as site effects, that can obscure true biological signals. Independent component analysis (ICA)-based harmonization methods, such as the dual projection ICA (ICA-DP) model, aim to mitigate these effects while preserving meaningful signal. However, the repeatability of ICA decompositions across different runs and parameter settings remains a critical challenge, affecting the stability and reliability of site effects removal. Here, we propose a novel evaluation framework for ICA repeatability that jointly assesses spatial components, their mixing coefficients, and component energy-a theoretically grounded but often overlooked parameter based on back-projection. Using both simulated and real multi-site MRI datasets, we demonstrate that incorporating component energy into repeatability metrics provides a more robust and theoretically grounded assessment of ICA stability. We further revise the ICA-DP harmonization scheme by removing site-associated components comprehensively, resulting in improved preservation of biologically relevant signals. Our results establish the importance of repeatability analysis and support the proposed framework as a reliable tool for ICA-based harmonization in multi-site studies.

Authors 6

1. Yuxing Hao

   Dalian University of Technology · University of Jyväskylä

   Affiliation as printed

   School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, Dalian, China; Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland

2. Yongjie Zhu corresponding

   University of Helsinki · Dalian University of Technology · Aalto University

   Affiliation as printed

   School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, Dalian, China; Department of Computer Science, University of Helsinki, Helsinki, Finland; Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland. Electronic address: yongjie.zhu@helsinki.fi

3. Chenwei Yan Aachen Department of Psychiatry, Psychotherapy and Psychosomatics Faculty of Medicine

   Dalian University of Technology · RWTH Aachen University

   Affiliation as printed

   School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, Dalian, China; Department of Psychiatry, Psychotherapy and Psychosomatics, Faculty of Medicine, RWTH Aachen University, Aachen, Germany

4. Huanjie Li

   Dalian University of Technology

   Affiliation as printed

   School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, Dalian, China

5. Tommi Kärkkäinen

   University of Jyväskylä

   Affiliation as printed

   Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland

6. Fengyu Cong

   Dalian University of Technology · University of Jyväskylä

   Affiliation as printed

   School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, Dalian, China; Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland; Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology), Ministry of Education, China