Site effects how-to and when: An overview of retrospective techniques to accommodate site effects in multi-site neuroimaging analyses
Year: 2022
Type: article
Abstract: Site differences, or systematic differences in feature distributions across multiple data-acquisition sites, are a known source of heterogeneity that may adversely affect large-scale meta- and mega-analyses of independently collected neuroimaging data. They influence nearly all multi-site imaging modalities and biomarkers, and methods to compensate for them can improve reliability and generalizability in the analysis of genetics, omics, and clinical data. The origins of statistical site effects are complex and involve both technical differences (scanner vendor, head coil, acquisition parameters, imaging processing) and differences in sample characteristics (inclusion/exclusion criteria, sample size, ancestry) between sites. In an age of expanding international consortium research, there is a growing need to disentangle technical site effects from sample characteristics of interest. Numerous statistical and machine learning methods have been developed to control for, model, or attenuate site effects – yet to date, no comprehensive review has discussed the benefits and drawbacks of each for different use cases. Here, we provide an overview of the different existing statistical and machine learning methods developed to remove unwanted site effects from independently collected neuroimaging samples. We focus on linear mixed effect models, the ComBat technique and its variants, adjustments based on image quality metrics, normative modeling, and deep learning approaches such as generative adversarial networks. For each method, we outline the statistical foundation and summarize strengths and weaknesses, including their assumptions and conditions of use. We provide information on software availability and comment on the ease of use and the applicability of these methods to different types of data. We discuss validation and comparative reports, mention caveats and provide guidance on when to use each method, depending on context and specific research questions.
Source: Frontiers in Neurology
Institutions: The University of Melbourne, Orygen, University of Southern California, Sun Yat-sen University, University of Pennsylvania, Universidade Federal do Rio Grande do Sul, Max Planck Institute of Psychiatry, Radboud University Medical Center, Donders Institute for Brain, Cognition and Behaviour
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: gold
Estimated APC paid: $2,950
Funders: Alzheimer's Association, Biogen, University of Pennsylvania, Wellcome Trust, Multiple Sclerosis Society, National Institutes of Health, National Health and Medical Research Council, National Institute on Aging, National Institute of Mental Health, National Institute of Biomedical Imaging and Bioengineering
Awards: BRAINCHART: Normative brain charting for predicting and stratifying psychosis, ENIGMA-APOE2 : A global Study of the Alzheimer's Protective Genotype, G1512275605, BRAINCHART: Normative brain charting for predicting and stratifying psychosis, FiberNET: Deep learning to evaluate brain tract integrity worldwide and in AD, G1793114910, ENIGMA-COINSTAC: Advanced Worldwide Transdiagnostic Analysis of Valence System Brain Circuit, G290699439, G3455626259, G4138939251, G5072561859, G5459904085, ENIGMA Center for Worldwide Medicine, Imaging & Genomics, G6915108039, G700495459, High resolution mapping of the genetic risk for disease in the aging brain, G8351931241, G8568853127, A global alliance to unlock brain mechanisms influencing suicidal behaviors through the ENIGMA Consortium, Ultrascale Machine Learning to Empower Discovery in Alzheimers Disease Biobanks
OpenAlex ID: W4307873068