Mitigating site effects in covariance for machine learning in neuroimaging data

Chen, Andrew A.; Beer, Jacob; Tustison, Nicholas J.; Cook, Philip A.; Shinohara, Russell T.; Shou, Haochang

doi:10.1002/hbm.25688

Cited by 62 publications

(56 citation statements)

References 46 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most of the methods, including ComBat are univariate approaches that would be limited to capturing all sources of batch effects which could be represented by the batch-specific latent patterns. (Chen and others , 2022)…”

Section: Introductionmentioning

confidence: 99%

RELIEF: a structured multivariate approach for removal of latent inter-scanner effects

Zhang

Oliver

Voineskos

et al. 2022

Preprint

View full text Add to dashboard Cite

Combining data collected from multiple studies is becoming common and is advantageous to researchers to increase the reproducibility of scientific discoveries. However, at the same time, unwanted "batch effects" are commonly observed across neuroimaging data collected from multiple study sites or scanners, rendering difficulties in combining such data to obtain reliable findings. While methods for handling such unwanted variations have been proposed recently, most of them use univariate approaches which would be too simple to capture all sources of batch effects which could be represented by the batch-specific latent patterns. In this paper, we propose a novel multivariate harmonization method, called UNIFAC harmonization, for estimating and removing both explicit and latent batch effects. Our approach is based on the simultaneous dimension reduction and factorization of interlinked matrices through a penalized objective, which provides a new direction in neuroimaging research for harmonizing multivariate features across batches. Using the Social Processes Initiative in Neurobiology of the Schizophrenia (SPINS) dataset and extensive simulation studies, we show that UNIFAC harmonization performed better than the existing methods in entirely removing batch effects as well as retaining associations of interest to increase statistical power. The proposed method is publicly available as a R package.

show abstract

Section: Introductionmentioning

confidence: 99%

RELIEF: a structured multivariate approach for removal of latent inter-scanner effects

Zhang

Oliver

Voineskos

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, the linear nature of our model may leave out important non-linear covariate and scanner effects. Extensions of EB ComBat have shown improved performance by modeling scanner covariance effects (Chen et al, 2021) and non-linear covariate effects (Pomponio et al, 2020). While our work compares EB and FB approaches to Longitudinal ComBat (Beer et al, 2020), more complicated FB models are straightforward to implement.…”

Section: Discussionmentioning

confidence: 99%

ComBat Harmonization: Empirical Bayes versus Fully Bayes Approaches

Reynolds

Chaudhary

Torbati

et al. 2022

Preprint

View full text Add to dashboard Cite

Studying small effects or subtle neuroanatomical variation requires large-scale sample size data. As a result, combining neuroimaging data from multiple datasets is necessary. Variation in acquisition protocols, magnetic field strength, scanner build, and many other non-biologically related factors can introduce undesirable bias into studies. Hence, harmonization is required to remove the bias-inducing factors from the data. ComBat, introduced by (Johnson et al., 2007), is one of the most common methods applied to features from structural images. ComBat models the data using a hierarchical Bayesian model and uses the empirical Bayes approach to infer the distribution of the unknown factors. The empirical Bayes harmonization method is computationally efficient and provides valid point estimates. However, it tends to underestimate uncertainty. This paper investigates a new approach, fully Bayesian ComBat, where Monte Carlo Sampling is used for statistical inference. Our experiments show that our new fully Bayesian approach offers more accurate harmonization, unconstrained posterior distributions, and representative uncertainty quantification at the expense of higher computation costs for the inference. This fully Bayesian approach generates a rich posterior distribution, which is also useful for generating simulated imaging features for improving classifier performance in a limited data setting. We show the generative capacity of our model for augmenting and improving the detection of patients with Alzheimer's disease. Posterior distributions for harmonized imaging measures can also be used for brain-wide uncertainty comparison and more principled downstream statistical analysis. Code for our new fully Bayesian ComBat extension is available at https://github.com/batmanlab/BayesComBat.

show abstract

“…As mentioned before, in addition to ComBat, other extensions to ComBat like CovBat (Chen et al, 2021) have been proposed. Similarly, recently proposed methods like NeuroHarmony (Garcia-Dias et al, 2020) need to be tested and evaluated in terms of their sample size requirement for achieving inter-site harmonization.…”

Section: Discussionmentioning

confidence: 99%

Sample size requirement for achieving multisite harmonization using structural brain MRI features

Parekh

Bhalerao

John

et al. 2022

Preprint

View full text Add to dashboard Cite

When data is pooled across multiple sites, the extracted features are confounded by site effects. Harmonization methods attempt to correct these site effects while preserving the biological variability within the features. However, little is known about the sample size requirement for effectively learning the harmonization parameters and their relationship with the increasing number of sites. In this study, we performed experiments to find the minimum sample size required to achieve multisite harmonization (using neuroHarmonize) using volumetric and surface features by leveraging the concept of learning curves. Our first two experiments show that site-effects are effectively removed in a univariate and multivariate manner; however, it is essential to regress the effect of covariates from the harmonized data additionally. Our following two experiments with actual and simulated data showed that the minimum sample size required for achieving harmonization grows with the increasing average Mahalanobis distances between the sites and their reference distribution. We conclude by positing a general framework to understand the site effects using the Mahalanobis distance. Further, we provide insights on the various factors in a cross-validation design to achieve optimal inter-site harmonization.

show abstract

Mitigating site effects in covariance for machine learning in neuroimaging data

Cited by 62 publications

References 46 publications

RELIEF: a structured multivariate approach for removal of latent inter-scanner effects

RELIEF: a structured multivariate approach for removal of latent inter-scanner effects

ComBat Harmonization: Empirical Bayes versus Fully Bayes Approaches

Sample size requirement for achieving multisite harmonization using structural brain MRI features

Contact Info

Product

Resources

About