Goal-specific brain MRI harmonization

An, Lijun; Chen, Jianzhong; Chen, Pansheng; Zhang, Chen; He, Tong; Chen, Christopher; Zhou, Juan; Yeo, B.T. Thomas

doi:10.1016/j.neuroimage.2022.119570

Cited by 21 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the nonconvolutional setting of DeepComBat, each 1 × 1 element of the latent space vector corresponds to one convolutional filter, and similar moment-matching is performed, but at the group level instead of the individual input level. Relatedly, we show DeepComBat performs better than dcVAE and gcVAE, which were trained using the default hyperparameter values specified by An et al (2022).…”

Section: Deepcombat Resembles Other Moment-matching Harmonization Met...mentioning

confidence: 87%

“…DeepComBat was evaluated against unharmonized data as well as other featurelevel harmonization methods where code was available. These methods included ComBat, CovBat, dcVAE, and gcVAE (An et al, 2022;Chen et al, 2022a;Fortin et al, 2017;Moyer et al, 2020). Notably, since no code was provided in the original manuscript for dcVAE, we implemented this method using code provided by An et al (2022).…”

Section: Discussionmentioning

confidence: 99%

“…These methods included ComBat, CovBat, dcVAE, and gcVAE (An et al, 2022;Chen et al, 2022a;Fortin et al, 2017;Moyer et al, 2020). Notably, since no code was provided in the original manuscript for dcVAE, we implemented this method using code provided by An et al (2022). For all comparison methods, we used default settings and hyperparameters provided in the code.…”

Section: Discussionmentioning

confidence: 99%

“…From the deep learning perspective, feature-level multivariate harmonization methods have leveraged the conditional variational autoencoder (CVAE) architecture, an adaptation of the standard variational autoencoder that attempts to disentangle the latent space distribution from covariates of interest (Kingma and Welling, 2014;Sohn et al, 2015). These models include diffusion CVAE (dcVAE, Moyer et al, 2020) and goalspecific CVAE (gcVAE, An et al, 2022). In dcVAE, an encoder is used to embed vector representations of diffusion MRI data as latent space distributions, and the encoder is penalized when batch-specific information is present in the latent space representation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data

Lucas

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

Neuroimaging data from multiple batches (i.e. acquisition sites, scanner manufacturer, datasets, etc.) are increasingly necessary to gain new insights into the human brain. However, multi-batch data, as well as extracted radiomic features, exhibit pronounced technical artifacts across batches. These batch effects introduce confounding into the data and can obscure biological effects of interest, decreasing the generalizability and reproducibility of findings. This is especially true when multi-batch data is used alongside complex downstream analysis models, such as machine learning methods. Image harmonization methods seeking to remove these batch effects are important for mitigating these issues; however, significant multivariate batch effects remain in the data following harmonization by current state-of-the-art statistical and deep learning methods. We present DeepCombat, a deep learning harmonization method based on a conditional variational autoencoder architecture and the ComBat harmonization model. DeepCombat learns and removes subject-level batch effects by accounting for the multivariate relationships between features. Additionally, DeepComBat relaxes a number of strong assumptions commonly made by previous deep learning harmonization methods and is empirically robust across a wide range of hyperparameter choices. We apply this method to neuroimaging data from a large cognitive-aging cohort and find that DeepCombat outperforms existing methods, as assessed by a battery of machine learning methods, in removing scanner effects from cortical thickness measurements while preserving biological heterogeneity. Additionally, DeepComBat provides a new perspective for statistically-motivated deep learning harmonization methods.

show abstract

Section: Deepcombat Resembles Other Moment-matching Harmonization Met...mentioning

confidence: 87%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data

Lucas

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep neural networks (DNNs) are promising for eliminating nonlinear site differences distributed across the brain (Hu et al, 2023). Variational autoencoder (VAE)-based approaches (Moyer et al, 2020; Russkikh et al, 2020; Zuo et al, 2021; An et al, 2022) use an encoder to generate site-invariant latent representations from input MRI data. Site information is then concatenated to the latent representations to reconstruct the MRI data via a decoder.…”

Section: Introductionmentioning

confidence: 99%

DeepResBat: deep residual batch harmonization accounting for covariate distribution differences

An,

Zhang,

Wulan

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Pooling MRI data from multiple datasets requires harmonization to reduce undesired inter- site variabilities, while preserving effects of biological variables (or covariates). The popular harmonization approach ComBat uses a mixed effect regression framework that explicitly accounts for covariate distribution differences across datasets. There is also significant interest in developing harmonization approaches based on deep neural networks (DNNs), such as conditional variational autoencoder (cVAE). However, current DNN approaches do not explicitly account for covariate distribution differences across datasets. Here, we provide mathematical results, suggesting that not accounting for covariates can lead to suboptimal harmonization outcomes. We propose two DNN-based harmonization approaches that explicitly account for covariate distribution differences across datasets: covariate VAE (coVAE) and DeepResBat. The coVAE approach is a natural extension of cVAE by concatenating covariates and site information with site- and covariate-invariant latent representations. DeepResBat adopts a residual framework inspired by ComBat. DeepResBat first removes the effects of covariates with nonlinear regression trees, followed by eliminating site differences with cVAE. Finally, covariate effects are added back to the harmonized residuals. Using three datasets from three different continents with a total of 2787 participants and 10085 anatomical T1 scans, we find that DeepResBat and coVAE outperformed ComBat, CovBat and cVAE in terms of removing dataset differences, while enhancing biological effects of interest. However, coVAE hallucinates spurious associations between anatomical MRI and covariates even when no association exists. Therefore, future studies proposing DNN-based harmonization approaches should be aware of this false positive pitfall. Overall, our results suggest that DeepResBat is an effective deep learning alternative to ComBat.

show abstract

Digital phenotyping: An equal opportunity approach to reducing disparities in Alzheimer's disease and related dementia research

Britton,

Huang,

Villarreal

et al. 2023

Alz & Dem Diag Ass & Dis Mo

View full text Add to dashboard Cite

A rapidly aging world population is fueling a concomitant increase in Alzheimer's disease (AD) and related dementias (ADRD). Scientific inquiry, however, has largely focused on White populations in Australia, the European Union, and North America. As such, there is an incomplete understanding of AD in other populations. In this perspective, we describe research efforts and challenges of cohort studies from three regions of the world: Central America, East Africa, and East Asia. These cohorts are engaging with the Davos Alzheimer's Collaborative (DAC), a global partnership that brings together cohorts from around the world to advance understanding of AD. Each cohort is poised to leverage the widespread use of mobile devices to integrate digital phenotyping into current methodologies and mitigate the lack of representativeness in AD research of racial and ethnic minorities across the globe. In addition to methods that these three cohorts are already using, DAC has developed a digital phenotyping protocol that can collect ADRD‐related data remotely via smartphone and/or in clinic via a tablet to generate a common data elements digital dataset that can be harmonized with additional clinical and molecular data being collected at each cohort site and when combined across cohorts and made accessible can provide a global data resource that is more racially/ethnically represented of the world population.

show abstract

Goal-specific brain MRI harmonization

Cited by 21 publications

References 43 publications

DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data

DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data

DeepResBat: deep residual batch harmonization accounting for covariate distribution differences

Digital phenotyping: An equal opportunity approach to reducing disparities in Alzheimer's disease and related dementia research

Contact Info

Product

Resources

About