Harmonization of diffusionMRIdata sets with adaptive dictionary learning

Abstract

Diffusion magnetic resonance imaging can indirectly infer the microstructure of tissues and provide metrics subject to normal variability in a population. Potentially abnormal values may yield essential information to support analysis of controls and patients cohorts, but subtle confounds could be mistaken for purely biologically driven variations amongst subjects. In this work, we propose a new harmonization algorithm based on adaptive dictionary learning to mitigate the unwanted variability caused by different scanner hardware while preserving the natural biological variability of the data. Our harmonization algorithm does not require paired training data sets, nor spatial registration or matching spatial resolution. Overcomplete dictionaries are learned iteratively from all data sets at the same time with an adaptive regularization criterion, removing variability attributable to the scanners in the process. The obtained mapping is applied directly in the native space of each subject toward a scanner-space. The method is evaluated with a public database which consists of two different protocols acquired on three different scanners. Results show that the effect size of the four studied diffusion metrics is preserved while removing variability attributable to the scanner. Experiments with alterations using a free water compartment, which is not simulated in the training data, shows that the modifications applied to the diffusion weighted images are preserved in the diffusion metrics after harmonization, while still reducing global variability at the same time. The algorithm could help multicenter studies pooling their data by removing scanner specific confounds, and increase statistical power in the process.

Integrating large-scale neuroimaging research datasets: Harmonisation of white matter hyperintensity measurements across Whitehall and UK Biobank datasets

“…Extra sources of variability in the measurements can be introduced by differences in the angular and spatial resolution, the number and distribution of diffusion gradient directions, the b-values, and other acquisition protocol parameters ( Tax et al., 2019 ; Fortin et al., 2017 ). Several harmonisation strategies have been developed for dMRI including statistical data pooling techniques ( Fortin et al., 2017 ), dictionary learning architectures ( St‐Jean et al., 2020 ) and registration-based methods ( Mirzaalian et al., 2016 ; Mirzaalian et al., 2018 ), but it remains an active area of research ( Tax et al., 2019 ; Ning et al., 2019 , 2020 ). Further work in this area should allow integration of DTI-derived measures in multimodal analyses such as ours, while maintaining good consistency of results.…”

Age-dependent brain morphometry in Major Depressive disorder

“…To remove confounding site, scanner, protocol effects while retaining the biological information, morphometric measures in this multi-center study was first harmonized. Various neuroimaging data harmonization techniques have been proposed in the literature, including statistical approaches ( Fortin et al, 2017 , Fortin et al, 2016 , Pomponio et al, 2020 ) and dictionary- and deep-learning approaches ( St-Jean et al, 2020 , Dewey et al, 2019 ). We harmonized individual ROI gray matter volume and cortical thickness measures using a model that builds upon a statistical harmonization technique, ComBat, which was originally developed as a batch adjustment method for genomics data ( Johnson et al, 2007 ).…”

Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions

“…Sparse dictionary learning (SDL): SDL [136] [ 137 ] was a representation learning approach that aimed to reduce the complexity of the harmonisation task by decomposing the input data as a linear combination of components. SDL could be applied to identify the cohort-invariant features to reconstruct the raw data from a huge number of random features [ 170 ].…”