Large data initiatives and high-powered brain imaging analyses require the pooling of MR images acquired across multiple scanners, often using different protocols. Prospective cross-site harmonization often involves the use of a phantom or traveling subjects. However, as more datasets are becoming publicly available, there is a growing need for retrospective harmonization, pooling data from sites not originally coordinated together. Several retrospective harmonization techniques have shown promise in removing cross-site image variation. However, most unsupervised methods cannot distinguish between image-acquisition based variability and cross-site population variability, so they require that datasets contain subjects or patient groups with similar clinical or demographic information. To overcome this limitation, we consider cross-site MRI image harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a reference image directly, without knowing their site/scanner labels a priori. We trained our model using data from five large-scale multi-site datasets with varied demographics. Results demonstrated that our styleencoding model can harmonize MR images, and match intensity profiles, successfully, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. Moreover, we further demonstrated that if we included diverse enough images into the training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising novel tool for ongoing collaborative studies.
Diffusion-weighted magnetic resonance imaging (dMRI) is sensitive to microstructural changes in the brain that occur with normal aging and Alzheimer's disease (AD). There is much interest in which dMRI measures are most strongly correlated with clinical measures of AD severity, such as the clinical dementia rating (CDR), and biological processes that may be disrupted in AD, such as brain amyloid load measured using PET. Of these processes, some can be targeted using novel drugs. Since 2016, the Alzheimer's Disease Neuroimaging Initiative (ADNI) has collected dMRI data from three scanner manufacturers across 58 sites using 7 different protocols that vary in angular resolution, scan duration, and in the number and distribution of diffusion-weighted gradients. Here, we assessed dMRI data from 730 of those individuals (447 cognitively normal controls, 214 with mild cognitive impairment, 69 with dementia; age: 74.1±7.9 years; 381 female/349 male). To harmonize data from different protocols, we applied ComBat, ComBat-GAM, and CovBat to dMRI metrics from 28 white matter regions of interest. We ranked all dMRI metrics in order of the strength of clinically relevant associations, and assessed how this depended on the harmonization methods employed. dMRI metrics were associated with age and clinical impairment, but also with amyloid positivity. All harmonization methods gave comparable results while enabling data integration across multiple scanners and protocols.
Background Multi‐shell diffusion MRI (dMRI) biophysical models can estimate intracellular (ICVF), extracellular (ECVF) and free water (ISOVF) volume fractions (VFs) in brain tissue, and may offer insight into Alzheimer's disease pathological processes. These microstructural measures can be calculated in the cortex using a gray matter specific model that may be sensitive to amyloid and tau burden. Here, we evaluated relationships between regional cortical microstructural VFs and CSF amyloid and tau biomarkers. Method Multi‐shell dMRI and CSF biomarker data were available for 50 ADNI‐3 participants (age: 72.4±6.4 yrs; 20 male; 36 cognitively normal, 12 MCI, 2 dementia). Cortical ICVF, ECVF and ISOVF were estimated with the multi‐tissue spherical mean technique (MT‐SMT). Mean cortical measures were extracted from 4 lobes and the cingulate cortex, parcellated with FreeSurfer. Random‐effects linear regressions tested associations between regional dMRI measures and CSF pTau or Aβ42/Aβ40 burden, adjusting for age, sex, education, and grouping by scanning site. FDR (q=0.05) was used to correct for multiple comparisons across 5 regions, 3 diffusion measures, and 2 tests. Result Higher Aβ42/Aβ40 was associated with lower ISOVF throughout the cortex (Figure 1), and higher ECVF and ICVF in the cingulate, frontal and temporal lobes. Higher ICVF was also found in the parietal cortex. Higher pTau was associated with higher ISOVF in the occipital and parietal lobes, and lower ECVF in the frontal and parietal lobes (Figure 2). No pTau ICVF associations were detected. Conclusion Lower ICVF and higher ISOVF with greater amyloid and tau may indicate neuronal loss or edema, while lower ECVF could reflect, for example, as neuronal swelling or an influx of activated microglia. Lower ECVF with greater amyloid and tau burden may also reflect accumulation of large hydrophobic amyloid plaques and neurofibrillary tangles in the extracellular space. These results are preliminary and, as many factors influence dMRI measures, should be interpreted with caution. Future work will incorporate multimodal imaging to map associations of diffusion measures with localized PET‐derived amyloid and tau measures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.