Search

Data harmonization is necessary for removing confounding effects in multi-site diffusion image analysis. One such harmonization method, LinearRISH, scales rotationally invariant spherical harmonic (RISH) features from one site ("target") to the second ("reference") to reduce confounding scanner effects. However, reference and target site designations are not arbitrary and resultant diffusion metrics (fractional anisotropy, mean diffusivity) are biased by this choice. In this work we propose MidRISH: rather than scaling reference RISH features to target RISH features, we project both sites to a mid-space. We validate MidRISH with the following experiments: harmonizing scanner differences from 37 matched patients free of cognitive impairment, and harmonizing acquisition and study differences on 117 matched patients free of cognitive impairment. We find that MidRISH reduces bias of reference selection while preserving harmonization efficacy of LinearRISH. Users should be cautious when performing LinearRISH harmonization. To select a reference site is to choose diffusion metric effect-size. Our proposed method eliminates the bias-inducing site selection step., (Copyright © 2024 Elsevier Inc. All rights reserved.)

T1-weighted (T1w) MRI has low frequency intensity artifacts due to magnetic field inhomogeneities. Removal of these biases in T1w MRI images is a critical preprocessing step to ensure spatially consistent image interpretation. N4ITK bias field correction, the current state-of-the-art, is implemented in such a way that makes it difficult to port between different pipelines and workflows, thus making it hard to reimplement and reproduce results across local, cloud, and edge platforms. Moreover, N4ITK is opaque to optimization before and after its application, meaning that methodological development must work around the inhomogeneity correction step. Given the importance of bias fields correction in structural preprocessing and flexible implementation, we pursue a deep learning approximation / reinterpretation of the N4ITK bias fields correction to create a method which is portable, flexible, and fully differentiable. In this paper, we trained a deep learning network "DeepN4" on eight independent cohorts from 72 different scanners and age ranges with N4ITK-corrected T1w MRI and bias field for supervision in log space. We found that we can closely approximate N4ITK bias fields correction with naïve networks. We evaluate the peak signal to noise ratio (PSNR) in test dataset against the N4ITK corrected images. The median PSNR of corrected images between N4ITK and DeepN4 was 47.96 dB. In addition, we assess the DeepN4 model on eight additional external datasets and show the generalizability of the approach. This study establishes that incompatible N4ITK preprocessing steps can be closely approximated by naïve deep neural networks, facilitating more flexibility. All code and models are released at https://github.com/MASILab/DeepN4 ., (© 2024. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Introduction: We compared gender disparities in later-life memory, overall and by education, in India and the United States (US)., Methods: Data (N = 7443) were from harmonized cognitive assessment protocols (HCAPs) in the Longitudinal Aging Study of India-Diagnostic Assessment of Dementia (LASI-DAD; N = 4096; 2017-19) and US Health and Retirement Study HCAP (HRS-HCAP; N = 3347; 2016-17). We derived harmonized memory factors from each study using confirmatory factor analysis. We used multivariable-adjusted linear regression to compare gender disparities in memory function between countries, overall and by education., Results: In the United States, older women had better memory than older men (0.28 SD-unit difference; 95% CI: 0.22, 0.35). In India, older women had worse memory than older men (-0.15 SD-unit difference; 95% CI: -0.20, -0.10), which attenuated with increasing education and literacy., Conclusion: We observed gender disparities in memory in India that were not present in the United States, and which dissipated with education and literacy., (© 2023 The Authors. Alzheimer's & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer's Association.)