English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Purpose: In the present work we describe the correction of diffusion-weightedMRI for site and scanner biases using a novel method based on invariantrepresentation.  Theory and Methods: Pooled imaging data from multiple sources are subject tovariation between the sources. Correcting for these biases has become veryimportant as imaging studies increase in size and multi-site cases become morecommon. We propose learning an intermediate representation invariant tosite/protocol variables, a technique adapted from information theory-basedalgorithmic fairness; by leveraging the data processing inequality, such arepresentation can then be used to create an image reconstruction that isuninformative of its original source, yet still faithful to underlyingstructures. To implement this, we use a deep learning method based onvariational auto-encoders (VAE) to construct scanner invariant encodings of theimaging data.  Results: To evaluate our method, we use training data from the 2018 MICCAIComputational Diffusion MRI (CDMRI) Challenge Harmonization dataset. Ourproposed method shows improvements on independent test data relative to arecently published baseline method on each subtask, mapping data from threedifferent scanning contexts to and from one separate target scanning context.  Conclusion: As imaging studies continue to grow, the use of pooled multi-siteimaging will similarly increase. Invariant representation presents a strongcandidate for the harmonization of these data.

Scanner Invariant Representations for Diffusion MRI Harmonization