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

Current deep learning approaches for diffusion MRI modeling circumvent theneed for densely-sampled diffusion-weighted images (DWIs) by directlypredicting microstructural indices from sparsely-sampled DWIs. However, theyimplicitly make unrealistic assumptions of static $q$-space sampling duringtraining and reconstruction. Further, such approaches can restrict downstreamusage of variably sampled DWIs for usages including the estimation ofmicrostructural indices or tractography. We propose a generative adversarialtranslation framework for high-quality DWI synthesis with arbitrary $q$-spacesampling given commonly acquired structural images (e.g., B0, T1, T2). Ourtranslation network linearly modulates its internal representations conditionedon continuous $q$-space information, thus removing the need for fixed samplingschemes. Moreover, this approach enables downstream estimation of high-qualitymicrostructural maps from arbitrarily subsampled DWIs, which may beparticularly important in cases with sparsely sampled DWIs. Across severalrecent methodologies, the proposed approach yields improved DWI synthesisaccuracy and fidelity with enhanced downstream utility as quantified by theaccuracy of scalar microstructure indices estimated from the synthesizedimages. Code is available athttps://github.com/mengweiren/q-space-conditioned-dwi-synthesis.

Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI