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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The human thalamus is a highly connected subcortical grey-matter structurewithin the brain. It comprises dozens of nuclei with different function andconnectivity, which are affected differently by disease. For this reason, thereis growing interest in studying the thalamic nuclei in vivo with MRI. Tools areavailable to segment the thalamus from 1 mm T1 scans, but the contrast of thelateral and internal boundaries is too faint to produce reliable segmentations.Some tools have attempted to incorporate information from diffusion MRI in thesegmentation to refine these boundaries, but do not generalise well acrossdiffusion MRI acquisitions. Here we present the first CNN that can segmentthalamic nuclei from T1 and diffusion data of any resolution without retrainingor fine tuning. Our method builds on a public histological atlas of thethalamic nuclei and silver standard segmentations on high-quality diffusiondata obtained with a recent Bayesian adaptive segmentation tool. We combinethese with an approximate degradation model for fast domain randomisationduring training. Our CNN produces a segmentation at 0.7 mm isotropicresolution, irrespective of the resolution of the input. Moreover, it uses aparsimonious model of the diffusion signal at each voxel (fractional anisotropyand principal eigenvector) that is compatible with virtually any set ofdirections and b-values, including huge amounts of legacy data. We show resultsof our proposed method on three heterogeneous datasets acquired on dozens ofdifferent scanners. An implementation of the method is publicly available athttps://freesurfer.net/fswiki/ThalamicNucleiDTI.

Domain-agnostic segmentation of thalamic nuclei from joint structural and diffusion MRI