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

We propose a geometric deep-learning-based framework, TractGeoNet, forperforming regression using diffusion magnetic resonance imaging (dMRI)tractography and associated pointwise tissue microstructure measurements. Byemploying a point cloud representation, TractGeoNet can directly utilizepointwise tissue microstructure and positional information from all pointswithin a fiber tract. To improve regression performance, we propose a novelloss function, the Paired-Siamese Regression loss, which encourages the modelto focus on accurately predicting the relative differences between regressionlabel scores rather than just their absolute values. In addition, we propose aCritical Region Localization algorithm to identify highly predictive anatomicalregions within the white matter fiber tracts for the regression task. Weevaluate the effectiveness of the proposed method by predicting individualperformance on two neuropsychological assessments of language using a datasetof 20 association white matter fiber tracts from 806 subjects from the HumanConnectome Project. The results demonstrate superior prediction performance ofTractGeoNet compared to several popular regression models. Of the twenty tractsstudied, we find that the left arcuate fasciculus tract is the most highlypredictive of the two studied language performance assessments. The localizedcritical regions are widespread and distributed across both hemispheres and allcerebral lobes, including areas of the brain considered important for languagefunction such as superior and anterior temporal regions, pars opercularis, andprecentral gyrus. Overall, TractGeoNet demonstrates the potential of geometricdeep learning to enhance the study of the brain's white matter fiber tracts andto relate their structure to human traits such as language performance.

TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance