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

The structure and variability of the brain's connections can be investigatedvia prediction of non-imaging phenotypes using neural networks. However, knownneuroanatomical relationships between input features are generally ignored innetwork design. We propose TractGraphCNN, a novel, anatomically informed graphCNN framework for machine learning tasks using diffusion MRI tractography. AnEdgeConv module aggregates features from anatomically similar white matterconnections indicated by graph edges, and an attention module enablesinterpretation of predictive white matter tracts. Results in a sex predictiontestbed task demonstrate strong performance of TractGraphCNN in two largedatasets (HCP and ABCD). Graphs informed by white matter geometry demonstratehigher performance than graphs informed by gray matter connectivity. Overall,the bilateral cingulum and left middle longitudinal fasciculus are consistentlyhighly predictive of sex. This work shows the potential of incorporatinganatomical information, especially known anatomical similarities between inputfeatures, to guide convolutions in neural networks.

TractGraphCNN: anatomically informed graph CNN for classification using diffusion MRI tractography