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

Brain surface analysis is essential to neuroscience, however, the complexgeometry of the brain cortex hinders computational methods for this task. Thedifficulty arises from a discrepancy between 3D imaging data, which isrepresented in Euclidean space, and the non-Euclidean geometry of thehighly-convoluted brain surface. Recent advances in machine learning haveenabled the use of neural networks for non-Euclidean spaces. These facilitatethe learning of surface data, yet pooling strategies often remain constrainedto a single fixed-graph. This paper proposes a new learnable graph poolingmethod for processing multiple surface-valued data to output subject-basedinformation. The proposed method innovates by learning an intrinsic aggregationof graph nodes based on graph spectral embedding. We illustrate the advantagesof our approach with in-depth experiments on two large-scale benchmarkdatasets. The flexibility of the pooling strategy is evaluated on fourdifferent prediction tasks, namely, subject-sex classification, regression ofcortical region sizes, classification of Alzheimer's disease stages, and brainage regression. Our experiments demonstrate the superiority of our learnablepooling approach compared to other pooling techniques for graph convolutionnetworks, with results improving the state-of-the-art in brain surfaceanalysis.

Learnable Pooling in Graph Convolution Networks for Brain Surface Analysis