no code implementations • 5 Jun 2018 • Salim Arslan, Sofia Ira Ktena, Ben Glocker, Daniel Rueckert
Graph convolutional networks (GCNs) allow to apply traditional convolution operations in non-Euclidean domains, where data are commonly modelled as irregular graphs.
no code implementations • 17 Feb 2018 • Salim Arslan
In this thesis, we present robust and fully-automated methods for the subdivision of the entire human cerebral cortex based on connectivity information.
no code implementations • 29 Mar 2017 • Sofia Ira Ktena, Salim Arslan, Sarah Parisot, Daniel Rueckert
Data-driven brain parcellations aim to provide a more accurate representation of an individual's functional connectivity, since they are able to capture individual variability that arises due to development or disease.