no code implementations • 7 Feb 2024 • Zhenshan Xie, Simon Dahan, Logan Z. J. Williams, M. Jorge Cardoso, Emma C. Robinson
Cortical surface analysis has gained increased prominence, given its potential implications for neurological and developmental disorders.
1 code implementation • 10 Aug 2023 • Simon Dahan, Mariana da Silva, Daniel Rueckert, Emma C Robinson
By reconstructing surface data from a masked version of the input, the proposed method effectively models cortical structure to learn strong representations that translate to improved performance in downstream tasks.
1 code implementation • 21 Mar 2023 • Simon Dahan, Abdulah Fawaz, Mohamed A. Suliman, Mariana da Silva, Logan Z. J. Williams, Daniel Rueckert, Emma C. Robinson
Surface meshes are a favoured domain for representing structural and functional information on the human cortex, but their complex topology and geometry pose significant challenges for deep learning analysis.
1 code implementation • 31 May 2022 • Simon Dahan, Logan Z. J. Williams, Abdulah Fawaz, Daniel Rueckert, Emma C. Robinson
The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds.
1 code implementation • 7 Apr 2022 • Simon Dahan, Hao Xu, Logan Z. J. Williams, Abdulah Fawaz, Chunhui Yang, Timothy S. Coalson, Michelle C. Williams, David E. Newby, A. David Edwards, Matthew F. Glasser, Alistair A. Young, Daniel Rueckert, Emma C. Robinson
Results suggest that Surface Vision Transformers (SiT) demonstrate consistent improvement over geometric deep learning methods for brain age and fluid intelligence prediction and achieve comparable performance on calcium score classification to standard metrics used in clinical practice.
1 code implementation • 30 Mar 2022 • Simon Dahan, Abdulah Fawaz, Logan Z. J. Williams, Chunhui Yang, Timothy S. Coalson, Matthew F. Glasser, A. David Edwards, Daniel Rueckert, Emma C. Robinson
Motivated by the success of attention-modelling in computer vision, we translate convolution-free vision transformer approaches to surface data, to introduce a domain-agnostic architecture to study any surface data projected onto a spherical manifold.
1 code implementation • 7 Sep 2021 • Simon Dahan, Logan Z. J. Williams, Daniel Rueckert, Emma C. Robinson
Results show a prediction accuracy of 94. 4% for sex classification (an increase of 6. 2% compared to other methods), and an improvement of correlation with fluid intelligence of 0. 325 vs 0. 144, relative to a baseline model that encodes space and time separately.