Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dahan, Simon, Fawaz, Abdulah, Williams, Logan Z. J., Yang, Chunhui, Coalson, Timothy S., Glasser, Matthew F., Edwards, A. David, Rueckert, Daniel, Robinson, Emma C.
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913377151877120
author Dahan, Simon
Fawaz, Abdulah
Williams, Logan Z. J.
Yang, Chunhui
Coalson, Timothy S.
Glasser, Matthew F.
Edwards, A. David
Rueckert, Daniel
Robinson, Emma C.
author_facet Dahan, Simon
Fawaz, Abdulah
Williams, Logan Z. J.
Yang, Chunhui
Coalson, Timothy S.
Glasser, Matthew F.
Edwards, A. David
Rueckert, Daniel
Robinson, Emma C.
contents The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range associations, as the generalisation of convolutions to irregular surfaces is non-trivial. 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. Here, surface patching is achieved by representing spherical data as a sequence of triangular patches, extracted from a subdivided icosphere. A transformer model encodes the sequence of patches via successive multi-head self-attention layers while preserving the sequence resolution. We validate the performance of the proposed Surface Vision Transformer (SiT) on the task of phenotype regression from cortical surface metrics derived from the Developing Human Connectome Project (dHCP). Experiments show that the SiT generally outperforms surface CNNs, while performing comparably on registered and unregistered data. Analysis of transformer attention maps offers strong potential to characterise subtle cognitive developmental patterns.
format Preprint
id arxiv_https___arxiv_org_abs_2203_16414
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis
Dahan, Simon
Fawaz, Abdulah
Williams, Logan Z. J.
Yang, Chunhui
Coalson, Timothy S.
Glasser, Matthew F.
Edwards, A. David
Rueckert, Daniel
Robinson, Emma C.
Computer Vision and Pattern Recognition
Image and Video Processing
Neurons and Cognition
The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range associations, as the generalisation of convolutions to irregular surfaces is non-trivial. 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. Here, surface patching is achieved by representing spherical data as a sequence of triangular patches, extracted from a subdivided icosphere. A transformer model encodes the sequence of patches via successive multi-head self-attention layers while preserving the sequence resolution. We validate the performance of the proposed Surface Vision Transformer (SiT) on the task of phenotype regression from cortical surface metrics derived from the Developing Human Connectome Project (dHCP). Experiments show that the SiT generally outperforms surface CNNs, while performing comparably on registered and unregistered data. Analysis of transformer attention maps offers strong potential to characterise subtle cognitive developmental patterns.
title Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis
topic Computer Vision and Pattern Recognition
Image and Video Processing
Neurons and Cognition
url https://arxiv.org/abs/2203.16414