Hierarchical Mesh Transformers with Topology-Guided Pretraining for Morphometric Analysis of Brain Structures

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xiong, Yujian, Farazi, Mohammad, Chen, Yanxi, Zhu, Wenhui, Dong, Xuanzhao, Lepore, Natasha, Su, Yi, Mushtaq, Raza, Foldes, Stephen, Yang, Andrew, Wang, Yalin
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911571351961600
author Xiong, Yujian
Farazi, Mohammad
Chen, Yanxi
Zhu, Wenhui
Dong, Xuanzhao
Lepore, Natasha
Su, Yi
Mushtaq, Raza
Foldes, Stephen
Yang, Andrew
Wang, Yalin
author_facet Xiong, Yujian
Farazi, Mohammad
Chen, Yanxi
Zhu, Wenhui
Dong, Xuanzhao
Lepore, Natasha
Su, Yi
Mushtaq, Raza
Foldes, Stephen
Yang, Andrew
Wang, Yalin
contents Representation learning on large-scale unstructured volumetric and surface meshes poses significant challenges in neuroimaging, especially when models must incorporate diverse vertex-level morphometric descriptors, such as cortical thickness, curvature, sulcal depth, and myelin content, which carry subtle disease-related signals. Current approaches either ignore these clinically informative features or support only a single mesh topology, restricting their use across imaging pipelines. We introduce a hierarchical transformer framework designed for heterogeneous mesh analysis that operates on spatially adaptive tree partitions constructed from simplicial complexes of arbitrary order. This design accommodates both volumetric and surface discretizations within a single architecture, enabling efficient multi-scale attention without topology-specific modifications. A feature projection module maps variable-length per-vertex clinical descriptors into the spatial hierarchy, separating geometric structure from feature dimensionality and allowing seamless integration of different neuroimaging feature sets. Self-supervised pretraining via masked reconstruction of both coordinates and morphometric channels on large unlabeled cohorts yields a transferable encoder backbone applicable to diverse downstream tasks and mesh modalities. We validate our approach on Alzheimer's disease classification and amyloid burden prediction using volumetric brain meshes from ADNI, as well as focal cortical dysplasia detection on cortical surface meshes from the MELD dataset, achieving state-of-the-art results across all benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05215
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchical Mesh Transformers with Topology-Guided Pretraining for Morphometric Analysis of Brain Structures
Xiong, Yujian
Farazi, Mohammad
Chen, Yanxi
Zhu, Wenhui
Dong, Xuanzhao
Lepore, Natasha
Su, Yi
Mushtaq, Raza
Foldes, Stephen
Yang, Andrew
Wang, Yalin
Computer Vision and Pattern Recognition
Neurons and Cognition
Representation learning on large-scale unstructured volumetric and surface meshes poses significant challenges in neuroimaging, especially when models must incorporate diverse vertex-level morphometric descriptors, such as cortical thickness, curvature, sulcal depth, and myelin content, which carry subtle disease-related signals. Current approaches either ignore these clinically informative features or support only a single mesh topology, restricting their use across imaging pipelines. We introduce a hierarchical transformer framework designed for heterogeneous mesh analysis that operates on spatially adaptive tree partitions constructed from simplicial complexes of arbitrary order. This design accommodates both volumetric and surface discretizations within a single architecture, enabling efficient multi-scale attention without topology-specific modifications. A feature projection module maps variable-length per-vertex clinical descriptors into the spatial hierarchy, separating geometric structure from feature dimensionality and allowing seamless integration of different neuroimaging feature sets. Self-supervised pretraining via masked reconstruction of both coordinates and morphometric channels on large unlabeled cohorts yields a transferable encoder backbone applicable to diverse downstream tasks and mesh modalities. We validate our approach on Alzheimer's disease classification and amyloid burden prediction using volumetric brain meshes from ADNI, as well as focal cortical dysplasia detection on cortical surface meshes from the MELD dataset, achieving state-of-the-art results across all benchmarks.
title Hierarchical Mesh Transformers with Topology-Guided Pretraining for Morphometric Analysis of Brain Structures
topic Computer Vision and Pattern Recognition
Neurons and Cognition
url https://arxiv.org/abs/2604.05215