Topology-Aware Graph Augmentation for Predicting Clinical Trajectories in Neurocognitive Disorders

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Qianqian, Wang, Wei, Fang, Yuqi, Li, Hong-Jun, Bozoki, Andrea, Liu, Mingxia
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910683352793088
author Wang, Qianqian
Wang, Wei
Fang, Yuqi
Li, Hong-Jun
Bozoki, Andrea
Liu, Mingxia
author_facet Wang, Qianqian
Wang, Wei
Fang, Yuqi
Li, Hong-Jun
Bozoki, Andrea
Liu, Mingxia
contents Brain networks/graphs derived from resting-state functional MRI (fMRI) help study underlying pathophysiology of neurocognitive disorders by measuring neuronal activities in the brain. Some studies utilize learning-based methods for brain network analysis, but typically suffer from low model generalizability caused by scarce labeled fMRI data. As a notable self-supervised strategy, graph contrastive learning helps leverage auxiliary unlabeled data. But existing methods generally arbitrarily perturb graph nodes/edges to generate augmented graphs, without considering essential topology information of brain networks. To this end, we propose a topology-aware graph augmentation (TGA) framework, comprising a pretext model to train a generalizable encoder on large-scale unlabeled fMRI cohorts and a task-specific model to perform downstream tasks on a small target dataset. In the pretext model, we design two novel topology-aware graph augmentation strategies: (1) hub-preserving node dropping that prioritizes preserving brain hub regions according to node importance, and (2) weight-dependent edge removing that focuses on keeping important functional connectivities based on edge weights. Experiments on 1, 688 fMRI scans suggest that TGA outperforms several state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00888
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Topology-Aware Graph Augmentation for Predicting Clinical Trajectories in Neurocognitive Disorders
Wang, Qianqian
Wang, Wei
Fang, Yuqi
Li, Hong-Jun
Bozoki, Andrea
Liu, Mingxia
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Neurons and Cognition
Brain networks/graphs derived from resting-state functional MRI (fMRI) help study underlying pathophysiology of neurocognitive disorders by measuring neuronal activities in the brain. Some studies utilize learning-based methods for brain network analysis, but typically suffer from low model generalizability caused by scarce labeled fMRI data. As a notable self-supervised strategy, graph contrastive learning helps leverage auxiliary unlabeled data. But existing methods generally arbitrarily perturb graph nodes/edges to generate augmented graphs, without considering essential topology information of brain networks. To this end, we propose a topology-aware graph augmentation (TGA) framework, comprising a pretext model to train a generalizable encoder on large-scale unlabeled fMRI cohorts and a task-specific model to perform downstream tasks on a small target dataset. In the pretext model, we design two novel topology-aware graph augmentation strategies: (1) hub-preserving node dropping that prioritizes preserving brain hub regions according to node importance, and (2) weight-dependent edge removing that focuses on keeping important functional connectivities based on edge weights. Experiments on 1, 688 fMRI scans suggest that TGA outperforms several state-of-the-art methods.
title Topology-Aware Graph Augmentation for Predicting Clinical Trajectories in Neurocognitive Disorders
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Neurons and Cognition
url https://arxiv.org/abs/2411.00888