Cited by Multimodal Hyperbolic Graph Learning for Alzheimer’s Disease Detection

Hyperbolic embedding of brain networks detects regions disrupted by neurodegeneration in Alzheimer's disease DOI

Alice Longhena, Martin Guillemaud, Fabrizio De Vico Fallani

et al.

Physical review. E, Journal Year: 2025, Volume and Issue: 111(4)

Published: April 2, 2025

Language: Английский

Citations

Brain state model: A novel method to represent the rhythmicity of object-specific selective attention from magnetoencephalography data DOI

Chunyu Liu, Xinyue Yang, Xueyuan Xu

et al.

Neurocomputing, Journal Year: 2025, Volume and Issue: unknown, P. 129920 - 129920

Published: March 1, 2025

Language: Английский

Citations

Detecting local perturbations of networks in a latent hyperbolic space DOI

Alice Longhena,

Martin Guillemaud, Mario Chávez

et al.

arXiv (Cornell University), Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Graph theoretical approaches have been proven to be effective in the characterization of connected systems, as well quantifying their dysfunction due perturbation. In this paper, we show advantage a non-Euclidean (hyperbolic) representation networks identify local connectivity perturbations and characterize induced effects on large scale. We propose two perturbation scores based representations latent geometric space, obtained through an embedding onto hyperbolic Poincar\'e disk. numerically demonstrate that these methods are able localize with homogeneous or heterogeneous degree connectivity. apply framework most perturbed brain areas epileptic patients following surgery. This study is conceived effort developing more powerful tools represent analyze networks, it first network techniques case epilepsy.

Language: Английский

Citations

Multimodal Hyperbolic Graph Learning for Alzheimer's Disease Detection DOI

C. Xie,

Wenhao Zhou,

Ciyuan Peng

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 4, 2024

Abstract Multimodal graph learning techniques have demonstrated significant potential in modeling brain networks for Alzheimer’s disease (AD) detection. However, most existing methods rely on Euclidean space representations and overlook the scale-free small-world properties of networks, which are characterized by power-law distributions dense local clustering nodes. This oversight results distortions when representing these complex structures. To address this issue, we propose a novel multimodal Poincaré Fréchet mean convolutional network (MochaGCN) AD MochaGCN leverages exponential growth characteristics hyperbolic to capture networks. Specifically, combine convolution extract features from enhancing their rep-resentations space. Our approach constructs integrating information diffusion tensor imaging (DTI) functional magnetic resonance (fMRI) data. Experiments Disease Neuroimaging Initiative (ADNI) dataset demonstrate that proposed method outperforms state-of-the-art techniques.

Language: Английский

Citations

Multimodal Hyperbolic Graph Learning for Alzheimer’s Disease Detection DOI

C. Xie,

Wenhao Zhou,

Ciyuan Peng

et al.

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 390 - 403

Published: Nov. 20, 2024

Language: Английский

Citations