Saved in:
Bibliographic Details
Main Authors: Lamprou, Charalampos, Alshehhi, Aamna, Hadjileontiadis, Leontios J., Seghier, Mohamed L.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.02120
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911190305734656
author Lamprou, Charalampos
Alshehhi, Aamna
Hadjileontiadis, Leontios J.
Seghier, Mohamed L.
author_facet Lamprou, Charalampos
Alshehhi, Aamna
Hadjileontiadis, Leontios J.
Seghier, Mohamed L.
contents Accounting for inter-individual variability in brain function is key to precision medicine. Here, by considering functional inter-individual variability as meaningful data rather than noise, we introduce VarCoNet, an enhanced self-supervised framework for robust functional connectome (FC) extraction from resting-state fMRI (rs-fMRI) data. VarCoNet employs self-supervised contrastive learning to exploit inherent functional inter-individual variability, serving as a brain function encoder that generates FC embeddings readily applicable to downstream tasks even in the absence of labeled data. Contrastive learning is facilitated by a novel augmentation strategy based on segmenting rs-fMRI signals. At its core, VarCoNet integrates a 1D-CNN-Transformer encoder for advanced time-series processing, enhanced with a robust Bayesian hyperparameter optimization. Our VarCoNet framework is evaluated on two downstream tasks: (i) subject fingerprinting, using rs-fMRI data from the Human Connectome Project, and (ii) autism spectrum disorder (ASD) classification, using rs-fMRI data from the ABIDE I and ABIDE II datasets. Using different brain parcellations, our extensive testing against state-of-the-art methods, including 13 deep learning methods, demonstrates VarCoNet's superiority, robustness, interpretability, and generalizability. Overall, VarCoNet provides a versatile and robust framework for FC analysis in rs-fMRI.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02120
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRI
Lamprou, Charalampos
Alshehhi, Aamna
Hadjileontiadis, Leontios J.
Seghier, Mohamed L.
Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
Neurons and Cognition
Accounting for inter-individual variability in brain function is key to precision medicine. Here, by considering functional inter-individual variability as meaningful data rather than noise, we introduce VarCoNet, an enhanced self-supervised framework for robust functional connectome (FC) extraction from resting-state fMRI (rs-fMRI) data. VarCoNet employs self-supervised contrastive learning to exploit inherent functional inter-individual variability, serving as a brain function encoder that generates FC embeddings readily applicable to downstream tasks even in the absence of labeled data. Contrastive learning is facilitated by a novel augmentation strategy based on segmenting rs-fMRI signals. At its core, VarCoNet integrates a 1D-CNN-Transformer encoder for advanced time-series processing, enhanced with a robust Bayesian hyperparameter optimization. Our VarCoNet framework is evaluated on two downstream tasks: (i) subject fingerprinting, using rs-fMRI data from the Human Connectome Project, and (ii) autism spectrum disorder (ASD) classification, using rs-fMRI data from the ABIDE I and ABIDE II datasets. Using different brain parcellations, our extensive testing against state-of-the-art methods, including 13 deep learning methods, demonstrates VarCoNet's superiority, robustness, interpretability, and generalizability. Overall, VarCoNet provides a versatile and robust framework for FC analysis in rs-fMRI.
title VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRI
topic Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
Neurons and Cognition
url https://arxiv.org/abs/2510.02120