VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRI

2025-10-02 · Charalampos Lamprou, Aamna Alshehhi, Leontios J. Hadjileontiadis, Mohamed L. Seghier arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.02120

Code (0)

등록된 구현이 없습니다.

Tasks

Hyperparameter Optimization Contrastive Learning

Semantic-Aware Implicit Template Learning via Part Deformation Consistency

2023-08-23 · ICCV 2023 1 · Sihyeon Kim, Minseok Joo, Jaewon Lee, Juyeon Ko 외

Learning implicit templates as neural fields has recently shown impressive performance in unsupervised shape correspondence. Despite the success, we observe current approaches, which solely rely on geometric information,…

Subject-Aware Contrastive Learning for Biosignals

2020-06-30 · Joseph Y. Cheng, Hanlin Goh, Kaan Dogrusoz, Oncel Tuzel 외

Datasets for biosignals, such as electroencephalogram (EEG) and electrocardiogram (ECG), often have noisy labels and have limited number of subjects (<100). To handle these challenges, we propose a self-supervised approa…

Anomaly Detection Contrastive Learning Data Augmentation EEG+8

DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer

2021-07-20 · Yoni Schirris, Efstratios Gavves, Iris Nederlof, Hugo Mark Horlings 외

We propose a Deep learning-based weak label learning method for analyzing whole slide images (WSIs) of Hematoxylin and Eosin (H&E) stained tumor tissue not requiring pixel-level or tile-level annotations using Self-super…

Classification Multiple Instance Learning Self-Supervised Learning whole slide images

DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Prediction

2026-05-11 · Guiqiu Liao, Matjaž Jogan, Daniel A. Hashimoto arxiv

Dense prediction tasks in surgical computer vision, such as segmentation and surgical zone prediction, can provide valuable guidance for laparoscopic and robotic surgery. However, these models often suffer from distribut…

Variability-Aware Training and Self-Tuning of Highly Quantized DNNs for Analog PIM

2021-11-11 · Zihao Deng, Michael Orshansky

DNNs deployed on analog processing in memory (PIM) architectures are subject to fabrication-time variability. We developed a new joint variability- and quantization-aware DNN training algorithm for highly quantized analo…

Quantization