Brain Network Analysis Based on Fine-tuned Self-supervised Model for Brain Disease Diagnosis

2025-06-13

AI Summary

Current brain network foundation models are predominantly limited to unidimensional representations, constraining their generalizability and clinical applicability. To address this, we propose the first multidimensional extension of a brain network foundation model specifically designed for neurological disorder diagnosis. Our method leverages large-scale fMRI-derived functional connectivity data and employs a Transformer architecture for self-supervised pretraining. We introduce lightweight adapter modules that jointly learn dynamic inter-regional connectivity patterns and multiscale regional brain representations. A compact latent space is further constructed to balance transferability and discriminative capacity. This work establishes the first multidimensional fine-tuning paradigm for brain network foundation models. Extensive evaluations across multiple downstream diagnostic tasks—including Alzheimer’s disease and schizophrenia—demonstrate significant performance gains over state-of-the-art methods, validating both superior generalization capability and strong potential for clinical translation.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Functional brain network analysis has become an indispensable tool for brain disease analysis. It is profoundly impacted by deep learning methods, which can characterize complex connections between ROIs. However, the research on foundation models of brain network is limited and constrained to a single dimension, which restricts their extensive application in neuroscience. In this study, we propose a fine-tuned brain network model for brain disease diagnosis. It expands brain region representations across multiple dimensions based on the original brain network model, thereby enhancing its generalizability. Our model consists of two key modules: (1)an adapter module that expands brain region features across different dimensions. (2)a fine-tuned foundation brain network model, based on self-supervised learning and pre-trained on fMRI data from thousands of participants. Specifically, its transformer block is able to effectively extract brain region features and compute the inter-region associations. Moreover, we derive a compact latent representation of the brain network for brain disease diagnosis. Our downstream experiments in this study demonstrate that the proposed model achieves superior performance in brain disease diagnosis, which potentially offers a promising approach in brain network analysis research.

Problem

• Limited foundation models for brain network analysis
• Single-dimensional constraints in brain network research
• Need for generalizable multi-dimensional brain disease diagnosis

Innovation

• Fine-tuned self-supervised brain network model
• Multi-dimensional brain region feature expansion
• Transformer-based inter-region association computation