BRIEF: BRain-Inspired network connection search with Extensive temporal feature Fusion enhances disease classification

2025-08-15

AI Summary

To address the reliance on empirically designed architectures and insufficient multi-scale feature fusion in fMRI-based psychiatric disorder classification, this paper proposes the brain-inspired BRIEF framework. First, it introduces reinforcement learning—specifically an enhanced Q-learning algorithm—into fMRI neural architecture search, formulating connectivity optimization as a Markov decision process. Second, it designs a Transformer-attention fusion module to enable hierarchical interactive learning among time-series features, static/dynamic functional connectivity, and multi-scale entropy features. The proposed method significantly improves model interpretability and generalizability: it achieves AUCs of 91.5% and 78.4% for schizophrenia and autism spectrum disorder classification, respectively—outperforming 21 state-of-the-art models by 2.2–12.1%. Moreover, BRIEF enhances biomarker identification capability, offering neurobiologically plausible insights into disorder-specific functional alterations.

Technology Category

• Machine Learning: Bio-inspired Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Brain-Sensing and Analysis

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Existing deep learning models for functional MRI-based classification have limitations in network architecture determination (relying on experience) and feature space fusion (mostly simple concatenation, lacking mutual learning). Inspired by the human brain's mechanism of updating neural connections through learning and decision-making, we proposed a novel BRain-Inspired feature Fusion (BRIEF) framework, which is able to optimize network architecture automatically by incorporating an improved neural network connection search (NCS) strategy and a Transformer-based multi-feature fusion module. Specifically, we first extracted 4 types of fMRI temporal representations, i.e., time series (TCs), static/dynamic functional connection (FNC/dFNC), and multi-scale dispersion entropy (MsDE), to construct four encoders. Within each encoder, we employed a modified Q-learning to dynamically optimize the NCS to extract high-level feature vectors, where the NCS is formulated as a Markov Decision Process. Then, all feature vectors were fused via a Transformer, leveraging both stable/time-varying connections and multi-scale dependencies across different brain regions to achieve the final classification. Additionally, an attention module was embedded to improve interpretability. The classification performance of our proposed BRIEF was compared with 21 state-of-the-art models by discriminating two mental disorders from healthy controls: schizophrenia (SZ, n=1100) and autism spectrum disorder (ASD, n=1550). BRIEF demonstrated significant improvements of 2.2% to 12.1% compared to 21 algorithms, reaching an AUC of 91.5% - 0.6% for SZ and 78.4% - 0.5% for ASD, respectively. This is the first attempt to incorporate a brain-inspired, reinforcement learning strategy to optimize fMRI-based mental disorder classification, showing significant potential for identifying precise neuroimaging biomarkers.

Problem

• Automating network architecture search for fMRI classification models
• Integrating multiple temporal fMRI features with mutual learning
• Improving mental disorder diagnosis accuracy via brain-inspired fusion

Innovation

• Improved neural network connection search strategy
• Transformer-based multi-feature fusion module
• Q-learning optimized Markov Decision Process