BrainTAP: Brain Disorder Prediction with Adaptive Distill and Selective Prior Integration

2026-02-10

AI Summary

Existing multimodal brain network fusion approaches often overlook modality-specific characteristics due to shallow interactions or excessive homogenization, and they statically incorporate expert priors, thereby limiting their predictive performance for attention-related disorders. To address these limitations, this work proposes a Transformer-based framework that introduces an Adaptive Mutual Distillation (AMD) mechanism to enable hierarchical and collaborative interaction between functional and structural connectivity. Additionally, a Selective Prior Fusion (SPF) module is designed to dynamically integrate neuroanatomical knowledge. Experiments on the ABCD dataset demonstrate that the proposed method significantly outperforms current state-of-the-art models, achieving higher accuracy in disorder prediction and overcoming the constraints of conventional multimodal fusion strategies and static prior utilization.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Predicting clinical outcomes from brain networks in large-scale neuroimaging cohorts such as the Adolescent Brain Cognitive Development (ABCD) study requires effectively integrating functional connectivity (FC) and structural connectivity (SC) while incorporating expert neurobiological knowledge. However, existing multimodal fusion approaches are shallow or over-homogenize the inherently heterogeneous characteristics of FC and SC, while expert-defined anatomical priors are underutilized with static integration. To address these limitations, we propose Brain Transformer with Adaptive Mutual-Distill and Selective Prior Fusion (BrainTAP). We introduce Adaptive Mutual Distill (AMD), which enables layer-wise information exchange between modalities through learnable distill-intact ratios, preserving modality-specific signals while capturing cross-modal synergies. We further develop Selective Prior Fusion (SPF), which integrates expert-defined anatomical priors in an adaptive way. Evaluated on the ABCD dataset for predicting attention-related disorders, BrainTAP achieves superior performance over state-of-the-art baselines, demonstrating its effectiveness for brain disorder prediction.

Problem

• brain disorder prediction
• multimodal fusion
• functional connectivity
• structural connectivity
• anatomical priors

Innovation

• Adaptive Mutual Distill
• Selective Prior Fusion
• multimodal fusion
• brain disorder prediction
• neuroimaging