PIME: Prototype-based Interpretable MCTS-Enhanced Brain Network Analysis for Disorder Diagnosis

2026-02-24

AI Summary

This work proposes an intrinsically interpretable framework that integrates prototype learning with consistency training to address the challenges of noise interference in fMRI functional connectivity networks and the limited reliability of existing post-hoc explanation methods. By constructing a structured latent space and leveraging Monte Carlo Tree Search (MCTS) under prototype constraints, the method extracts minimal sufficient explanatory subgraphs, enabling stable and neuroscientifically consistent brain network analysis and disease diagnosis. Notably, this approach is the first to unify intrinsic interpretability with subgraph optimization through a prototype consistency objective combined with MCTS. Evaluated on three fMRI benchmark datasets, it achieves state-of-the-art performance, identifies key brain regions aligned with neuroimaging consensus, and demonstrates 90% cross-atlas explanation stability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Interpretability, Explainability, and Transparency
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Machine learning and data science for the Web

Abstract

Recent deep learning methods for fMRI-based diagnosis have achieved promising accuracy by modeling functional connectivity networks. However, standard approaches often struggle with noisy interactions, and conventional post-hoc attribution methods may lack reliability, potentially highlighting dataset-specific artifacts. To address these challenges, we introduce PIME, an interpretable framework that bridges intrinsic interpretability with minimal-sufficient subgraph optimization by integrating prototype-based classification and consistency training with structural perturbations during learning. This encourages a structured latent space and enables Monte Carlo Tree Search (MCTS) under a prototype-consistent objective to extract compact minimal-sufficient explanatory subgraphs post-training. Experiments on three benchmark fMRI datasets demonstrate that PIME achieves state-of-the-art performance. Furthermore, by constraining the search space via learned prototypes, PIME identifies critical brain regions that are consistent with established neuroimaging findings. Stability analysis shows 90% reproducibility and consistent explanations across atlases.

Problem

• fMRI
• brain network analysis
• disorder diagnosis
• interpretability
• noisy interactions

Innovation

• prototype-based interpretability
• Monte Carlo Tree Search (MCTS)
• minimal-sufficient subgraph
• consistency training
• fMRI brain network analysis