MAPI-GNN: Multi-Activation Plane Interaction Graph Neural Network for Multimodal Medical Diagnosis

TL;DR

MAPI-GNN introduces a dynamic, multi-graph approach for multimodal medical diagnosis, leveraging semantic disentanglement and relational fusion to improve accuracy over static graph methods.

Contribution

The paper presents a novel multi-activation plane interaction framework that reconstructs patient-specific graphs from disentangled features for enhanced diagnosis.

Findings

Outperforms state-of-the-art methods on two medical diagnosis tasks.

Effectively models patient-specific pathological relationships.

Demonstrates robustness across diverse multimodal datasets.

Abstract

Graph neural networks are increasingly applied to multimodal medical diagnosis for their inherent relational modeling capabilities. However, their efficacy is often compromised by the prevailing reliance on a single, static graph built from indiscriminate features, hindering the ability to model patient-specific pathological relationships. To this end, the proposed Multi-Activation Plane Interaction Graph Neural Network (MAPI-GNN) reconstructs this single-graph paradigm by learning a multifaceted graph profile from semantically disentangled feature subspaces. The framework first uncovers latent graph-aware patterns via a multi-dimensional discriminator; these patterns then guide the dynamic construction of a stack of activation graphs; and this multifaceted profile is finally aggregated and contextualized by a relational fusion engine for a robust diagnosis. Extensive experiments on two diverse tasks, comprising over 1300 patient samples, demonstrate that MAPI-GNN significantly outperforms state-of-the-art methods.