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

Ziwei Qin, Xuhui Song, Deqing Huang, Na Qin, Jun Li
12/23/2025
cs.CV

No official code found. Best implementation: HecateBlair/MAPI-GNN (3 stars, MIT, last commit 2025-12-22).

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.

View on arXivView PDF

Code Implementations(1)

HecateBlair/MAPI-GNNCommunity69%
MIT

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

30PythonJan 14, 202510 months agoMIT

Similar Papers

TopoTune : A Framework for Generalized Combinatorial Complex Neural Networks

84% match1 repo2452026

Enhanced Graph Convolutional Network with Chebyshev Spectral Graph and Graph Attention for Autism Spectrum Disorder Classification

84% match1 repo2025

Information Bottleneck-Guided Heterogeneous Graph Learning for Interpretable Neurodevelopmental Disorder Diagnosis

84% match2025

TGraphX: Tensor-Aware Graph Neural Network for Multi-Dimensional Feature Learning

82% match1 repo22025

MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction

82% match2023

MM-GTUNets: Unified Multi-Modal Graph Deep Learning for Brain Disorders Prediction

82% match1 repo392024

Cite this paper

@article{qin2025mapignn,
  title  = {MAPI-GNN: Multi-Activation Plane Interaction Graph Neural Network for Multimodal Medical Diagnosis},
  author = {Ziwei Qin and Xuhui Song and Deqing Huang and Na Qin and Jun Li},
  year   = {2025},
  eprint = {2512.20026},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.20026v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.20026.svg)](https://codeofpaper.com/paper/2512.20026)

Discussion