Edge-variational Graph Convolutional Networks for Uncertainty-aware Disease Prediction

TL;DR

This paper introduces a novel graph convolutional network framework that integrates multimodal data with uncertainty estimation for improved disease prediction across various medical conditions.

Contribution

It proposes a generalizable, uncertainty-aware graph neural network with variational edges and Monte-Carlo edge dropout for multimodal disease diagnosis.

Findings

Improves diagnostic accuracy for Autism, Alzheimer's, and ocular diseases.

Demonstrates effectiveness across four different databases.

Provides a mathematically proven, optimizable framework for multimodal data integration.

Abstract

There is a rising need for computational models that can complementarily leverage data of different modalities while investigating associations between subjects for population-based disease analysis. Despite the success of convolutional neural networks in representation learning for imaging data, it is still a very challenging task. In this paper, we propose a generalizable framework that can automatically integrate imaging data with non-imaging data in populations for uncertainty-aware disease prediction. At its core is a learnable adaptive population graph with variational edges, which we mathematically prove that it is optimizable in conjunction with graph convolutional neural networks. To estimate the predictive uncertainty related to the graph topology, we propose the novel concept of Monte-Carlo edge dropout. Experimental results on four databases show that our method can consistently and significantly improve the diagnostic accuracy for Autism spectrum disorder, Alzheimer's disease, and ocular diseases, indicating its generalizability in leveraging multimodal data for computer-aided diagnosis.