Latent-Graph Learning for Disease Prediction

Abstract

Recently, Graph Convolutional Networks (GCNs) have proven to be a powerful machine learning tool for Computer-Aided Diagnosis (CADx) and disease prediction. A key component in these models is to build a population graph, where the graph adjacency matrix represents pair-wise patient similarities. Until now, the similarity metrics have been defined manually, usually based on meta-features like demographics or clinical scores. The definition of the metric, however, needs careful tuning, as GCNs are very sensitive to the graph structure. In this paper, we demonstrate for the first time in the CADx domain that it is possible to learn a single, optimal graph towards the GCN's downstream task of disease classification. To this end, we propose a novel, end-to-end trainable graph learning architecture for dynamic and localized graph pruning. Unlike commonly employed spectral GCN approaches, our GCN is spatial and inductive, and can thus infer previously unseen patients as well. We demonstrate significant classification improvements with our learned graph on two CADx problems in medicine. We further explain and visualize this result using an artificial dataset, underlining the importance of graph learning for more accurate and robust inference with GCNs in medical applications.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Geometric deep learning: going beyond Euclidean data
• Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
• Learning Discrete Structures for Graph Neural Networks
• Differentiable Graph Module (DGM) for Graph Convolutional Networks
• TADPOLE Challenge: Prediction of Longitudinal Evolution in Alzheimer's Disease
• InceptionGCN: Receptive Field Aware Graph Convolutional Network for Disease Prediction
• Adaptive Image-Feature Learning for Disease Classification Using Inductive Graph Networks

Cited by in corpus (6)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Differentiable Graph Module (DGM) for Graph Convolutional Networks
• Simultaneous imputation and disease classification in incomplete medical datasets using Multigraph Geometric Matrix Completion (MGMC)
• SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
• U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Prediction
• Multi-modal Graph Learning for Disease Prediction