DeepAI AI Chat
Log In Sign Up

Latent Patient Network Learning for Automatic Diagnosis

by   Luca Cosmo, et al.
USI Università della Svizzera italiana

Recently, Graph Convolutional Networks (GCNs) has 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.


page 5

page 8


Dynamic Dual-Graph Fusion Convolutional Network For Alzheimer's Disease Diagnosis

In this paper, a dynamic dual-graph fusion convolutional network is prop...

Decision Support for Intoxication Prediction Using Graph Convolutional Networks

Every day, poison control centers (PCC) are called for immediate classif...

AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction

Recently, Graph Convolutional Networks (GCNs) have proven to be a powerf...

RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data

Disease prediction is a well-known classification problem in medical app...

Learning Adaptive Neighborhoods for Graph Neural Networks

Graph convolutional networks (GCNs) enable end-to-end learning on graph ...

Adaptive image-feature learning for disease classification using inductive graph networks

Recently, Geometric Deep Learning (GDL) has been introduced as a novel a...