InceptionGCN: Receptive Field Aware Graph Convolutional Network for Disease Prediction
This addresses disease prediction in medical imaging using multimodal data, representing an incremental improvement over existing GCN methods.
The paper tackles disease prediction by introducing InceptionGCN, a graph convolutional network architecture with geometric inception modules that capture intra- and inter-graph structural heterogeneity, achieving results on two publicly available datasets.
Geometric deep learning provides a principled and versatile manner for the integration of imaging and non-imaging modalities in the medical domain. Graph Convolutional Networks (GCNs) in particular have been explored on a wide variety of problems such as disease prediction, segmentation, and matrix completion by leveraging large, multimodal datasets. In this paper, we introduce a new spectral domain architecture for deep learning on graphs for disease prediction. The novelty lies in defining geometric 'inception modules' which are capable of capturing intra- and inter-graph structural heterogeneity during convolutions. We design filters with different kernel sizes to build our architecture. We show our disease prediction results on two publicly available datasets. Further, we provide insights on the behaviour of regular GCNs and our proposed model under varying input scenarios on simulated data.