Raghavendra Selvan, Thomas Kipf, Max Welling, Jesper H. Pedersen, Jens Petersen, Marleen de Bruijne
Published 2018-04-12Version 1
We present extraction of tree structures, such as airways, from image data as a graph refinement task. To this end, we propose a graph auto-encoder model that uses an encoder based on graph neural networks (GNNs) to learn embeddings from input node features and a decoder to predict connections between nodes. Performance of the GNN model is compared with mean-field networks in their ability to extract airways from 3D chest CT scans.
Comments: Extended Abstract submitted to MIDL, 2018. 3 pages
A Comparative Study of Graph Neural Networks for Shape Classification in Neuroimaging
Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks
Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks
![QR code for arXiv:1804.04436 [cs.CV]](http://oss.arxitics.com/images/favicon.svg)