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.
@article{arxiv.1804.04436,
title = {Extraction of Airways using Graph Neural Networks},
author = {Raghavendra Selvan and Thomas Kipf and Max Welling and Jesper H. Pedersen and Jens Petersen and Marleen de Bruijne},
journal= {arXiv preprint arXiv:1804.04436},
year = {2018}
}
Comments
Extended Abstract submitted to MIDL, 2018. 3 pages