English

Extraction of Airways using Graph Neural Networks

Computer Vision and Pattern Recognition 2018-04-13 v1

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-23T01:21:34.049Z