Extraction of Airways using Graph Neural Networks

TY - ABST

T1 - Extraction of Airways using Graph Neural Networks

AU - Raghavendra, Selvan

AU - Kipf, Thomas

AU - Welling, Max

AU - Pedersen, Jesper Johannes Holst

AU - Petersen, Jens

AU - de Bruijne, Marleen

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

UR - https://openreview.net/forum?id=rkn2fjjjG

M3 - Conference abstract for conference

T2 - 1st International conference on Medical Imaging with Deep Learning

Y2 - 4 July 2018 through 6 July 2018

ER -