Extraction of Airways using Graph Neural Networks

Selvan Raghavendra; Thomas  Kipf; Max Welling; Jesper Johannes Holst Pedersen; Jens Petersen; Marleen de Bruijne

Extraction of Airways using Graph Neural Networks

Selvan Raghavendra, Thomas Kipf, Max Welling, Jesper Johannes Holst Pedersen, Jens Petersen, Marleen de Bruijne

Department of Clinical Medicine

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.

Original language	English
Publication date	2018
Number of pages	3
Publication status	Published - 2018
Event	1st International conference on Medical Imaging with Deep Learning - Amsterdam, Netherlands Duration: 4 Jul 2018 → 6 Jul 2018

Conference

Conference	1st International conference on Medical Imaging with Deep Learning
Country/Territory	Netherlands
City	Amsterdam
Period	04/07/2018 → 06/07/2018

Cite this

@conference{524ad3bb9bce4db8ba02ca7fa42fc4b4,

title = "Extraction of Airways using Graph Neural Networks",

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. ",

author = "Selvan Raghavendra and Thomas Kipf and Max Welling and Pedersen, {Jesper Johannes Holst} and Jens Petersen and {de Bruijne}, Marleen",

year = "2018",

language = "English",

note = "1st International conference on Medical Imaging with Deep Learning ; Conference date: 04-07-2018 Through 06-07-2018",

}

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 -

Extraction of Airways using Graph Neural Networks

Abstract

Conference

Other files and links

Fingerprint

Cite this