Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography

Jelmer M. Wolterink*, Tim Leiner, Ivana Išgum

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Detection of coronary artery stenosis in coronary CT angiography (CCTA) requires highly personalized surface meshes enclosing the coronary lumen. In this work, we propose to use graph convolutional networks (GCNs) to predict the spatial location of vertices in a tubular surface mesh that segments the coronary artery lumen. Predictions for individual vertex locations are based on local image features as well as on features of neighboring vertices in the mesh graph. The method was trained and evaluated using the publicly available Coronary Artery Stenoses Detection and Quantification Evaluation Framework. Surface meshes enclosing the full coronary artery tree were automatically extracted. A quantitative evaluation on 78 coronary artery segments showed that these meshes corresponded closely to reference annotations, with a Dice similarity coefficient of 0.75/0.73, a mean surface distance of 0.25/0.28 mm, and a Hausdorff distance of 1.53/1.86 mm in healthy/diseased vessel segments. The results showed that inclusion of mesh information in a GCN improves segmentation overlap and accuracy over a baseline model without interaction on the mesh. The results indicate that GCNs allow efficient extraction of coronary artery surface meshes and that the use of GCNs leads to regular and more accurate meshes.

Original languageEnglish
Title of host publicationGraph Learning in Medical Imaging
Subtitle of host publication1st International Workshop, GLMI 2019, held in Conjunction with MICCAI 2019, Proceedings
EditorsDaoqiang Zhang, Luping Zhou, Biao Jie, Mingxia Liu
Place of PublicationCham
PublisherSpringer
Pages62-69
Number of pages8
ISBN (Electronic)978-3-030-35817-4
ISBN (Print)978-3-030-35816-7
DOIs
Publication statusPublished - 1 Jan 2019
Externally publishedYes
Event1st International Workshop on Graph Learning in Medical Imaging, GLMI 2019 - Shenzhen, China
Duration: 17 Oct 201917 Oct 2019
Conference number: 1

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11849
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Workshop

Workshop1st International Workshop on Graph Learning in Medical Imaging, GLMI 2019
Abbreviated titleGLMI
CountryChina
CityShenzhen
Period17/10/1917/10/19

Keywords

  • Coronary arteries
  • Coronary CT angiography
  • Graph convolutional networks
  • Lumen segmentation

Fingerprint Dive into the research topics of 'Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography'. Together they form a unique fingerprint.

  • Cite this

    Wolterink, J. M., Leiner, T., & Išgum, I. (2019). Graph Convolutional Networks for Coronary Artery Segmentation in Cardiac CT Angiography. In D. Zhang, L. Zhou, B. Jie, & M. Liu (Eds.), Graph Learning in Medical Imaging: 1st International Workshop, GLMI 2019, held in Conjunction with MICCAI 2019, Proceedings (pp. 62-69). (Lecture Notes in Computer Science; Vol. 11849). Cham: Springer. https://doi.org/10.1007/978-3-030-35817-4_8