Dilated convolutional neural networks for cardiovascular MR segmentation in congenital heart disease

Jelmer M. Wolterink*, Tim Leiner, Max A. Viergever, Ivana Išgum

*Corresponding author for this work

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

34 Citations (Scopus)

Abstract

We propose an automatic method using dilated convolutional neural networks (CNNs) for segmentation of the myocardium and blood pool in cardiovascular MR (CMR) of patients with congenital heart disease (CHD). Ten training and ten test CMR scans cropped to an ROI around the heart were provided in the MICCAI 2016 HVSMR challenge. A dilated CNNwith a receptive field of 131×131 voxels was trained for myocardium and blood pool segmentation in axial, sagittal and coronal image slices. Performance was evaluated within the HVSMR challenge. Automatic segmentation of the test scans resulted in Dice indices of 0.80 ± 0.06 and 0.93 ± 0.02, average distances to boundaries of 0.96 ± 0.31 and 0.89 ± 0.24 mm, and Hausdorff distances of 6.13 ± 3.76 and 7.07 ± 3.01mm for the myocardium and blood pool, respectively. Segmentation took 41.5 ± 14.7 s per scan. In conclusion, dilated CNNs trained on a small set of CMR images of CHD patients showing large anatomical variability provide accurate myocardium and blood pool segmentations.

Original languageEnglish
Title of host publicationReconstruction, Segmentation, and Analysis of Medical Images
Subtitle of host publicationFirst International Workshops, RAMBO 2016 and HVSMR 2016, Held in Conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Revised Selected Papers
EditorsMaria A. Zuluaga, Mehdi H. Moghari, Danielle F. Pace, Bernhard Kainz, Kanwal Bhatia
Place of PublicationCham
PublisherSpringer
Pages95-102
Number of pages8
ISBN (Electronic)978-3-319-52280-7
ISBN (Print)978-3-319-52279-1
DOIs
Publication statusPublished - 1 Jan 2017
Externally publishedYes
Event1st International Workshop on Reconstruction and Analysis of Moving Body Organs, RAMBO 2016 and 1st International Workshop on Whole-Heart and Great Vessel Segmentation from 3D Cardiovascular MRI in Congenital Heart Disease, HVSMR 2016 - Athens, Greece
Duration: 17 Oct 201621 Oct 2016
Conference number: 1

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10129
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference1st International Workshop on Reconstruction and Analysis of Moving Body Organs, RAMBO 2016 and 1st International Workshop on Whole-Heart and Great Vessel Segmentation from 3D Cardiovascular MRI in Congenital Heart Disease, HVSMR 2016
Abbreviated titleRAMBOI-HVSMR
CountryGreece
CityAthens
Period17/10/1621/10/16

Keywords

  • Cardiovascular MR
  • Congenital heart disease
  • Deep learning
  • Dilated convolutional neural networks
  • Medical image segmentation

Fingerprint Dive into the research topics of 'Dilated convolutional neural networks for cardiovascular MR segmentation in congenital heart disease'. Together they form a unique fingerprint.

Cite this