Heart chamber segmentation from CT using convolutional neural networks

James D. Dormer; Ling Ma; Martin Halicek; Carolyn M. Reilly; Eduard Schreibmann; Baowei Fei

doi:10.1117/12.2293554

Heart chamber segmentation from CT using convolutional neural networks

James D. Dormer, Ling Ma, Martin Halicek, Carolyn M. Reilly, Eduard Schreibmann, Baowei Fei

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

26 Scopus citations

Abstract

CT is routinely used for radiotherapy planning with organs and regions of interest being segmented for diagnostic evaluation and parameter optimization. For cardiac segmentation, many methods have been proposed for left ventricular segmentation, but few for simultaneous segmentation of the entire heart. In this work, we present a convolutional neural networks (CNN)-based cardiac chamber segmentation method for 3D CT with 5 classes: left ventricle, right ventricle, left atrium, right atrium, and background. We achieved an overall accuracy of 87.2% ± 3.3% and an overall chamber accuracy of 85.6 ± 6.1%. The deep learning based segmentation method may provide an automatic tool for cardiac segmentation on CT images.

Original language	English (US)
Title of host publication	Medical Imaging 2018
Subtitle of host publication	Biomedical Applications in Molecular, Structural, and Functional Imaging
Editors	Barjor Gimi, Andrzej Krol
Publisher	SPIE
ISBN (Electronic)	9781510616455
DOIs	https://doi.org/10.1117/12.2293554
State	Published - 2018
Externally published	Yes
Event	Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging - Houston, United States Duration: Feb 11 2018 → Feb 13 2018

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	10578
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging
Country/Territory	United States
City	Houston
Period	2/11/18 → 2/13/18

Keywords

CT imaging
Cardiac imaging
Convolutional neural networks
Deep Learning
Heart chamber segmentation
Image segmentation
Whole heart segmentation

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Biomaterials
Atomic and Molecular Physics, and Optics
Radiology Nuclear Medicine and imaging

Access to Document

10.1117/12.2293554

Cite this

Dormer, J. D., Ma, L., Halicek, M., Reilly, C. M., Schreibmann, E., & Fei, B. (2018). Heart chamber segmentation from CT using convolutional neural networks. In B. Gimi, & A. Krol (Eds.), Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging Article 105782S (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10578). SPIE. https://doi.org/10.1117/12.2293554

Heart chamber segmentation from CT using convolutional neural networks. / Dormer, James D.; Ma, Ling; Halicek, Martin et al.
Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging. ed. / Barjor Gimi; Andrzej Krol. SPIE, 2018. 105782S (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10578).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Dormer, JD, Ma, L, Halicek, M, Reilly, CM, Schreibmann, E & Fei, B 2018, Heart chamber segmentation from CT using convolutional neural networks. in B Gimi & A Krol (eds), Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging., 105782S, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10578, SPIE, Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging, Houston, United States, 2/11/18. https://doi.org/10.1117/12.2293554

@inproceedings{ca9bcd248a1746848f2eab2e71ab146f,

title = "Heart chamber segmentation from CT using convolutional neural networks",

abstract = "CT is routinely used for radiotherapy planning with organs and regions of interest being segmented for diagnostic evaluation and parameter optimization. For cardiac segmentation, many methods have been proposed for left ventricular segmentation, but few for simultaneous segmentation of the entire heart. In this work, we present a convolutional neural networks (CNN)-based cardiac chamber segmentation method for 3D CT with 5 classes: left ventricle, right ventricle, left atrium, right atrium, and background. We achieved an overall accuracy of 87.2% ± 3.3% and an overall chamber accuracy of 85.6 ± 6.1%. The deep learning based segmentation method may provide an automatic tool for cardiac segmentation on CT images.",

keywords = "CT imaging, Cardiac imaging, Convolutional neural networks, Deep Learning, Heart chamber segmentation, Image segmentation, Whole heart segmentation",

author = "Dormer, {James D.} and Ling Ma and Martin Halicek and Reilly, {Carolyn M.} and Eduard Schreibmann and Baowei Fei",

note = "Funding Information: This research is supported in part by NIH grants (CA176684, CA156775, and CA204254) and by the National Cancer Institute (NCI) via NRG Oncology, a member of the NCI National Clinical Trials Network with Federal funds from the Department of Health and Human Services under Grant Number U10 CA37422. The contents of this publication do not necessarily reflect the views or policies of the Department of Health and Human Services, nor does it imply endorsement by the U.S. Government. Publisher Copyright: {\textcopyright} 2018 SPIE.; Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging ; Conference date: 11-02-2018 Through 13-02-2018",

year = "2018",

doi = "10.1117/12.2293554",

language = "English (US)",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Barjor Gimi and Andrzej Krol",

booktitle = "Medical Imaging 2018",

}

TY - GEN

T1 - Heart chamber segmentation from CT using convolutional neural networks

AU - Dormer, James D.

AU - Ma, Ling

AU - Halicek, Martin

AU - Reilly, Carolyn M.

AU - Schreibmann, Eduard

AU - Fei, Baowei

N1 - Funding Information: This research is supported in part by NIH grants (CA176684, CA156775, and CA204254) and by the National Cancer Institute (NCI) via NRG Oncology, a member of the NCI National Clinical Trials Network with Federal funds from the Department of Health and Human Services under Grant Number U10 CA37422. The contents of this publication do not necessarily reflect the views or policies of the Department of Health and Human Services, nor does it imply endorsement by the U.S. Government. Publisher Copyright: © 2018 SPIE.

PY - 2018

Y1 - 2018

N2 - CT is routinely used for radiotherapy planning with organs and regions of interest being segmented for diagnostic evaluation and parameter optimization. For cardiac segmentation, many methods have been proposed for left ventricular segmentation, but few for simultaneous segmentation of the entire heart. In this work, we present a convolutional neural networks (CNN)-based cardiac chamber segmentation method for 3D CT with 5 classes: left ventricle, right ventricle, left atrium, right atrium, and background. We achieved an overall accuracy of 87.2% ± 3.3% and an overall chamber accuracy of 85.6 ± 6.1%. The deep learning based segmentation method may provide an automatic tool for cardiac segmentation on CT images.

AB - CT is routinely used for radiotherapy planning with organs and regions of interest being segmented for diagnostic evaluation and parameter optimization. For cardiac segmentation, many methods have been proposed for left ventricular segmentation, but few for simultaneous segmentation of the entire heart. In this work, we present a convolutional neural networks (CNN)-based cardiac chamber segmentation method for 3D CT with 5 classes: left ventricle, right ventricle, left atrium, right atrium, and background. We achieved an overall accuracy of 87.2% ± 3.3% and an overall chamber accuracy of 85.6 ± 6.1%. The deep learning based segmentation method may provide an automatic tool for cardiac segmentation on CT images.

KW - CT imaging

KW - Cardiac imaging

KW - Convolutional neural networks

KW - Deep Learning

KW - Heart chamber segmentation

KW - Image segmentation

KW - Whole heart segmentation

UR - http://www.scopus.com/inward/record.url?scp=85049568496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049568496&partnerID=8YFLogxK

U2 - 10.1117/12.2293554

DO - 10.1117/12.2293554

M3 - Conference contribution

C2 - 30197464

AN - SCOPUS:85049568496

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2018

A2 - Gimi, Barjor

A2 - Krol, Andrzej

PB - SPIE

T2 - Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging

Y2 - 11 February 2018 through 13 February 2018

ER -

Heart chamber segmentation from CT using convolutional neural networks

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this