Left-ventricular epi- and endocardium extraction from 3D ultrasound images using an automatically constructed 3D ASM

C. Butakoff; S. Balocco; F. M. Sukno; C. Hoogendoorn; C. Tobon-Gomez; G. Avegliano; A. F. Frangi

doi:10.1080/21681163.2014.910703

Left-ventricular epi- and endocardium extraction from 3D ultrasound images using an automatically constructed 3D ASM

C. Butakoff^*, S. Balocco, F. M. Sukno, C. Hoogendoorn, C. Tobon-Gomez, G. Avegliano, A. F. Frangi

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, we propose an automatic method for constructing an active shape model (ASM) to segment the complete cardiac left ventricle in 3D ultrasound (3DUS) images, which avoids costly manual landmarking. The automatic construction of the ASM has already been addressed in the literature; however, the direct application of these methods to 3DUS is hampered by a high level of noise and artefacts. Therefore, we propose to construct the ASM by fusing the multidetector computed tomography data, to learn the shape, with the artificially generated 3DUS, in order to learn the neighbourhood of the boundaries. Our artificial images were generated by two approaches: a faster one that does not take into account the geometry of the transducer, and a more comprehensive one, implemented in Field II toolbox. The segmentation accuracy of our ASM was evaluated on 20 patients with left-ventricular asynchrony, demonstrating plausibility of the approach.

Original language	English
Pages (from-to)	265-280
Number of pages	16
Journal	Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization
Volume	4
Issue number	5
DOIs	https://doi.org/10.1080/21681163.2014.910703
Publication status	Published - 29 Apr 2014

Keywords

3D ultrasound
ASM
cardiac segmentation
shape model
statistical model

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1080/21681163.2014.910703

Cite this

Butakoff, C., Balocco, S., Sukno, F. M., Hoogendoorn, C., Tobon-Gomez, C., Avegliano, G., & Frangi, A. F. (2014). Left-ventricular epi- and endocardium extraction from 3D ultrasound images using an automatically constructed 3D ASM. Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization, 4(5), 265-280. https://doi.org/10.1080/21681163.2014.910703

@article{edf7021456bf4fb2ab03f19b7c4a73c1,

title = "Left-ventricular epi- and endocardium extraction from 3D ultrasound images using an automatically constructed 3D ASM",

abstract = "In this paper, we propose an automatic method for constructing an active shape model (ASM) to segment the complete cardiac left ventricle in 3D ultrasound (3DUS) images, which avoids costly manual landmarking. The automatic construction of the ASM has already been addressed in the literature; however, the direct application of these methods to 3DUS is hampered by a high level of noise and artefacts. Therefore, we propose to construct the ASM by fusing the multidetector computed tomography data, to learn the shape, with the artificially generated 3DUS, in order to learn the neighbourhood of the boundaries. Our artificial images were generated by two approaches: a faster one that does not take into account the geometry of the transducer, and a more comprehensive one, implemented in Field II toolbox. The segmentation accuracy of our ASM was evaluated on 20 patients with left-ventricular asynchrony, demonstrating plausibility of the approach.",

keywords = "3D ultrasound, ASM, cardiac segmentation, shape model, statistical model",

author = "C. Butakoff and S. Balocco and Sukno, {F. M.} and C. Hoogendoorn and C. Tobon-Gomez and G. Avegliano and Frangi, {A. F.}",

note = "Publisher Copyright: {\textcopyright} 2014 Taylor & Francis.",

year = "2014",

month = apr,

day = "29",

doi = "10.1080/21681163.2014.910703",

language = "English",

volume = "4",

pages = "265--280",

journal = "Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization",

issn = "2168-1163",

publisher = "Taylor & Francis",

number = "5",

}

Butakoff, C, Balocco, S, Sukno, FM, Hoogendoorn, C, Tobon-Gomez, C, Avegliano, G & Frangi, AF 2014, 'Left-ventricular epi- and endocardium extraction from 3D ultrasound images using an automatically constructed 3D ASM', Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization, vol. 4, no. 5, pp. 265-280. https://doi.org/10.1080/21681163.2014.910703

TY - JOUR

T1 - Left-ventricular epi- and endocardium extraction from 3D ultrasound images using an automatically constructed 3D ASM

AU - Butakoff, C.

AU - Balocco, S.

AU - Sukno, F. M.

AU - Hoogendoorn, C.

AU - Tobon-Gomez, C.

AU - Avegliano, G.

AU - Frangi, A. F.

PY - 2014/4/29

Y1 - 2014/4/29

N2 - In this paper, we propose an automatic method for constructing an active shape model (ASM) to segment the complete cardiac left ventricle in 3D ultrasound (3DUS) images, which avoids costly manual landmarking. The automatic construction of the ASM has already been addressed in the literature; however, the direct application of these methods to 3DUS is hampered by a high level of noise and artefacts. Therefore, we propose to construct the ASM by fusing the multidetector computed tomography data, to learn the shape, with the artificially generated 3DUS, in order to learn the neighbourhood of the boundaries. Our artificial images were generated by two approaches: a faster one that does not take into account the geometry of the transducer, and a more comprehensive one, implemented in Field II toolbox. The segmentation accuracy of our ASM was evaluated on 20 patients with left-ventricular asynchrony, demonstrating plausibility of the approach.

AB - In this paper, we propose an automatic method for constructing an active shape model (ASM) to segment the complete cardiac left ventricle in 3D ultrasound (3DUS) images, which avoids costly manual landmarking. The automatic construction of the ASM has already been addressed in the literature; however, the direct application of these methods to 3DUS is hampered by a high level of noise and artefacts. Therefore, we propose to construct the ASM by fusing the multidetector computed tomography data, to learn the shape, with the artificially generated 3DUS, in order to learn the neighbourhood of the boundaries. Our artificial images were generated by two approaches: a faster one that does not take into account the geometry of the transducer, and a more comprehensive one, implemented in Field II toolbox. The segmentation accuracy of our ASM was evaluated on 20 patients with left-ventricular asynchrony, demonstrating plausibility of the approach.

KW - 3D ultrasound

KW - ASM

KW - cardiac segmentation

KW - shape model

KW - statistical model

UR - http://www.scopus.com/inward/record.url?scp=84981365821&partnerID=8YFLogxK

U2 - 10.1080/21681163.2014.910703

DO - 10.1080/21681163.2014.910703

M3 - Article

AN - SCOPUS:84981365821

SN - 2168-1163

VL - 4

SP - 265

EP - 280

JO - Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization

JF - Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization

IS - 5

ER -

Left-ventricular epi- and endocardium extraction from 3D ultrasound images using an automatically constructed 3D ASM

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this