Carotid artery wall segmentation by coupled surface graph cuts

Andres Arias; Jens Petersen; Arna van Engelen; Hui Tang; Mariana Selwaness; Jacqueline C. M. Witteman; Aad van der Lugt; Wiro Niessen; Marleen de Bruijne

doi:10.1007/978-3-642-36620-8_5

Carotid artery wall segmentation by coupled surface graph cuts

Andres Arias, Jens Petersen, Arna van Engelen, Hui Tang, Mariana Selwaness, Jacqueline C. M. Witteman, Aad van der Lugt, Wiro Niessen, Marleen de Bruijne

Department of Computer Science

7 Citations (Scopus)

814 Downloads (Pure)

Abstract

We present a three-dimensional coupled surface graph cut algorithm for carotid wall segmentation from Magnetic Resonance Imaging (MRI). Using cost functions that highlight both inner and outer vessel wall borders, the method combines the search for both borders into a single graph cut optimization. Our approach requires little user interaction and can robustly segment the carotid artery bifurcation. Experiments on 32 carotid arteries from 16 patients show good agreement between manual segmentation performed by an expert and our method. The mean relative area of overlap is more than 85% for both lumen and outer vessel wall. In addition, differences in measured wall thickness with respect to the manual annotations were smaller than the in-plane pixel size.

Original language	English
Title of host publication	Medical Computer Vision. Recognition techniques and applications in medical imaging : Second International MICCAI Workshop, MCV 2012, Nice, France, Revised Selected Papers
Editors	Bjoern H. Menze, Georg Langs, Le Lu, Albert Montillo, Zhuowen Tu, Antonio Criminisi
Number of pages	10
Publisher	Springer
Publication date	2013
Pages	38-47
ISBN (Print)	978-3-642-36619-2
ISBN (Electronic)	978-3-642-36620-8
DOIs	https://doi.org/10.1007/978-3-642-36620-8_5
Publication status	Published - 2013
Event	Second International MICCAI Workshop on Medical Computer Vision: Recognition techniques and applications in medical imaging - Nice, France Duration: 5 Oct 2012 → 5 Oct 2012 Conference number: 2

Conference

Conference	Second International MICCAI Workshop on Medical Computer Vision
Number	2
Country/Territory	France
City	Nice
Period	05/10/2012 → 05/10/2012

Series	Lecture notes in computer science
Volume	7766
ISSN	0302-9743

Access to Document

10.1007/978-3-642-36620-8_5

arias_miccai_workshop_2012Accepted author manuscript, 1.01 MB

Cite this

Arias, A., Petersen, J., van Engelen, A., Tang, H., Selwaness, M., Witteman, J. C. M., van der Lugt, A., Niessen, W., & de Bruijne, M. (2013). Carotid artery wall segmentation by coupled surface graph cuts. In B. H. Menze, G. Langs, L. Lu, A. Montillo, Z. Tu, & A. Criminisi (Eds.), Medical Computer Vision. Recognition techniques and applications in medical imaging: Second International MICCAI Workshop, MCV 2012, Nice, France, Revised Selected Papers (pp. 38-47). Springer. Lecture notes in computer science Vol. 7766 https://doi.org/10.1007/978-3-642-36620-8_5

Carotid artery wall segmentation by coupled surface graph cuts. / Arias, Andres; Petersen, Jens; van Engelen, Arna et al.

Medical Computer Vision. Recognition techniques and applications in medical imaging: Second International MICCAI Workshop, MCV 2012, Nice, France, Revised Selected Papers. ed. / Bjoern H. Menze; Georg Langs; Le Lu; Albert Montillo; Zhuowen Tu; Antonio Criminisi. Springer, 2013. p. 38-47 (Lecture notes in computer science, Vol. 7766).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Arias, A, Petersen, J, van Engelen, A, Tang, H, Selwaness, M, Witteman, JCM, van der Lugt, A, Niessen, W & de Bruijne, M 2013, Carotid artery wall segmentation by coupled surface graph cuts. in BH Menze, G Langs, L Lu, A Montillo, Z Tu & A Criminisi (eds), Medical Computer Vision. Recognition techniques and applications in medical imaging: Second International MICCAI Workshop, MCV 2012, Nice, France, Revised Selected Papers. Springer, Lecture notes in computer science, vol. 7766, pp. 38-47, Second International MICCAI Workshop on Medical Computer Vision, Nice, France, 05/10/2012. https://doi.org/10.1007/978-3-642-36620-8_5

Arias A, Petersen J, van Engelen A, Tang H, Selwaness M, Witteman JCM et al. Carotid artery wall segmentation by coupled surface graph cuts. In Menze BH, Langs G, Lu L, Montillo A, Tu Z, Criminisi A, editors, Medical Computer Vision. Recognition techniques and applications in medical imaging: Second International MICCAI Workshop, MCV 2012, Nice, France, Revised Selected Papers. Springer. 2013. p. 38-47. (Lecture notes in computer science, Vol. 7766). doi: 10.1007/978-3-642-36620-8_5

Arias, Andres ; Petersen, Jens ; van Engelen, Arna et al. / Carotid artery wall segmentation by coupled surface graph cuts. Medical Computer Vision. Recognition techniques and applications in medical imaging: Second International MICCAI Workshop, MCV 2012, Nice, France, Revised Selected Papers. editor / Bjoern H. Menze ; Georg Langs ; Le Lu ; Albert Montillo ; Zhuowen Tu ; Antonio Criminisi. Springer, 2013. pp. 38-47 (Lecture notes in computer science, Vol. 7766).

@inproceedings{ec32a5626fff49ec9799050bd6ba68ff,

title = "Carotid artery wall segmentation by coupled surface graph cuts",

abstract = "We present a three-dimensional coupled surface graph cut algorithm for carotid wall segmentation from Magnetic Resonance Imaging (MRI). Using cost functions that highlight both inner and outer vessel wall borders, the method combines the search for both borders into a single graph cut optimization. Our approach requires little user interaction and can robustly segment the carotid artery bifurcation. Experiments on 32 carotid arteries from 16 patients show good agreement between manual segmentation performed by an expert and our method. The mean relative area of overlap is more than 85% for both lumen and outer vessel wall. In addition, differences in measured wall thickness with respect to the manual annotations were smaller than the in-plane pixel size.",

author = "Andres Arias and Jens Petersen and {van Engelen}, Arna and Hui Tang and Mariana Selwaness and Witteman, {Jacqueline C. M.} and {van der Lugt}, Aad and Wiro Niessen and {de Bruijne}, Marleen",

year = "2013",

doi = "10.1007/978-3-642-36620-8_5",

language = "English",

isbn = "978-3-642-36619-2",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "38--47",

editor = "Menze, {Bjoern H. } and Langs, {Georg } and Lu, {Le } and Montillo, {Albert } and Tu, {Zhuowen } and Criminisi, {Antonio }",

booktitle = "Medical Computer Vision. Recognition techniques and applications in medical imaging",

note = "Second International MICCAI Workshop on Medical Computer Vision : Recognition techniques and applications in medical imaging, MCV 2012 ; Conference date: 05-10-2012 Through 05-10-2012",

}

TY - GEN

T1 - Carotid artery wall segmentation by coupled surface graph cuts

AU - Arias, Andres

AU - Petersen, Jens

AU - van Engelen, Arna

AU - Tang, Hui

AU - Selwaness, Mariana

AU - Witteman, Jacqueline C. M.

AU - van der Lugt, Aad

AU - Niessen, Wiro

AU - de Bruijne, Marleen

N1 - Conference code: 2

PY - 2013

Y1 - 2013

N2 - We present a three-dimensional coupled surface graph cut algorithm for carotid wall segmentation from Magnetic Resonance Imaging (MRI). Using cost functions that highlight both inner and outer vessel wall borders, the method combines the search for both borders into a single graph cut optimization. Our approach requires little user interaction and can robustly segment the carotid artery bifurcation. Experiments on 32 carotid arteries from 16 patients show good agreement between manual segmentation performed by an expert and our method. The mean relative area of overlap is more than 85% for both lumen and outer vessel wall. In addition, differences in measured wall thickness with respect to the manual annotations were smaller than the in-plane pixel size.

AB - We present a three-dimensional coupled surface graph cut algorithm for carotid wall segmentation from Magnetic Resonance Imaging (MRI). Using cost functions that highlight both inner and outer vessel wall borders, the method combines the search for both borders into a single graph cut optimization. Our approach requires little user interaction and can robustly segment the carotid artery bifurcation. Experiments on 32 carotid arteries from 16 patients show good agreement between manual segmentation performed by an expert and our method. The mean relative area of overlap is more than 85% for both lumen and outer vessel wall. In addition, differences in measured wall thickness with respect to the manual annotations were smaller than the in-plane pixel size.

U2 - 10.1007/978-3-642-36620-8_5

DO - 10.1007/978-3-642-36620-8_5

M3 - Article in proceedings

SN - 978-3-642-36619-2

T3 - Lecture notes in computer science

SP - 38

EP - 47

BT - Medical Computer Vision. Recognition techniques and applications in medical imaging

A2 - Menze, Bjoern H.

A2 - Langs, Georg

A2 - Lu, Le

A2 - Montillo, Albert

A2 - Tu, Zhuowen

A2 - Criminisi, Antonio

PB - Springer

T2 - Second International MICCAI Workshop on Medical Computer Vision

Y2 - 5 October 2012 through 5 October 2012

ER -

Carotid artery wall segmentation by coupled surface graph cuts

Abstract

Conference

Access to Document

Fingerprint

Cite this