Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images

Juha Koikkalainen; Mika Pollari; Jyrki Lötjönen; Sari Kivistö; Kirsi Lauerma

doi:10.1007/978-3-540-30135-6_52

Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images

Juha Koikkalainen, Mika Pollari, Jyrki Lötjönen, Sari Kivistö, Kirsi Lauerma

VTT Technical Research Centre of Finland

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

7 Citations (Scopus)

Abstract

We introduce a framework for the automatic segmentation of the ventricles, atria, and epicardium simultaneously from cardiac magnetic resonance (MR) volumes. The basic idea is to utilize both shortaxis (SA) and long-axis (LA) MR volumes. Consequently, anatomical information is available from the whole heart volume. In this paper, the framework is used with deformable model based registration and segmentation methods to segment the cardiac structures. A database consisting of the cardiac MR volumes of 25 healthy subjects is used to validate the methods. The results presented in this paper prove that by using both the SA and LA MR volumes the ventricles and atria can be simultaneously segmented from cardiac MR volumes with a good accuracy. The results show that notably better segmentation results are obtained when the LA volumes are used in addition to the SA volumes. For example, this enables accurate segmentation of the ventricles also in the basal and apical levels.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention - MICCAI 2004
Editors	Christian Barillot, David R. Haynor, Pierre Hellier
Place of Publication	Heidelberg
Publisher	Springer
Pages	427-434
Volume	1
ISBN (Electronic)	978-3-540-30135-6
ISBN (Print)	978-3-540-22976-6
DOIs	https://doi.org/10.1007/978-3-540-30135-6_52
Publication status	Published - 2004
MoE publication type	A4 Article in a conference publication
Event	7th International Conference MICCAI 2004 - Saint-Malo, France Duration: 26 Sept 2004 → 29 Sept 2004

Publication series

Series	Lecture Notes in Computer Science
Volume	3216
ISSN	0302-9743

Conference

Conference	7th International Conference MICCAI 2004
Country/Territory	France
City	Saint-Malo
Period	26/09/04 → 29/09/04

Keywords

segmentation
deformable models
cardiac

Access to Document

10.1007/978-3-540-30135-6_52

Cite this

Koikkalainen, J., Pollari, M., Lötjönen, J., Kivistö, S., & Lauerma, K. (2004). Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images. In C. Barillot, D. R. Haynor, & P. Hellier (Eds.), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2004 (Vol. 1, pp. 427-434). Springer. https://doi.org/10.1007/978-3-540-30135-6_52

Koikkalainen, Juha ; Pollari, Mika ; Lötjönen, Jyrki et al. / Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images. Medical Image Computing and Computer-Assisted Intervention - MICCAI 2004. editor / Christian Barillot ; David R. Haynor ; Pierre Hellier. Vol. 1 Heidelberg : Springer, 2004. pp. 427-434 (Lecture Notes in Computer Science, Vol. 3216).

@inproceedings{063d623ad73c4f988c5d5193e3fdb76b,

title = "Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images",

abstract = "We introduce a framework for the automatic segmentation of the ventricles, atria, and epicardium simultaneously from cardiac magnetic resonance (MR) volumes. The basic idea is to utilize both shortaxis (SA) and long-axis (LA) MR volumes. Consequently, anatomical information is available from the whole heart volume. In this paper, the framework is used with deformable model based registration and segmentation methods to segment the cardiac structures. A database consisting of the cardiac MR volumes of 25 healthy subjects is used to validate the methods. The results presented in this paper prove that by using both the SA and LA MR volumes the ventricles and atria can be simultaneously segmented from cardiac MR volumes with a good accuracy. The results show that notably better segmentation results are obtained when the LA volumes are used in addition to the SA volumes. For example, this enables accurate segmentation of the ventricles also in the basal and apical levels.",

keywords = "segmentation, deformable models, cardiac",

author = "Juha Koikkalainen and Mika Pollari and Jyrki L{\"o}tj{\"o}nen and Sari Kivist{\"o} and Kirsi Lauerma",

note = "Project code: T3SU00308; 7th International Conference MICCAI 2004 ; Conference date: 26-09-2004 Through 29-09-2004",

year = "2004",

doi = "10.1007/978-3-540-30135-6_52",

language = "English",

isbn = "978-3-540-22976-6",

volume = "1",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "427--434",

editor = "Christian Barillot and Haynor, {David R.} and Pierre Hellier",

booktitle = "Medical Image Computing and Computer-Assisted Intervention - MICCAI 2004",

address = "Germany",

}

Koikkalainen, J, Pollari, M, Lötjönen, J, Kivistö, S & Lauerma, K 2004, Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images. in C Barillot, DR Haynor & P Hellier (eds), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2004. vol. 1, Springer, Heidelberg, Lecture Notes in Computer Science, vol. 3216, pp. 427-434, 7th International Conference MICCAI 2004, Saint-Malo, France, 26/09/04. https://doi.org/10.1007/978-3-540-30135-6_52

Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images. / Koikkalainen, Juha; Pollari, Mika; Lötjönen, Jyrki et al.
Medical Image Computing and Computer-Assisted Intervention - MICCAI 2004. ed. / Christian Barillot; David R. Haynor; Pierre Hellier. Vol. 1 Heidelberg: Springer, 2004. p. 427-434 (Lecture Notes in Computer Science, Vol. 3216).

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

TY - GEN

T1 - Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images

AU - Koikkalainen, Juha

AU - Pollari, Mika

AU - Lötjönen, Jyrki

AU - Kivistö, Sari

AU - Lauerma, Kirsi

N1 - Project code: T3SU00308

PY - 2004

Y1 - 2004

N2 - We introduce a framework for the automatic segmentation of the ventricles, atria, and epicardium simultaneously from cardiac magnetic resonance (MR) volumes. The basic idea is to utilize both shortaxis (SA) and long-axis (LA) MR volumes. Consequently, anatomical information is available from the whole heart volume. In this paper, the framework is used with deformable model based registration and segmentation methods to segment the cardiac structures. A database consisting of the cardiac MR volumes of 25 healthy subjects is used to validate the methods. The results presented in this paper prove that by using both the SA and LA MR volumes the ventricles and atria can be simultaneously segmented from cardiac MR volumes with a good accuracy. The results show that notably better segmentation results are obtained when the LA volumes are used in addition to the SA volumes. For example, this enables accurate segmentation of the ventricles also in the basal and apical levels.

AB - We introduce a framework for the automatic segmentation of the ventricles, atria, and epicardium simultaneously from cardiac magnetic resonance (MR) volumes. The basic idea is to utilize both shortaxis (SA) and long-axis (LA) MR volumes. Consequently, anatomical information is available from the whole heart volume. In this paper, the framework is used with deformable model based registration and segmentation methods to segment the cardiac structures. A database consisting of the cardiac MR volumes of 25 healthy subjects is used to validate the methods. The results presented in this paper prove that by using both the SA and LA MR volumes the ventricles and atria can be simultaneously segmented from cardiac MR volumes with a good accuracy. The results show that notably better segmentation results are obtained when the LA volumes are used in addition to the SA volumes. For example, this enables accurate segmentation of the ventricles also in the basal and apical levels.

KW - segmentation

KW - deformable models

KW - cardiac

U2 - 10.1007/978-3-540-30135-6_52

DO - 10.1007/978-3-540-30135-6_52

M3 - Conference article in proceedings

SN - 978-3-540-22976-6

VL - 1

T3 - Lecture Notes in Computer Science

SP - 427

EP - 434

BT - Medical Image Computing and Computer-Assisted Intervention - MICCAI 2004

A2 - Barillot, Christian

A2 - Haynor, David R.

A2 - Hellier, Pierre

PB - Springer

CY - Heidelberg

T2 - 7th International Conference MICCAI 2004

Y2 - 26 September 2004 through 29 September 2004

ER -

Koikkalainen J, Pollari M, Lötjönen J, Kivistö S, Lauerma K. Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images. In Barillot C, Haynor DR, Hellier P, editors, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2004. Vol. 1. Heidelberg: Springer. 2004. p. 427-434. (Lecture Notes in Computer Science, Vol. 3216). doi: 10.1007/978-3-540-30135-6_52

Segmentation of Cardiac Structures Simultaneously from Short- and Long-axis MR Images

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this