Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images

Jyrki Lötjönen; S. Kivistö; J. Koikkalainen; D. Smutek; K. Lauerma

doi:10.1016/j.media.2004.06.013

Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images

Jyrki Lötjönen (Corresponding Author), S. Kivistö, J. Koikkalainen, D. Smutek, K. Lauerma

VTT Technical Research Centre of Finland

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

168 Citations (Scopus)

Abstract

We describe a new 3-D statistical shape model of the heart consisting of atria, ventricles and epicardium. The model was constructed by combining information on standard short- and long-axis cardiac MR images. In the model, the variability of the shape was modeled with PCA- and ICA-based shape models as well as with non-parametric landmark probability distributions and a probabilistic atlas. The statistical atlas was built from 25 healthy subjects. The shape model was evaluated by applying it to image segmentation. The probabilistic atlas was found to be superior to the other shape models (p<0.001) in this study.

Original language	English
Pages (from-to)	371-386
Journal	Medical Image Analysis
Volume	8
Issue number	3
DOIs	https://doi.org/10.1016/j.media.2004.06.013
Publication status	Published - 2004
MoE publication type	A1 Journal article-refereed

Keywords

shape analysis
statistical shape models
cardiac models
atlas
model-based image analysis

Access to Document

10.1016/j.media.2004.06.013

Cite this

@article{e5445ad0d323470090a9bddb8d276a54,

title = "Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images",

abstract = "We describe a new 3-D statistical shape model of the heart consisting of atria, ventricles and epicardium. The model was constructed by combining information on standard short- and long-axis cardiac MR images. In the model, the variability of the shape was modeled with PCA- and ICA-based shape models as well as with non-parametric landmark probability distributions and a probabilistic atlas. The statistical atlas was built from 25 healthy subjects. The shape model was evaluated by applying it to image segmentation. The probabilistic atlas was found to be superior to the other shape models (p<0.001) in this study.",

keywords = "shape analysis, statistical shape models, cardiac models, atlas, model-based image analysis",

author = "Jyrki L{\"o}tj{\"o}nen and S. Kivist{\"o} and J. Koikkalainen and D. Smutek and K. Lauerma",

year = "2004",

doi = "10.1016/j.media.2004.06.013",

language = "English",

volume = "8",

pages = "371--386",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier",

number = "3",

}

TY - JOUR

T1 - Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images

AU - Lötjönen, Jyrki

AU - Kivistö, S.

AU - Koikkalainen, J.

AU - Smutek, D.

AU - Lauerma, K.

PY - 2004

Y1 - 2004

N2 - We describe a new 3-D statistical shape model of the heart consisting of atria, ventricles and epicardium. The model was constructed by combining information on standard short- and long-axis cardiac MR images. In the model, the variability of the shape was modeled with PCA- and ICA-based shape models as well as with non-parametric landmark probability distributions and a probabilistic atlas. The statistical atlas was built from 25 healthy subjects. The shape model was evaluated by applying it to image segmentation. The probabilistic atlas was found to be superior to the other shape models (p<0.001) in this study.

AB - We describe a new 3-D statistical shape model of the heart consisting of atria, ventricles and epicardium. The model was constructed by combining information on standard short- and long-axis cardiac MR images. In the model, the variability of the shape was modeled with PCA- and ICA-based shape models as well as with non-parametric landmark probability distributions and a probabilistic atlas. The statistical atlas was built from 25 healthy subjects. The shape model was evaluated by applying it to image segmentation. The probabilistic atlas was found to be superior to the other shape models (p<0.001) in this study.

KW - shape analysis

KW - statistical shape models

KW - cardiac models

KW - atlas

KW - model-based image analysis

U2 - 10.1016/j.media.2004.06.013

DO - 10.1016/j.media.2004.06.013

M3 - Article

SN - 1361-8415

VL - 8

SP - 371

EP - 386

JO - Medical Image Analysis

JF - Medical Image Analysis

IS - 3

ER -

Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images

Abstract

Keywords

Access to Document

Fingerprint

Cite this