High dimensional statistical shape model for medical image analysis

Heng Huang, Fillia Makedon, Roderick McColl

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Statistical shape models have been widely used in biomedical image analysis, e.g. segmentation, registration, and shape classification. The traditional statistical shape models forced all shape parameters of each shape into one vector and put all vectors together to generate the point distribution model (PDM). The standard principal component analysis (PCA) was employed to project all shapes onto subspaces for dimensionality reduction. Since the shape vectors have a large dimension, the previous methods is computational expensive. In this paper, we propose a novel statistical shape models using natural PDM representations by multiple matrices and two dimensional PCA (2DPCA) is used to reduce the dimensionality of shape parameters. Because 2DPCA considers the correlations of row by row and column by column, our technique can fast extract the principle shape parameters. Combining with spherical harmonics shape representation, we create a framework for biomedical anatomic structures' shape analysis and classification. The experimental results using real cardiac left ventricle shapes have demonstrated our method outperforms the previous statistical shape modeling.

Original languageEnglish (US)
Title of host publication2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI
Pages1541-1544
Number of pages4
DOIs
StatePublished - 2008
Event2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI - Paris, France
Duration: May 14 2008May 17 2008

Other

Other2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI
CountryFrance
CityParis
Period5/14/085/17/08

Fingerprint

Image analysis
Principal component analysis
Computational methods

Keywords

  • 2DPCA
  • Cardiac shape classification
  • PCA
  • Shape classification
  • Statistical shape modeling

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Huang, H., Makedon, F., & McColl, R. (2008). High dimensional statistical shape model for medical image analysis. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI (pp. 1541-1544). [4541303] https://doi.org/10.1109/ISBI.2008.4541303

High dimensional statistical shape model for medical image analysis. / Huang, Heng; Makedon, Fillia; McColl, Roderick.

2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 1541-1544 4541303.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Huang, H, Makedon, F & McColl, R 2008, High dimensional statistical shape model for medical image analysis. in 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI., 4541303, pp. 1541-1544, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI, Paris, France, 5/14/08. https://doi.org/10.1109/ISBI.2008.4541303
Huang H, Makedon F, McColl R. High dimensional statistical shape model for medical image analysis. In 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. p. 1541-1544. 4541303 https://doi.org/10.1109/ISBI.2008.4541303
Huang, Heng ; Makedon, Fillia ; McColl, Roderick. / High dimensional statistical shape model for medical image analysis. 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI. 2008. pp. 1541-1544
@inproceedings{0eb2a7e9d7314fdd92016638e086ef67,
title = "High dimensional statistical shape model for medical image analysis",
abstract = "Statistical shape models have been widely used in biomedical image analysis, e.g. segmentation, registration, and shape classification. The traditional statistical shape models forced all shape parameters of each shape into one vector and put all vectors together to generate the point distribution model (PDM). The standard principal component analysis (PCA) was employed to project all shapes onto subspaces for dimensionality reduction. Since the shape vectors have a large dimension, the previous methods is computational expensive. In this paper, we propose a novel statistical shape models using natural PDM representations by multiple matrices and two dimensional PCA (2DPCA) is used to reduce the dimensionality of shape parameters. Because 2DPCA considers the correlations of row by row and column by column, our technique can fast extract the principle shape parameters. Combining with spherical harmonics shape representation, we create a framework for biomedical anatomic structures' shape analysis and classification. The experimental results using real cardiac left ventricle shapes have demonstrated our method outperforms the previous statistical shape modeling.",
keywords = "2DPCA, Cardiac shape classification, PCA, Shape classification, Statistical shape modeling",
author = "Heng Huang and Fillia Makedon and Roderick McColl",
year = "2008",
doi = "10.1109/ISBI.2008.4541303",
language = "English (US)",
isbn = "9781424420032",
pages = "1541--1544",
booktitle = "2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI",

}

TY - GEN

T1 - High dimensional statistical shape model for medical image analysis

AU - Huang, Heng

AU - Makedon, Fillia

AU - McColl, Roderick

PY - 2008

Y1 - 2008

N2 - Statistical shape models have been widely used in biomedical image analysis, e.g. segmentation, registration, and shape classification. The traditional statistical shape models forced all shape parameters of each shape into one vector and put all vectors together to generate the point distribution model (PDM). The standard principal component analysis (PCA) was employed to project all shapes onto subspaces for dimensionality reduction. Since the shape vectors have a large dimension, the previous methods is computational expensive. In this paper, we propose a novel statistical shape models using natural PDM representations by multiple matrices and two dimensional PCA (2DPCA) is used to reduce the dimensionality of shape parameters. Because 2DPCA considers the correlations of row by row and column by column, our technique can fast extract the principle shape parameters. Combining with spherical harmonics shape representation, we create a framework for biomedical anatomic structures' shape analysis and classification. The experimental results using real cardiac left ventricle shapes have demonstrated our method outperforms the previous statistical shape modeling.

AB - Statistical shape models have been widely used in biomedical image analysis, e.g. segmentation, registration, and shape classification. The traditional statistical shape models forced all shape parameters of each shape into one vector and put all vectors together to generate the point distribution model (PDM). The standard principal component analysis (PCA) was employed to project all shapes onto subspaces for dimensionality reduction. Since the shape vectors have a large dimension, the previous methods is computational expensive. In this paper, we propose a novel statistical shape models using natural PDM representations by multiple matrices and two dimensional PCA (2DPCA) is used to reduce the dimensionality of shape parameters. Because 2DPCA considers the correlations of row by row and column by column, our technique can fast extract the principle shape parameters. Combining with spherical harmonics shape representation, we create a framework for biomedical anatomic structures' shape analysis and classification. The experimental results using real cardiac left ventricle shapes have demonstrated our method outperforms the previous statistical shape modeling.

KW - 2DPCA

KW - Cardiac shape classification

KW - PCA

KW - Shape classification

KW - Statistical shape modeling

UR - http://www.scopus.com/inward/record.url?scp=51049089934&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51049089934&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2008.4541303

DO - 10.1109/ISBI.2008.4541303

M3 - Conference contribution

SN - 9781424420032

SP - 1541

EP - 1544

BT - 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Proceedings, ISBI

ER -