Affine invariant surface evolutions for 3D image segmentation

Yogesh Rathi; Peter Olver; Guillermo Sapiro; Allen Tannenbaum

doi:10.1117/12.640282

Affine invariant surface evolutions for 3D image segmentation

Yogesh Rathi, Peter Olver, Guillermo Sapiro, Allen Tannenbaum

Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

In this paper we present an algorithm for 3D medical image segmentation based on an affine invariant flow. The algorithm is simple to implement and semi-automatic. The technique is based on active contours evolving in time according to intrinsic geometric measures of the image. The surface flow is obtained by minimizing a global energy with respect to an affine invariant metric. Affine invariant edge detectors for 3-dimensional objects are also computed which have the same qualitative behavior as the Euclidean edge detectors. Results on artificial and real MRI images show that the algorithm performs well, both in terms of accuracy and robustness to noise.

Original language	English (US)
Title of host publication	Image Processing
Subtitle of host publication	Algorithms and Systems, Neural Networks, and Machine Learning - Proceedings of SPIE-IS and T Electronic Imaging
DOIs	https://doi.org/10.1117/12.640282
State	Published - 2006
Event	Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning - San Jose, CA, United States Duration: Jan 16 2006 → Jan 18 2006

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	6064
ISSN (Print)	0277-786X

Conference

Conference	Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning
Country/Territory	United States
City	San Jose, CA
Period	1/16/06 → 1/18/06

Keywords

3D Surface Evolution
Geometric Active Contours
Level Sets
Segmentation

Access

10.1117/12.640282

OpenUrl availability

Full text

Cite this

Rathi, Y., Olver, P., Sapiro, G., & Tannenbaum, A. (2006). Affine invariant surface evolutions for 3D image segmentation. In Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning - Proceedings of SPIE-IS and T Electronic Imaging Article 606401 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6064). https://doi.org/10.1117/12.640282

Affine invariant surface evolutions for 3D image segmentation. / Rathi, Yogesh; Olver, Peter; Sapiro, Guillermo et al.
Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning - Proceedings of SPIE-IS and T Electronic Imaging. 2006. 606401 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6064).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Rathi, Y, Olver, P, Sapiro, G & Tannenbaum, A 2006, Affine invariant surface evolutions for 3D image segmentation. in Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning - Proceedings of SPIE-IS and T Electronic Imaging., 606401, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6064, Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning, San Jose, CA, United States, 1/16/06. https://doi.org/10.1117/12.640282

@inproceedings{e6bca41131e2454a8cf4a025a3c2cfa2,

title = "Affine invariant surface evolutions for 3D image segmentation",

abstract = "In this paper we present an algorithm for 3D medical image segmentation based on an affine invariant flow. The algorithm is simple to implement and semi-automatic. The technique is based on active contours evolving in time according to intrinsic geometric measures of the image. The surface flow is obtained by minimizing a global energy with respect to an affine invariant metric. Affine invariant edge detectors for 3-dimensional objects are also computed which have the same qualitative behavior as the Euclidean edge detectors. Results on artificial and real MRI images show that the algorithm performs well, both in terms of accuracy and robustness to noise.",

keywords = "3D Surface Evolution, Geometric Active Contours, Level Sets, Segmentation",

author = "Yogesh Rathi and Peter Olver and Guillermo Sapiro and Allen Tannenbaum",

note = "Copyright: Copyright 2011 Elsevier B.V., All rights reserved.; Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning ; Conference date: 16-01-2006 Through 18-01-2006",

year = "2006",

doi = "10.1117/12.640282",

language = "English (US)",

isbn = "0819461040",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "Image Processing",

}

TY - GEN

T1 - Affine invariant surface evolutions for 3D image segmentation

AU - Rathi, Yogesh

AU - Olver, Peter

AU - Sapiro, Guillermo

AU - Tannenbaum, Allen

PY - 2006

Y1 - 2006

N2 - In this paper we present an algorithm for 3D medical image segmentation based on an affine invariant flow. The algorithm is simple to implement and semi-automatic. The technique is based on active contours evolving in time according to intrinsic geometric measures of the image. The surface flow is obtained by minimizing a global energy with respect to an affine invariant metric. Affine invariant edge detectors for 3-dimensional objects are also computed which have the same qualitative behavior as the Euclidean edge detectors. Results on artificial and real MRI images show that the algorithm performs well, both in terms of accuracy and robustness to noise.

AB - In this paper we present an algorithm for 3D medical image segmentation based on an affine invariant flow. The algorithm is simple to implement and semi-automatic. The technique is based on active contours evolving in time according to intrinsic geometric measures of the image. The surface flow is obtained by minimizing a global energy with respect to an affine invariant metric. Affine invariant edge detectors for 3-dimensional objects are also computed which have the same qualitative behavior as the Euclidean edge detectors. Results on artificial and real MRI images show that the algorithm performs well, both in terms of accuracy and robustness to noise.

KW - 3D Surface Evolution

KW - Geometric Active Contours

KW - Level Sets

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=33645697722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645697722&partnerID=8YFLogxK

U2 - 10.1117/12.640282

DO - 10.1117/12.640282

M3 - Conference contribution

AN - SCOPUS:33645697722

SN - 0819461040

SN - 9780819461049

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Image Processing

T2 - Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning

Y2 - 16 January 2006 through 18 January 2006

ER -

Affine invariant surface evolutions for 3D image segmentation

Abstract

Publication series

Conference

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this