A framework for shape matching in deformable image registration

Karsten Østergaard Noe; Jesper Mosegaard; Kari Tanderup; Thomas Sangild Sørensen

A framework for shape matching in deformable image registration

Karsten Østergaard Noe, Jesper Mosegaard, Kari Tanderup, Thomas Sangild Sørensen

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Conference article › Research › peer-review

Abstract

Many existing image registration methods have difficulties in accurately describing significant rotation and bending of entities (e.g. organs) between two datasets. A common problem in this case is to ensure that the resulting registration is physically plausible, i.e. that the registration describes the actual bending/rotation occurring rather than just introducing expansion in some areas and shrinkage in others. In this work we developed a general framework for deformable image registration of two 3D datasets that alleviates this problem. To ensure that only physically feasible and plausible solutions to the registration problem are found, a soft tissue deformable model is used to constrain the search space for the desired correspondence map while minimizing a similarity metric between the source and reference datasets. Results from a deformable phantom experiment were used to verify and evaluate the framework.

Original language	English
Book series	Studies in Health Technology and Informatics
Volume	132
Pages (from-to)	333-337
Number of pages	5
ISSN	0926-9630
Publication status	Published - 2008
Event	16th Medicine Meets Virtual Reality - Long Beach, United States Duration: 29 Jan 2008 → 1 Feb 2008 Conference number: 16

Conference

Conference	16th Medicine Meets Virtual Reality
Number	16
Country/Territory	United States
City	Long Beach
Period	29/01/2008 → 01/02/2008

Cite this

@inproceedings{06a2abf0105d11ddb919000ea68e967b,

title = "A framework for shape matching in deformable image registration",

abstract = "Many existing image registration methods have difficulties in accurately describing significant rotation and bending of entities (e.g. organs) between two datasets. A common problem in this case is to ensure that the resulting registration is physically plausible, i.e. that the registration describes the actual bending/rotation occurring rather than just introducing expansion in some areas and shrinkage in others. In this work we developed a general framework for deformable image registration of two 3D datasets that alleviates this problem. To ensure that only physically feasible and plausible solutions to the registration problem are found, a soft tissue deformable model is used to constrain the search space for the desired correspondence map while minimizing a similarity metric between the source and reference datasets. Results from a deformable phantom experiment were used to verify and evaluate the framework.",

author = "Noe, {Karsten {\O}stergaard} and Jesper Mosegaard and Kari Tanderup and S{\o}rensen, {Thomas Sangild}",

note = "978-1-58603-822-9 Serie: Studies in health technology and informatics, IOS Press, 132, 0926-9630 Volumne: 132; 16th Medicine Meets Virtual Reality ; Conference date: 29-01-2008 Through 01-02-2008",

year = "2008",

language = "English",

volume = "132",

pages = "333--337",

journal = "Studies in Health Technology and Informatics",

issn = "0926-9630",

publisher = "I O S Press",

}

TY - GEN

T1 - A framework for shape matching in deformable image registration

AU - Noe, Karsten Østergaard

AU - Mosegaard, Jesper

AU - Tanderup, Kari

AU - Sørensen, Thomas Sangild

N1 - Conference code: 16

PY - 2008

Y1 - 2008

N2 - Many existing image registration methods have difficulties in accurately describing significant rotation and bending of entities (e.g. organs) between two datasets. A common problem in this case is to ensure that the resulting registration is physically plausible, i.e. that the registration describes the actual bending/rotation occurring rather than just introducing expansion in some areas and shrinkage in others. In this work we developed a general framework for deformable image registration of two 3D datasets that alleviates this problem. To ensure that only physically feasible and plausible solutions to the registration problem are found, a soft tissue deformable model is used to constrain the search space for the desired correspondence map while minimizing a similarity metric between the source and reference datasets. Results from a deformable phantom experiment were used to verify and evaluate the framework.

AB - Many existing image registration methods have difficulties in accurately describing significant rotation and bending of entities (e.g. organs) between two datasets. A common problem in this case is to ensure that the resulting registration is physically plausible, i.e. that the registration describes the actual bending/rotation occurring rather than just introducing expansion in some areas and shrinkage in others. In this work we developed a general framework for deformable image registration of two 3D datasets that alleviates this problem. To ensure that only physically feasible and plausible solutions to the registration problem are found, a soft tissue deformable model is used to constrain the search space for the desired correspondence map while minimizing a similarity metric between the source and reference datasets. Results from a deformable phantom experiment were used to verify and evaluate the framework.

M3 - Conference article

SN - 0926-9630

VL - 132

SP - 333

EP - 337

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

T2 - 16th Medicine Meets Virtual Reality

Y2 - 29 January 2008 through 1 February 2008

ER -

A framework for shape matching in deformable image registration

Abstract

Conference

Fingerprint

Cite this