Deformable Density Matching for 3D Non rigid
Registration of Shapes 1st Edition by Arunabha S
Roy, Ajay Gopinath, Anand Rangarajan ISBN
9783540757573 pdf download
https://ebookball.com/product/deformable-density-matching-
for-3d-non-rigid-registration-of-shapes-1st-edition-by-arunabha-
s-roy-ajay-gopinath-anand-rangarajan-isbn-9783540757573-13520/
Explore and download more ebooks or textbooks
at ebookball.com
, Get Your Digital Files Instantly: PDF, ePub, MOBI and More
Quick Digital Downloads: PDF, ePub, MOBI and Other Formats
Generalized Surface Flows for Deformable Registration and Cortical
Matching 1st Edition by I Eckstein, A A Joshi, CJ Kuo, R Leahy, M
Desbrun ISBN 9783540757573
https://ebookball.com/product/generalized-surface-flows-for-
deformable-registration-and-cortical-matching-1st-edition-by-i-
eckstein-a-a-joshi-cj-kuo-r-leahy-m-desbrun-
isbn-9783540757573-9180/
Non rigid Surface Registration Using Spherical Thin Plate Splines 1st
Edition by Guangyu Zou, Jing Hua, Otto Muzik ISBN 9783540757573
https://ebookball.com/product/non-rigid-surface-registration-
using-spherical-thin-plate-splines-1st-edition-by-guangyu-zou-
jing-hua-otto-muzik-isbn-9783540757573-9696/
Numerical geometry of non rigid shapes 1st Edition by Alexander
Bronstein, Michael Bronstein, Ron Kimmel ISBN 9780387733012 038773301
https://ebookball.com/product/numerical-geometry-of-non-rigid-
shapes-1st-edition-by-alexander-bronstein-michael-bronstein-ron-
kimmel-isbn-9780387733012-0387733019-19890/
Thoracic CT PET Registration Using a 3D Breathing Model 1st Edition by
Antonio Moreno, Sylvie Chambon, Anand P Santhanam, Roberta Brocardo,
Patrick Kupelian, Jannick P Rolland, Elsa Angelini, Isabelle Bloch
ISBN 9783540757573
https://ebookball.com/product/thoracic-ct-pet-registration-
using-a-3d-breathing-model-1st-edition-by-antonio-moreno-sylvie-
chambon-anand-p-santhanam-roberta-brocardo-patrick-kupelian-
jannick-p-rolland-elsa-angelini-isabelle-bloch/
,3D 2D Image Registration The Impact of X Ray Views and Their Number
1st Edition by Dejan Tomazevic, Bostjan Likar, Franjo Pernus ISBN
9783540757573
https://ebookball.com/product/3d-2d-image-registration-the-
impact-of-x-ray-views-and-their-number-1st-edition-by-dejan-
tomazevic-bostjan-likar-franjo-pernus-isbn-9783540757573-11208/
Matching Tensors for Automatic Correspondence and Registration 1st
edition by Ajmal Mian, Mohammed Bennamoun, Robyn Owens ISBN 35402
9783540219835
https://ebookball.com/product/matching-tensors-for-automatic-
correspondence-and-registration-1st-edition-by-ajmal-mian-
mohammed-bennamoun-robyn-owens-
isbn-3540219835-9783540219835-14176/
Joint Bayes Filter A Hybrid Tracker for Non-rigid Hand Motion
Recognition 1st edition by Huang Fei, Ian Reid ISBN 3540219828
9783540219828
https://ebookball.com/product/joint-bayes-filter-a-hybrid-
tracker-for-non-rigid-hand-motion-recognition-1st-edition-by-
huang-fei-ian-reid-isbn-3540219828-9783540219828-9234/
Probabilistic Speckle Decorrelation for 3D Ultrasound 1st Edition by
Catherine Laporte, Tal Arbel ISBN 9783540757573
https://ebookball.com/product/probabilistic-speckle-
decorrelation-for-3d-ultrasound-1st-edition-by-catherine-laporte-
tal-arbel-isbn-9783540757573-12122/
Registration of High Angular Resolution Diffusion MRI Images Using 4th
Order Tensors 1st Edition by Angelos Barmpoutis, Baba C VemurI, John R
Forder ISBN 9783540757573
https://ebookball.com/product/registration-of-high-angular-
resolution-diffusion-mri-images-using-4th-order-tensors-1st-
edition-by-angelos-barmpoutis-baba-c-vemuri-john-r-forder-
isbn-9783540757573-13718/
, Deformable Density Matching for 3D Non-rigid
Registration of Shapes
Arunabha S. Roy1 , Ajay Gopinath1 , and Anand Rangarajan2,
1
Imaging Technologies Laboratory, GE Global Research Center, Bangalore, India
2
Department of CISE, University of Florida, Gainesville, FL, USA
Abstract. There exists a large body of literature on shape matching
and registration in medical image analysis. However, most of the previ-
ous work is focused on matching particular sets of features—point-sets,
lines, curves and surfaces. In this work, we forsake specific geometric
shape representations and instead seek probabilistic representations—
specifically Gaussian mixture models—of shapes. We evaluate a closed-
form distance between two probabilistic shape representations for the
general case where the mixture models differ in variance and the num-
ber of components. We then cast non-rigid registration as a deformable
density matching problem. In our approach, we take one mixture den-
sity onto another by deforming the component centroids via a thin-plate
spline (TPS) and also minimizing the distance with respect to the vari-
ance parameters. We validate our approach on synthetic and 3D arterial
tree data and evaluate it on 3D hippocampal shapes.
1 Introduction
The need for shape matching occurs in diverse sub-domains of medical image
analysis. Whenever a biomedical image is segmented or parsed into a set of
shapes, the need for shape analysis and comparison usually arises [1]. In brain
mapping for example [2], we frequently require the comparison of cortical and
subcortical structures such as the thalamus, putamen etc. extracted from subject
neuroanatomical MRI images. Image databases often use shape features and
here the need is to index and query the shape database. In MR angiography,
the complex network of blood vessels in the brain can be represented as trees or
graphs and need to be compared across subjects. And in cardiac applications, if
heart chamber information is available and extracted as a set of shapes, the wall
tracking problem requires us to solve for shape correspondences in the cardiac
cycle [3].
The need for shape matching is followed by a need for good shape repre-
sentations. When shape features are extracted from medical images, they can
be represented using an entire gamut of representations—points, line segments,
curves, surfaces, trees, graphs and hybrid representations. What should be noted
here is that an inferential stage is present in any shape representation. That is,
A.R. was partially supported by NSF IIS 0307712 and NIH RO1 NS046812.
N. Ayache, S. Ourselin, A. Maeder (Eds.): MICCAI 2007, Part I, LNCS 4791, pp. 942–949, 2007.
c Springer-Verlag Berlin Heidelberg 2007
Registration of Shapes 1st Edition by Arunabha S
Roy, Ajay Gopinath, Anand Rangarajan ISBN
9783540757573 pdf download
https://ebookball.com/product/deformable-density-matching-
for-3d-non-rigid-registration-of-shapes-1st-edition-by-arunabha-
s-roy-ajay-gopinath-anand-rangarajan-isbn-9783540757573-13520/
Explore and download more ebooks or textbooks
at ebookball.com
, Get Your Digital Files Instantly: PDF, ePub, MOBI and More
Quick Digital Downloads: PDF, ePub, MOBI and Other Formats
Generalized Surface Flows for Deformable Registration and Cortical
Matching 1st Edition by I Eckstein, A A Joshi, CJ Kuo, R Leahy, M
Desbrun ISBN 9783540757573
https://ebookball.com/product/generalized-surface-flows-for-
deformable-registration-and-cortical-matching-1st-edition-by-i-
eckstein-a-a-joshi-cj-kuo-r-leahy-m-desbrun-
isbn-9783540757573-9180/
Non rigid Surface Registration Using Spherical Thin Plate Splines 1st
Edition by Guangyu Zou, Jing Hua, Otto Muzik ISBN 9783540757573
https://ebookball.com/product/non-rigid-surface-registration-
using-spherical-thin-plate-splines-1st-edition-by-guangyu-zou-
jing-hua-otto-muzik-isbn-9783540757573-9696/
Numerical geometry of non rigid shapes 1st Edition by Alexander
Bronstein, Michael Bronstein, Ron Kimmel ISBN 9780387733012 038773301
https://ebookball.com/product/numerical-geometry-of-non-rigid-
shapes-1st-edition-by-alexander-bronstein-michael-bronstein-ron-
kimmel-isbn-9780387733012-0387733019-19890/
Thoracic CT PET Registration Using a 3D Breathing Model 1st Edition by
Antonio Moreno, Sylvie Chambon, Anand P Santhanam, Roberta Brocardo,
Patrick Kupelian, Jannick P Rolland, Elsa Angelini, Isabelle Bloch
ISBN 9783540757573
https://ebookball.com/product/thoracic-ct-pet-registration-
using-a-3d-breathing-model-1st-edition-by-antonio-moreno-sylvie-
chambon-anand-p-santhanam-roberta-brocardo-patrick-kupelian-
jannick-p-rolland-elsa-angelini-isabelle-bloch/
,3D 2D Image Registration The Impact of X Ray Views and Their Number
1st Edition by Dejan Tomazevic, Bostjan Likar, Franjo Pernus ISBN
9783540757573
https://ebookball.com/product/3d-2d-image-registration-the-
impact-of-x-ray-views-and-their-number-1st-edition-by-dejan-
tomazevic-bostjan-likar-franjo-pernus-isbn-9783540757573-11208/
Matching Tensors for Automatic Correspondence and Registration 1st
edition by Ajmal Mian, Mohammed Bennamoun, Robyn Owens ISBN 35402
9783540219835
https://ebookball.com/product/matching-tensors-for-automatic-
correspondence-and-registration-1st-edition-by-ajmal-mian-
mohammed-bennamoun-robyn-owens-
isbn-3540219835-9783540219835-14176/
Joint Bayes Filter A Hybrid Tracker for Non-rigid Hand Motion
Recognition 1st edition by Huang Fei, Ian Reid ISBN 3540219828
9783540219828
https://ebookball.com/product/joint-bayes-filter-a-hybrid-
tracker-for-non-rigid-hand-motion-recognition-1st-edition-by-
huang-fei-ian-reid-isbn-3540219828-9783540219828-9234/
Probabilistic Speckle Decorrelation for 3D Ultrasound 1st Edition by
Catherine Laporte, Tal Arbel ISBN 9783540757573
https://ebookball.com/product/probabilistic-speckle-
decorrelation-for-3d-ultrasound-1st-edition-by-catherine-laporte-
tal-arbel-isbn-9783540757573-12122/
Registration of High Angular Resolution Diffusion MRI Images Using 4th
Order Tensors 1st Edition by Angelos Barmpoutis, Baba C VemurI, John R
Forder ISBN 9783540757573
https://ebookball.com/product/registration-of-high-angular-
resolution-diffusion-mri-images-using-4th-order-tensors-1st-
edition-by-angelos-barmpoutis-baba-c-vemuri-john-r-forder-
isbn-9783540757573-13718/
, Deformable Density Matching for 3D Non-rigid
Registration of Shapes
Arunabha S. Roy1 , Ajay Gopinath1 , and Anand Rangarajan2,
1
Imaging Technologies Laboratory, GE Global Research Center, Bangalore, India
2
Department of CISE, University of Florida, Gainesville, FL, USA
Abstract. There exists a large body of literature on shape matching
and registration in medical image analysis. However, most of the previ-
ous work is focused on matching particular sets of features—point-sets,
lines, curves and surfaces. In this work, we forsake specific geometric
shape representations and instead seek probabilistic representations—
specifically Gaussian mixture models—of shapes. We evaluate a closed-
form distance between two probabilistic shape representations for the
general case where the mixture models differ in variance and the num-
ber of components. We then cast non-rigid registration as a deformable
density matching problem. In our approach, we take one mixture den-
sity onto another by deforming the component centroids via a thin-plate
spline (TPS) and also minimizing the distance with respect to the vari-
ance parameters. We validate our approach on synthetic and 3D arterial
tree data and evaluate it on 3D hippocampal shapes.
1 Introduction
The need for shape matching occurs in diverse sub-domains of medical image
analysis. Whenever a biomedical image is segmented or parsed into a set of
shapes, the need for shape analysis and comparison usually arises [1]. In brain
mapping for example [2], we frequently require the comparison of cortical and
subcortical structures such as the thalamus, putamen etc. extracted from subject
neuroanatomical MRI images. Image databases often use shape features and
here the need is to index and query the shape database. In MR angiography,
the complex network of blood vessels in the brain can be represented as trees or
graphs and need to be compared across subjects. And in cardiac applications, if
heart chamber information is available and extracted as a set of shapes, the wall
tracking problem requires us to solve for shape correspondences in the cardiac
cycle [3].
The need for shape matching is followed by a need for good shape repre-
sentations. When shape features are extracted from medical images, they can
be represented using an entire gamut of representations—points, line segments,
curves, surfaces, trees, graphs and hybrid representations. What should be noted
here is that an inferential stage is present in any shape representation. That is,
A.R. was partially supported by NSF IIS 0307712 and NIH RO1 NS046812.
N. Ayache, S. Ourselin, A. Maeder (Eds.): MICCAI 2007, Part I, LNCS 4791, pp. 942–949, 2007.
c Springer-Verlag Berlin Heidelberg 2007
