Correspondence detection in diffusion tensor images

Christos Davatzikos, Feby Abraham, George Biros, Ragini Verma

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

Abstract

This paper presents a kernel-based method of correspondence detection in diffusion tensor images (DTI), a key step towards their deformable registration. The proposed method is driven by a few focus points chosen in white matter, characterized by a unique morphological signature which incorporates the anisotropy, orientation and the anatomic context by using "oriented" Gabor filters and several candidate matches for each focal point, defined using tensorial similarity of these orientation specific signatures. The final focal point correspondences are defined via minimization of a function that seeks to satisfy three criteria : sparsity, which enforces unique correspondence, tensorial similarity of Gabor features, and smoothness, and are obtained by solving a constrained non-linear optimization problem with inequality bound constraints, using an optimization solver that employs primal-dual interior point algorithms and which ensures global convergence. The solution of the optimization problem produces the best correspondences for the focal points and uses these correspondences to obtain the optimal kernelized interpolation parameters for non-focal points. Experimental results on human brain data in which datasets with tumor are matched with normal brains, demonstrates the ability of the method in determining very good correspondences in the white matter, and its applicability to datasets with large mass effect as in tumors.

Original languageEnglish (US)
Title of host publication2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings
Pages646-649
Number of pages4
Volume2006
StatePublished - 2006
Externally publishedYes
Event2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Arlington, VA, United States
Duration: Apr 6 2006Apr 9 2006

Other

Other2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro
CountryUnited States
CityArlington, VA
Period4/6/064/9/06

Fingerprint

Tensors
Tumors
Brain
Gabor filters
Interpolation
Anisotropy

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Davatzikos, C., Abraham, F., Biros, G., & Verma, R. (2006). Correspondence detection in diffusion tensor images. In 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings (Vol. 2006, pp. 646-649). [1624999]

Correspondence detection in diffusion tensor images. / Davatzikos, Christos; Abraham, Feby; Biros, George; Verma, Ragini.

2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. Vol. 2006 2006. p. 646-649 1624999.

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

Davatzikos, C, Abraham, F, Biros, G & Verma, R 2006, Correspondence detection in diffusion tensor images. in 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. vol. 2006, 1624999, pp. 646-649, 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Arlington, VA, United States, 4/6/06.
Davatzikos C, Abraham F, Biros G, Verma R. Correspondence detection in diffusion tensor images. In 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. Vol. 2006. 2006. p. 646-649. 1624999
Davatzikos, Christos ; Abraham, Feby ; Biros, George ; Verma, Ragini. / Correspondence detection in diffusion tensor images. 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. Vol. 2006 2006. pp. 646-649
@inproceedings{4e9327ecf10248a885b419d168b5b3c4,
title = "Correspondence detection in diffusion tensor images",
abstract = "This paper presents a kernel-based method of correspondence detection in diffusion tensor images (DTI), a key step towards their deformable registration. The proposed method is driven by a few focus points chosen in white matter, characterized by a unique morphological signature which incorporates the anisotropy, orientation and the anatomic context by using {"}oriented{"} Gabor filters and several candidate matches for each focal point, defined using tensorial similarity of these orientation specific signatures. The final focal point correspondences are defined via minimization of a function that seeks to satisfy three criteria : sparsity, which enforces unique correspondence, tensorial similarity of Gabor features, and smoothness, and are obtained by solving a constrained non-linear optimization problem with inequality bound constraints, using an optimization solver that employs primal-dual interior point algorithms and which ensures global convergence. The solution of the optimization problem produces the best correspondences for the focal points and uses these correspondences to obtain the optimal kernelized interpolation parameters for non-focal points. Experimental results on human brain data in which datasets with tumor are matched with normal brains, demonstrates the ability of the method in determining very good correspondences in the white matter, and its applicability to datasets with large mass effect as in tumors.",
author = "Christos Davatzikos and Feby Abraham and George Biros and Ragini Verma",
year = "2006",
language = "English (US)",
isbn = "0780395778",
volume = "2006",
pages = "646--649",
booktitle = "2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings",

}

TY - GEN

T1 - Correspondence detection in diffusion tensor images

AU - Davatzikos, Christos

AU - Abraham, Feby

AU - Biros, George

AU - Verma, Ragini

PY - 2006

Y1 - 2006

N2 - This paper presents a kernel-based method of correspondence detection in diffusion tensor images (DTI), a key step towards their deformable registration. The proposed method is driven by a few focus points chosen in white matter, characterized by a unique morphological signature which incorporates the anisotropy, orientation and the anatomic context by using "oriented" Gabor filters and several candidate matches for each focal point, defined using tensorial similarity of these orientation specific signatures. The final focal point correspondences are defined via minimization of a function that seeks to satisfy three criteria : sparsity, which enforces unique correspondence, tensorial similarity of Gabor features, and smoothness, and are obtained by solving a constrained non-linear optimization problem with inequality bound constraints, using an optimization solver that employs primal-dual interior point algorithms and which ensures global convergence. The solution of the optimization problem produces the best correspondences for the focal points and uses these correspondences to obtain the optimal kernelized interpolation parameters for non-focal points. Experimental results on human brain data in which datasets with tumor are matched with normal brains, demonstrates the ability of the method in determining very good correspondences in the white matter, and its applicability to datasets with large mass effect as in tumors.

AB - This paper presents a kernel-based method of correspondence detection in diffusion tensor images (DTI), a key step towards their deformable registration. The proposed method is driven by a few focus points chosen in white matter, characterized by a unique morphological signature which incorporates the anisotropy, orientation and the anatomic context by using "oriented" Gabor filters and several candidate matches for each focal point, defined using tensorial similarity of these orientation specific signatures. The final focal point correspondences are defined via minimization of a function that seeks to satisfy three criteria : sparsity, which enforces unique correspondence, tensorial similarity of Gabor features, and smoothness, and are obtained by solving a constrained non-linear optimization problem with inequality bound constraints, using an optimization solver that employs primal-dual interior point algorithms and which ensures global convergence. The solution of the optimization problem produces the best correspondences for the focal points and uses these correspondences to obtain the optimal kernelized interpolation parameters for non-focal points. Experimental results on human brain data in which datasets with tumor are matched with normal brains, demonstrates the ability of the method in determining very good correspondences in the white matter, and its applicability to datasets with large mass effect as in tumors.

UR - http://www.scopus.com/inward/record.url?scp=33750953813&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750953813&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780395778

SN - 9780780395770

VL - 2006

SP - 646

EP - 649

BT - 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings

ER -