Frameless registration of MR and CT 3D volumetric data sets

Rakesh Kumar; Kristin Dana; P. Anandan; Neil Okamoto; Jim Bergen; Paul Hemler; Thilaka S. Sumanaweera; Petra A. van den Elsen; John Adler

Frameless registration of MR and CT 3D volumetric data sets

Rakesh Kumar, Kristin Dana, P. Anandan, Neil Okamoto, Jim Bergen, Paul Hemler, Thilaka S. Sumanaweera, Petra A. van den Elsen, John Adler

Research output: Contribution to conference › Paper › peer-review

5 Scopus citations

Abstract

In this paper we present techniques for frameless registration of 3D Magnetic Resonance (MR) and Computed Tomography (CT) volumetric data of the head and spine. We present techniques for estimating a 3D affine or rigid transform which can be used to resample the CT (or MR) data to align with the MR (or CT) data. Our technique transforms the MR and CT data sets with spatial filters so they can be directly matched. The matching is done by a direct optimization technique using a gradient based descent approach and a coarse-to-fine control strategy over a 4D pyramid. We present results on registering the head and spine data by matching 3D edges and results on registering cranial ventricle data by matching images filtered by a Laplacian of a Gaussian.

Original language	American English
Pages	240-248
Number of pages	9
State	Published - 1994
Externally published	Yes
Event	Proceedings of the 2nd IEEE Workshop on Applications of Computer Vision - Sarasota, FL, USA Duration: Dec 5 1994 → Dec 7 1994

Other

Other	Proceedings of the 2nd IEEE Workshop on Applications of Computer Vision
City	Sarasota, FL, USA
Period	12/5/94 → 12/7/94

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Hardware and Architecture
Electrical and Electronic Engineering

Cite this

@conference{5062d78bd4eb49b288c2a8c7fe157b21,

title = "Frameless registration of MR and CT 3D volumetric data sets",

abstract = "In this paper we present techniques for frameless registration of 3D Magnetic Resonance (MR) and Computed Tomography (CT) volumetric data of the head and spine. We present techniques for estimating a 3D affine or rigid transform which can be used to resample the CT (or MR) data to align with the MR (or CT) data. Our technique transforms the MR and CT data sets with spatial filters so they can be directly matched. The matching is done by a direct optimization technique using a gradient based descent approach and a coarse-to-fine control strategy over a 4D pyramid. We present results on registering the head and spine data by matching 3D edges and results on registering cranial ventricle data by matching images filtered by a Laplacian of a Gaussian.",

author = "Rakesh Kumar and Kristin Dana and P. Anandan and Neil Okamoto and Jim Bergen and Paul Hemler and Sumanaweera, {Thilaka S.} and {van den Elsen}, {Petra A.} and John Adler",

year = "1994",

language = "American English",

pages = "240--248",

note = "Proceedings of the 2nd IEEE Workshop on Applications of Computer Vision ; Conference date: 05-12-1994 Through 07-12-1994",

}

TY - CONF

T1 - Frameless registration of MR and CT 3D volumetric data sets

AU - Kumar, Rakesh

AU - Dana, Kristin

AU - Anandan, P.

AU - Okamoto, Neil

AU - Bergen, Jim

AU - Hemler, Paul

AU - Sumanaweera, Thilaka S.

AU - van den Elsen, Petra A.

AU - Adler, John

PY - 1994

Y1 - 1994

N2 - In this paper we present techniques for frameless registration of 3D Magnetic Resonance (MR) and Computed Tomography (CT) volumetric data of the head and spine. We present techniques for estimating a 3D affine or rigid transform which can be used to resample the CT (or MR) data to align with the MR (or CT) data. Our technique transforms the MR and CT data sets with spatial filters so they can be directly matched. The matching is done by a direct optimization technique using a gradient based descent approach and a coarse-to-fine control strategy over a 4D pyramid. We present results on registering the head and spine data by matching 3D edges and results on registering cranial ventricle data by matching images filtered by a Laplacian of a Gaussian.

AB - In this paper we present techniques for frameless registration of 3D Magnetic Resonance (MR) and Computed Tomography (CT) volumetric data of the head and spine. We present techniques for estimating a 3D affine or rigid transform which can be used to resample the CT (or MR) data to align with the MR (or CT) data. Our technique transforms the MR and CT data sets with spatial filters so they can be directly matched. The matching is done by a direct optimization technique using a gradient based descent approach and a coarse-to-fine control strategy over a 4D pyramid. We present results on registering the head and spine data by matching 3D edges and results on registering cranial ventricle data by matching images filtered by a Laplacian of a Gaussian.

UR - http://www.scopus.com/inward/record.url?scp=0028752859&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028752859&partnerID=8YFLogxK

M3 - Paper

SP - 240

EP - 248

T2 - Proceedings of the 2nd IEEE Workshop on Applications of Computer Vision

Y2 - 5 December 1994 through 7 December 1994

ER -

Frameless registration of MR and CT 3D volumetric data sets

Abstract

Other

ASJC Scopus subject areas

Other files and links

Cite this