Motion Estimation of Skeletonized Angiographic Images Using Elastic Registration

Brian C.S. Tom; Aggelos K. Katsaggelos

doi:10.1109/42.310876

Motion Estimation of Skeletonized Angiographic Images Using Elastic Registration

Brian C.S. Tom, Aggelos K. Katsaggelos

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

35 Scopus citations

Abstract

In this paper an approach for estimating the motion of arteries in digital angiographic image sequences is proposed. Binary skeleton images are registered using an elastic registration algorithm in order to estimate the motion of the corresponding arteries. This algorithm operates recursively on the skeleton images by considering an autoregressive (AR) model of the deformation in conjunction with a dynamic programming (DP) algorithm. The AR model is used at the pixel level and provides a suitable cost function to DP through the innovation process. In addition, a moving average (MA) model for the motion of the entire skeleton is used in combination with the local AR model for improved registration results. The performance of this motion estimation method is demonstrated on simulated and real digital angiographic image sequences. It is shown that motion estimation using elastic registration of skeletons is very successful especially with low contrast and noisy angiographic images.

Original language	English (US)
Pages (from-to)	450-460
Number of pages	11
Journal	IEEE Transactions on Medical Imaging
Volume	13
Issue number	3
DOIs	https://doi.org/10.1109/42.310876
State	Published - Sep 1994

ASJC Scopus subject areas

Software
Radiological and Ultrasound Technology
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/42.310876

Cite this

@article{41f845db26f445f0b8fdc0776ca314dc,

title = "Motion Estimation of Skeletonized Angiographic Images Using Elastic Registration",

abstract = "In this paper an approach for estimating the motion of arteries in digital angiographic image sequences is proposed. Binary skeleton images are registered using an elastic registration algorithm in order to estimate the motion of the corresponding arteries. This algorithm operates recursively on the skeleton images by considering an autoregressive (AR) model of the deformation in conjunction with a dynamic programming (DP) algorithm. The AR model is used at the pixel level and provides a suitable cost function to DP through the innovation process. In addition, a moving average (MA) model for the motion of the entire skeleton is used in combination with the local AR model for improved registration results. The performance of this motion estimation method is demonstrated on simulated and real digital angiographic image sequences. It is shown that motion estimation using elastic registration of skeletons is very successful especially with low contrast and noisy angiographic images.",

author = "Tom, {Brian C.S.} and Katsaggelos, {Aggelos K.}",

note = "Funding Information: Manuscript received September 24, 1992; revised November 28, 1993. This material is based on work supported in part by Siemens. This paper was recommended by Associate Editor N. Ayache. B. Tom and A. Katsaggelos are at Northwestern University, Department of Electrical Engineering and Computer Science, McCormick School of Engineering, Evanston IL 60208 USA; e-mail aggk@delta.eecs.nwu.edu. S. Efstratiadis is at the Aristotelian University, Department of Electrical Engineering, Thessaloniki, Greece. IEEE Log Number 9403429.",

year = "1994",

month = sep,

doi = "10.1109/42.310876",

language = "English (US)",

volume = "13",

pages = "450--460",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Motion Estimation of Skeletonized Angiographic Images Using Elastic Registration

AU - Tom, Brian C.S.

AU - Katsaggelos, Aggelos K.

N1 - Funding Information: Manuscript received September 24, 1992; revised November 28, 1993. This material is based on work supported in part by Siemens. This paper was recommended by Associate Editor N. Ayache. B. Tom and A. Katsaggelos are at Northwestern University, Department of Electrical Engineering and Computer Science, McCormick School of Engineering, Evanston IL 60208 USA; e-mail aggk@delta.eecs.nwu.edu. S. Efstratiadis is at the Aristotelian University, Department of Electrical Engineering, Thessaloniki, Greece. IEEE Log Number 9403429.

PY - 1994/9

Y1 - 1994/9

N2 - In this paper an approach for estimating the motion of arteries in digital angiographic image sequences is proposed. Binary skeleton images are registered using an elastic registration algorithm in order to estimate the motion of the corresponding arteries. This algorithm operates recursively on the skeleton images by considering an autoregressive (AR) model of the deformation in conjunction with a dynamic programming (DP) algorithm. The AR model is used at the pixel level and provides a suitable cost function to DP through the innovation process. In addition, a moving average (MA) model for the motion of the entire skeleton is used in combination with the local AR model for improved registration results. The performance of this motion estimation method is demonstrated on simulated and real digital angiographic image sequences. It is shown that motion estimation using elastic registration of skeletons is very successful especially with low contrast and noisy angiographic images.

AB - In this paper an approach for estimating the motion of arteries in digital angiographic image sequences is proposed. Binary skeleton images are registered using an elastic registration algorithm in order to estimate the motion of the corresponding arteries. This algorithm operates recursively on the skeleton images by considering an autoregressive (AR) model of the deformation in conjunction with a dynamic programming (DP) algorithm. The AR model is used at the pixel level and provides a suitable cost function to DP through the innovation process. In addition, a moving average (MA) model for the motion of the entire skeleton is used in combination with the local AR model for improved registration results. The performance of this motion estimation method is demonstrated on simulated and real digital angiographic image sequences. It is shown that motion estimation using elastic registration of skeletons is very successful especially with low contrast and noisy angiographic images.

UR - http://www.scopus.com/inward/record.url?scp=0028497470&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028497470&partnerID=8YFLogxK

U2 - 10.1109/42.310876

DO - 10.1109/42.310876

M3 - Article

C2 - 18218520

AN - SCOPUS:0028497470

SN - 0278-0062

VL - 13

SP - 450

EP - 460

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 3

ER -

Motion Estimation of Skeletonized Angiographic Images Using Elastic Registration

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this