Registration of bone structures in 3D ultrasound and CT data: comparison of different optimization strategies

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Standard

Registration of bone structures in 3D ultrasound and CT data : comparison of different optimization strategies. / Winter, Susanne; Brendel, Bernhard; Igel, Christian.

I: International Congress Series, Bind 1281, 2005, s. 242-247.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Harvard

Winter, S, Brendel, B & Igel, C 2005, 'Registration of bone structures in 3D ultrasound and CT data: comparison of different optimization strategies', International Congress Series, bind 1281, s. 242-247. https://doi.org/10.1016/j.ics.2005.03.351

APA

Winter, S., Brendel, B., & Igel, C. (2005). Registration of bone structures in 3D ultrasound and CT data: comparison of different optimization strategies. International Congress Series, 1281, 242-247. https://doi.org/10.1016/j.ics.2005.03.351

Vancouver

Winter S, Brendel B, Igel C. Registration of bone structures in 3D ultrasound and CT data: comparison of different optimization strategies. International Congress Series. 2005;1281:242-247. https://doi.org/10.1016/j.ics.2005.03.351

Author

Winter, Susanne ; Brendel, Bernhard ; Igel, Christian. / Registration of bone structures in 3D ultrasound and CT data : comparison of different optimization strategies. I: International Congress Series. 2005 ; Bind 1281. s. 242-247.

Bibtex

@inproceedings{3df464bce4be4cafbe6ce330ce4a683c,
title = "Registration of bone structures in 3D ultrasound and CT data: comparison of different optimization strategies",
abstract = "We developed a fast and robust algorithm to register intraoperative three-dimensional ultrasound data of the spine with preoperative CT data. We compared different gradient-based and evolutionary optimization strategies for solving the registration problem. The iRprop, a fast gradient-based optimization algorithm, quickly and reliably led to higher registration rates than the two established methods BFGS and conjugate gradient descent (CG). The Covariance Matrix Adaptation evolution strategy (CMA) yielded the best results concerning registration rate and accuracy but at the cost of a slightly higher number of evaluations of the optimization criterion compared to CG and iRprop. The CMA was able to register patient data starting from a realistic misalignment in 98% of the trials in about 15 s per registration.",
keywords = "Evolutionary optimization, Image registration, Spine, Ultrasound",
author = "Susanne Winter and Bernhard Brendel and Christian Igel",
year = "2005",
doi = "10.1016/j.ics.2005.03.351",
language = "English",
volume = "1281",
pages = "242--247",
journal = "International Congress Series",
issn = "0531-5131",
publisher = "Elsevier",
note = "null ; Conference date: 22-06-2005 Through 25-06-2005",

}

RIS

TY - GEN

T1 - Registration of bone structures in 3D ultrasound and CT data

AU - Winter, Susanne

AU - Brendel, Bernhard

AU - Igel, Christian

N1 - Conference code: 19

PY - 2005

Y1 - 2005

N2 - We developed a fast and robust algorithm to register intraoperative three-dimensional ultrasound data of the spine with preoperative CT data. We compared different gradient-based and evolutionary optimization strategies for solving the registration problem. The iRprop, a fast gradient-based optimization algorithm, quickly and reliably led to higher registration rates than the two established methods BFGS and conjugate gradient descent (CG). The Covariance Matrix Adaptation evolution strategy (CMA) yielded the best results concerning registration rate and accuracy but at the cost of a slightly higher number of evaluations of the optimization criterion compared to CG and iRprop. The CMA was able to register patient data starting from a realistic misalignment in 98% of the trials in about 15 s per registration.

AB - We developed a fast and robust algorithm to register intraoperative three-dimensional ultrasound data of the spine with preoperative CT data. We compared different gradient-based and evolutionary optimization strategies for solving the registration problem. The iRprop, a fast gradient-based optimization algorithm, quickly and reliably led to higher registration rates than the two established methods BFGS and conjugate gradient descent (CG). The Covariance Matrix Adaptation evolution strategy (CMA) yielded the best results concerning registration rate and accuracy but at the cost of a slightly higher number of evaluations of the optimization criterion compared to CG and iRprop. The CMA was able to register patient data starting from a realistic misalignment in 98% of the trials in about 15 s per registration.

KW - Evolutionary optimization

KW - Image registration

KW - Spine

KW - Ultrasound

U2 - 10.1016/j.ics.2005.03.351

DO - 10.1016/j.ics.2005.03.351

M3 - Conference article

AN - SCOPUS:33646458732

VL - 1281

SP - 242

EP - 247

JO - International Congress Series

JF - International Congress Series

SN - 0531-5131

Y2 - 22 June 2005 through 25 June 2005

ER -

ID: 168565998