Efficient feature-based nonrigid registration of multiphase liver CT volumes

Dongjin Kwon, Il Dong Yun, Kyoungho Lee, Sang Uk Lee

Research output: Contribution to conferencePaperResearchpeer-review

12 Citations (Scopus)

Abstract

This paper presents an efficient feature-based nonrigid registration method for multiphase liver CT volumes. While radiologists routinely examine multiphase liver CT to detect hepatic diseases, they usually search corresponding points between 3D CT volumes by visual inspections using 2D slice images. As the liver is a deformable organ, there exist complex nonrigid transformations between liver CT volumes obtained at difference time points (phases). We introduce a fully automatic registration application for multiphase liver CT volumes. For two given liver CT volumes, we extract 3D features with their descriptors, and estimate correspondences by finding nearest neighbor in descriptor space. An energy function is constructed using the correspondence information and the smoothness measure of free-form deformation model based on B-splines. We integrate an approximated smoothness energy function and a robust correspondence energy estimator controlled by the confidence radius of the matching distance in this energy model. The energy function is optimized by sequentially reducing the confidence radius, and outlier correspondences are discarded systematically during convergence. We propose a highly efficient optimization procedure using the preconditioned nonlinear conjugate gradient method. In the experiments, we will provide quantitative and qualitative results on synthetic and clinical data sets.

Original languageEnglish
DOIs
StatePublished - 1 Jan 2008
Event2008 19th British Machine Vision Conference, BMVC 2008 - Leeds, United Kingdom
Duration: 1 Sep 20084 Sep 2008

Other

Other2008 19th British Machine Vision Conference, BMVC 2008
CountryUnited Kingdom
CityLeeds
Period1/09/084/09/08

Fingerprint

Liver
Conjugate gradient method
Splines
Inspection
Experiments

Cite this

Kwon, D., Yun, I. D., Lee, K., & Lee, S. U. (2008). Efficient feature-based nonrigid registration of multiphase liver CT volumes. Paper presented at 2008 19th British Machine Vision Conference, BMVC 2008, Leeds, United Kingdom. https://doi.org/10.5244/C.22.36
Kwon, Dongjin ; Yun, Il Dong ; Lee, Kyoungho ; Lee, Sang Uk. / Efficient feature-based nonrigid registration of multiphase liver CT volumes. Paper presented at 2008 19th British Machine Vision Conference, BMVC 2008, Leeds, United Kingdom.
@conference{71d993e8a4194311a75de653099ca033,
title = "Efficient feature-based nonrigid registration of multiphase liver CT volumes",
abstract = "This paper presents an efficient feature-based nonrigid registration method for multiphase liver CT volumes. While radiologists routinely examine multiphase liver CT to detect hepatic diseases, they usually search corresponding points between 3D CT volumes by visual inspections using 2D slice images. As the liver is a deformable organ, there exist complex nonrigid transformations between liver CT volumes obtained at difference time points (phases). We introduce a fully automatic registration application for multiphase liver CT volumes. For two given liver CT volumes, we extract 3D features with their descriptors, and estimate correspondences by finding nearest neighbor in descriptor space. An energy function is constructed using the correspondence information and the smoothness measure of free-form deformation model based on B-splines. We integrate an approximated smoothness energy function and a robust correspondence energy estimator controlled by the confidence radius of the matching distance in this energy model. The energy function is optimized by sequentially reducing the confidence radius, and outlier correspondences are discarded systematically during convergence. We propose a highly efficient optimization procedure using the preconditioned nonlinear conjugate gradient method. In the experiments, we will provide quantitative and qualitative results on synthetic and clinical data sets.",
author = "Dongjin Kwon and Yun, {Il Dong} and Kyoungho Lee and Lee, {Sang Uk}",
year = "2008",
month = "1",
day = "1",
doi = "10.5244/C.22.36",
language = "English",
note = "null ; Conference date: 01-09-2008 Through 04-09-2008",

}

Kwon, D, Yun, ID, Lee, K & Lee, SU 2008, 'Efficient feature-based nonrigid registration of multiphase liver CT volumes' Paper presented at 2008 19th British Machine Vision Conference, BMVC 2008, Leeds, United Kingdom, 1/09/08 - 4/09/08, . https://doi.org/10.5244/C.22.36

Efficient feature-based nonrigid registration of multiphase liver CT volumes. / Kwon, Dongjin; Yun, Il Dong; Lee, Kyoungho; Lee, Sang Uk.

2008. Paper presented at 2008 19th British Machine Vision Conference, BMVC 2008, Leeds, United Kingdom.

Research output: Contribution to conferencePaperResearchpeer-review

TY - CONF

T1 - Efficient feature-based nonrigid registration of multiphase liver CT volumes

AU - Kwon, Dongjin

AU - Yun, Il Dong

AU - Lee, Kyoungho

AU - Lee, Sang Uk

PY - 2008/1/1

Y1 - 2008/1/1

N2 - This paper presents an efficient feature-based nonrigid registration method for multiphase liver CT volumes. While radiologists routinely examine multiphase liver CT to detect hepatic diseases, they usually search corresponding points between 3D CT volumes by visual inspections using 2D slice images. As the liver is a deformable organ, there exist complex nonrigid transformations between liver CT volumes obtained at difference time points (phases). We introduce a fully automatic registration application for multiphase liver CT volumes. For two given liver CT volumes, we extract 3D features with their descriptors, and estimate correspondences by finding nearest neighbor in descriptor space. An energy function is constructed using the correspondence information and the smoothness measure of free-form deformation model based on B-splines. We integrate an approximated smoothness energy function and a robust correspondence energy estimator controlled by the confidence radius of the matching distance in this energy model. The energy function is optimized by sequentially reducing the confidence radius, and outlier correspondences are discarded systematically during convergence. We propose a highly efficient optimization procedure using the preconditioned nonlinear conjugate gradient method. In the experiments, we will provide quantitative and qualitative results on synthetic and clinical data sets.

AB - This paper presents an efficient feature-based nonrigid registration method for multiphase liver CT volumes. While radiologists routinely examine multiphase liver CT to detect hepatic diseases, they usually search corresponding points between 3D CT volumes by visual inspections using 2D slice images. As the liver is a deformable organ, there exist complex nonrigid transformations between liver CT volumes obtained at difference time points (phases). We introduce a fully automatic registration application for multiphase liver CT volumes. For two given liver CT volumes, we extract 3D features with their descriptors, and estimate correspondences by finding nearest neighbor in descriptor space. An energy function is constructed using the correspondence information and the smoothness measure of free-form deformation model based on B-splines. We integrate an approximated smoothness energy function and a robust correspondence energy estimator controlled by the confidence radius of the matching distance in this energy model. The energy function is optimized by sequentially reducing the confidence radius, and outlier correspondences are discarded systematically during convergence. We propose a highly efficient optimization procedure using the preconditioned nonlinear conjugate gradient method. In the experiments, we will provide quantitative and qualitative results on synthetic and clinical data sets.

UR - http://www.scopus.com/inward/record.url?scp=84898436628&partnerID=8YFLogxK

U2 - 10.5244/C.22.36

DO - 10.5244/C.22.36

M3 - Paper

ER -

Kwon D, Yun ID, Lee K, Lee SU. Efficient feature-based nonrigid registration of multiphase liver CT volumes. 2008. Paper presented at 2008 19th British Machine Vision Conference, BMVC 2008, Leeds, United Kingdom. https://doi.org/10.5244/C.22.36