Standard

Multiple-correlation similarity for block-matching based fast CT to ultrasound registration in liver interventions. / Banerjee, Jyotirmoy; Sun, Yuanyuan; Klink, Camiel; Gahrmann, Renske; Niessen, Wiro J.; Moelker, Adriaan; van Walsum, Theo.

In: Medical Image Analysis, Vol. 53, 2019, p. 132-141.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Banerjee, Jyotirmoy ; Sun, Yuanyuan ; Klink, Camiel ; Gahrmann, Renske ; Niessen, Wiro J. ; Moelker, Adriaan ; van Walsum, Theo. / Multiple-correlation similarity for block-matching based fast CT to ultrasound registration in liver interventions. In: Medical Image Analysis. 2019 ; Vol. 53. pp. 132-141.

BibTeX

@article{a9274f388f964334a45bd813be4432d3,
title = "Multiple-correlation similarity for block-matching based fast CT to ultrasound registration in liver interventions",
abstract = "In this work we present a fast approach to perform registration of computed tomography to ultrasound volumes for image guided intervention applications. The method is based on a combination of block-matching and outlier rejection. The block-matching uses a correlation based multimodal similarity metric, where the intensity and the gradient of the computed tomography images along with the ultrasound volumes are the input images to find correspondences between blocks in the computed tomography and the ultrasound volumes. A variance and octree based feature point-set selection method is used for selecting distinct and evenly spread point locations for block-matching. Geometric consistency and smoothness criteria are imposed in an outlier rejection step to refine the block-matching results. The block-matching results after outlier rejection are used to determine the affine transformation between the computed tomography and the ultrasound volumes. Various experiments are carried out to assess the optimal performance and the influence of parameters on accuracy and computational time of the registration. A leave-one-patient-out cross-validation registration error of 3.6 mm is achieved over 29 datasets, acquired from 17 patients.",
keywords = "3D, CT, Liver, Multimodal, Registration, Ultrasound",
author = "Jyotirmoy Banerjee and Yuanyuan Sun and Camiel Klink and Renske Gahrmann and Niessen, {Wiro J.} and Adriaan Moelker and {van Walsum}, Theo",
year = "2019",
doi = "10.1016/j.media.2019.02.003",
language = "English",
volume = "53",
pages = "132--141",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Multiple-correlation similarity for block-matching based fast CT to ultrasound registration in liver interventions

AU - Banerjee, Jyotirmoy

AU - Sun, Yuanyuan

AU - Klink, Camiel

AU - Gahrmann, Renske

AU - Niessen, Wiro J.

AU - Moelker, Adriaan

AU - van Walsum, Theo

PY - 2019

Y1 - 2019

N2 - In this work we present a fast approach to perform registration of computed tomography to ultrasound volumes for image guided intervention applications. The method is based on a combination of block-matching and outlier rejection. The block-matching uses a correlation based multimodal similarity metric, where the intensity and the gradient of the computed tomography images along with the ultrasound volumes are the input images to find correspondences between blocks in the computed tomography and the ultrasound volumes. A variance and octree based feature point-set selection method is used for selecting distinct and evenly spread point locations for block-matching. Geometric consistency and smoothness criteria are imposed in an outlier rejection step to refine the block-matching results. The block-matching results after outlier rejection are used to determine the affine transformation between the computed tomography and the ultrasound volumes. Various experiments are carried out to assess the optimal performance and the influence of parameters on accuracy and computational time of the registration. A leave-one-patient-out cross-validation registration error of 3.6 mm is achieved over 29 datasets, acquired from 17 patients.

AB - In this work we present a fast approach to perform registration of computed tomography to ultrasound volumes for image guided intervention applications. The method is based on a combination of block-matching and outlier rejection. The block-matching uses a correlation based multimodal similarity metric, where the intensity and the gradient of the computed tomography images along with the ultrasound volumes are the input images to find correspondences between blocks in the computed tomography and the ultrasound volumes. A variance and octree based feature point-set selection method is used for selecting distinct and evenly spread point locations for block-matching. Geometric consistency and smoothness criteria are imposed in an outlier rejection step to refine the block-matching results. The block-matching results after outlier rejection are used to determine the affine transformation between the computed tomography and the ultrasound volumes. Various experiments are carried out to assess the optimal performance and the influence of parameters on accuracy and computational time of the registration. A leave-one-patient-out cross-validation registration error of 3.6 mm is achieved over 29 datasets, acquired from 17 patients.

KW - 3D

KW - CT

KW - Liver

KW - Multimodal

KW - Registration

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85061547819&partnerID=8YFLogxK

U2 - 10.1016/j.media.2019.02.003

DO - 10.1016/j.media.2019.02.003

M3 - Article

VL - 53

SP - 132

EP - 141

JO - Medical Image Analysis

T2 - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -

ID: 51940305