Automated landmark-guided deformable image registration

Vasant Kearney, Susie Chen, Xuejun Gu, Tsuicheng Chiu, Honghuan Liu, Lan Jiang, Jing Wang, John Yordy, Lucien Nedzi, Weihua Mao

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The purpose of this work is to develop an automated landmark-guided deformable image registration (LDIR) algorithm between the planning CT and daily cone-beam CT (CBCT) with low image quality. This method uses an automated landmark generation algorithm in conjunction with a local small volume gradient matching search engine to map corresponding landmarks between the CBCT and the planning CT. The landmarks act as stabilizing control points in the following Demons deformable image registration. LDIR is implemented on graphics processing units (GPUs) for parallel computation to achieve ultra fast calculation. The accuracy of the LDIR algorithm has been evaluated on a synthetic case in the presence of different noise levels and data of six head and neck cancer patients. The results indicate that LDIR performed better than rigid registration, Demons, and intensity corrected Demons for all similarity metrics used. In conclusion, LDIR achieves high accuracy in the presence of multimodality intensity mismatch and CBCT noise contamination, while simultaneously preserving high computational efficiency.

Original languageEnglish (US)
Article number101
Pages (from-to)101-116
Number of pages16
JournalPhysics in Medicine and Biology
Volume60
Issue number1
DOIs
StatePublished - Jan 7 2015

Fingerprint

Cone-Beam Computed Tomography
Noise
Search Engine
Head and Neck Neoplasms

Keywords

  • Cone beam CT
  • Deformable image registration
  • Image guided radiotherapy

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology

Cite this

Kearney, V., Chen, S., Gu, X., Chiu, T., Liu, H., Jiang, L., ... Mao, W. (2015). Automated landmark-guided deformable image registration. Physics in Medicine and Biology, 60(1), 101-116. [101]. https://doi.org/10.1088/0031-9155/60/1/101

Automated landmark-guided deformable image registration. / Kearney, Vasant; Chen, Susie; Gu, Xuejun; Chiu, Tsuicheng; Liu, Honghuan; Jiang, Lan; Wang, Jing; Yordy, John; Nedzi, Lucien; Mao, Weihua.

In: Physics in Medicine and Biology, Vol. 60, No. 1, 101, 07.01.2015, p. 101-116.

Research output: Contribution to journalArticle

Kearney, V, Chen, S, Gu, X, Chiu, T, Liu, H, Jiang, L, Wang, J, Yordy, J, Nedzi, L & Mao, W 2015, 'Automated landmark-guided deformable image registration', Physics in Medicine and Biology, vol. 60, no. 1, 101, pp. 101-116. https://doi.org/10.1088/0031-9155/60/1/101
Kearney, Vasant ; Chen, Susie ; Gu, Xuejun ; Chiu, Tsuicheng ; Liu, Honghuan ; Jiang, Lan ; Wang, Jing ; Yordy, John ; Nedzi, Lucien ; Mao, Weihua. / Automated landmark-guided deformable image registration. In: Physics in Medicine and Biology. 2015 ; Vol. 60, No. 1. pp. 101-116.
@article{7b23122f4dae4f638e8de46d5575c33a,
title = "Automated landmark-guided deformable image registration",
abstract = "The purpose of this work is to develop an automated landmark-guided deformable image registration (LDIR) algorithm between the planning CT and daily cone-beam CT (CBCT) with low image quality. This method uses an automated landmark generation algorithm in conjunction with a local small volume gradient matching search engine to map corresponding landmarks between the CBCT and the planning CT. The landmarks act as stabilizing control points in the following Demons deformable image registration. LDIR is implemented on graphics processing units (GPUs) for parallel computation to achieve ultra fast calculation. The accuracy of the LDIR algorithm has been evaluated on a synthetic case in the presence of different noise levels and data of six head and neck cancer patients. The results indicate that LDIR performed better than rigid registration, Demons, and intensity corrected Demons for all similarity metrics used. In conclusion, LDIR achieves high accuracy in the presence of multimodality intensity mismatch and CBCT noise contamination, while simultaneously preserving high computational efficiency.",
keywords = "Cone beam CT, Deformable image registration, Image guided radiotherapy",
author = "Vasant Kearney and Susie Chen and Xuejun Gu and Tsuicheng Chiu and Honghuan Liu and Lan Jiang and Jing Wang and John Yordy and Lucien Nedzi and Weihua Mao",
year = "2015",
month = "1",
day = "7",
doi = "10.1088/0031-9155/60/1/101",
language = "English (US)",
volume = "60",
pages = "101--116",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "1",

}

TY - JOUR

T1 - Automated landmark-guided deformable image registration

AU - Kearney, Vasant

AU - Chen, Susie

AU - Gu, Xuejun

AU - Chiu, Tsuicheng

AU - Liu, Honghuan

AU - Jiang, Lan

AU - Wang, Jing

AU - Yordy, John

AU - Nedzi, Lucien

AU - Mao, Weihua

PY - 2015/1/7

Y1 - 2015/1/7

N2 - The purpose of this work is to develop an automated landmark-guided deformable image registration (LDIR) algorithm between the planning CT and daily cone-beam CT (CBCT) with low image quality. This method uses an automated landmark generation algorithm in conjunction with a local small volume gradient matching search engine to map corresponding landmarks between the CBCT and the planning CT. The landmarks act as stabilizing control points in the following Demons deformable image registration. LDIR is implemented on graphics processing units (GPUs) for parallel computation to achieve ultra fast calculation. The accuracy of the LDIR algorithm has been evaluated on a synthetic case in the presence of different noise levels and data of six head and neck cancer patients. The results indicate that LDIR performed better than rigid registration, Demons, and intensity corrected Demons for all similarity metrics used. In conclusion, LDIR achieves high accuracy in the presence of multimodality intensity mismatch and CBCT noise contamination, while simultaneously preserving high computational efficiency.

AB - The purpose of this work is to develop an automated landmark-guided deformable image registration (LDIR) algorithm between the planning CT and daily cone-beam CT (CBCT) with low image quality. This method uses an automated landmark generation algorithm in conjunction with a local small volume gradient matching search engine to map corresponding landmarks between the CBCT and the planning CT. The landmarks act as stabilizing control points in the following Demons deformable image registration. LDIR is implemented on graphics processing units (GPUs) for parallel computation to achieve ultra fast calculation. The accuracy of the LDIR algorithm has been evaluated on a synthetic case in the presence of different noise levels and data of six head and neck cancer patients. The results indicate that LDIR performed better than rigid registration, Demons, and intensity corrected Demons for all similarity metrics used. In conclusion, LDIR achieves high accuracy in the presence of multimodality intensity mismatch and CBCT noise contamination, while simultaneously preserving high computational efficiency.

KW - Cone beam CT

KW - Deformable image registration

KW - Image guided radiotherapy

UR - http://www.scopus.com/inward/record.url?scp=84918583761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84918583761&partnerID=8YFLogxK

U2 - 10.1088/0031-9155/60/1/101

DO - 10.1088/0031-9155/60/1/101

M3 - Article

C2 - 25479095

AN - SCOPUS:84918583761

VL - 60

SP - 101

EP - 116

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 1

M1 - 101

ER -