Pulmonary nodule registration

Rigid or nonrigid?

Suicheng Gu, David Wilson, Jun Tan, Jiantao Pu

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Purpose: The primary aim of this study is to investigate the performance difference of rigid and nonrigid registration schemes in matching corresponding pulmonary nodules depicted on sequential chest computed tomography (CT) examinations. Methods: A gradient descent based rigid registration algorithm with scaling was developed and it handled the involved geometric transformations (i.e., translation, rescaling, shearing, and rotation) separately instead of optimizing them in a single pass. Given two lung CT examinations, the scaling and translation parameters were simply estimated from the lung volume dimensions (e.g., size and mass center), while the rotation parameters were optimized progressively using gradient descent. To investigate the performance difference of rigid and nonrigid schemes in pulmonary nodule registration, the well-known nonrigid Demons algorithm was implemented and tested along with the developed schemes against 60 diverse low-dose clinical lung CT examinations with average 2-yr follow-up scans. A verified cancer and its correspondence in the follow-up scan as well as their spatial locations (mass center) were identified in each examination. In addition to the computational efficiency, the accuracy of these registration procedures was assessed by computing the Euclidean distances between the corresponding nodules after the registration. To demonstrate the advantage of the developed algorithm, the authors also implemented a fast iterative closest point (ICP) based rigid algorithm and compared their performance. Results: Our experiments on the collected chest CT examinations showed that the nodule registration errors in 3D Euclidean distance for the developed rigid affine approach, the traditional ICP algorithm, and the refining nonrigid Demons algorithm were 9.6, 9.8, and 10.0 mm, respectively, and the corresponding computational costs in time were 5, 300, and 55 s, respectively. Conclusions: A rigid solution may be preferred in practice for the pulmonary nodule registration in longitudinal studies because of its relatively high efficiency and sufficient accuracy for the clinical need.

Original languageEnglish (US)
Pages (from-to)4406-4414
Number of pages9
JournalMedical Physics
Volume38
Issue number7
DOIs
StatePublished - Jan 1 2011

Fingerprint

Lung
Tomography
Thorax
Longitudinal Studies
Costs and Cost Analysis
Neoplasms

Keywords

  • Demons algorithm
  • follow-up study
  • pulmonary nodule
  • rigid/nonrigid registration

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Pulmonary nodule registration : Rigid or nonrigid? / Gu, Suicheng; Wilson, David; Tan, Jun; Pu, Jiantao.

In: Medical Physics, Vol. 38, No. 7, 01.01.2011, p. 4406-4414.

Research output: Contribution to journalArticle

Gu, Suicheng ; Wilson, David ; Tan, Jun ; Pu, Jiantao. / Pulmonary nodule registration : Rigid or nonrigid?. In: Medical Physics. 2011 ; Vol. 38, No. 7. pp. 4406-4414.
@article{9118a7b823c34a54ac3667ec9508f287,
title = "Pulmonary nodule registration: Rigid or nonrigid?",
abstract = "Purpose: The primary aim of this study is to investigate the performance difference of rigid and nonrigid registration schemes in matching corresponding pulmonary nodules depicted on sequential chest computed tomography (CT) examinations. Methods: A gradient descent based rigid registration algorithm with scaling was developed and it handled the involved geometric transformations (i.e., translation, rescaling, shearing, and rotation) separately instead of optimizing them in a single pass. Given two lung CT examinations, the scaling and translation parameters were simply estimated from the lung volume dimensions (e.g., size and mass center), while the rotation parameters were optimized progressively using gradient descent. To investigate the performance difference of rigid and nonrigid schemes in pulmonary nodule registration, the well-known nonrigid Demons algorithm was implemented and tested along with the developed schemes against 60 diverse low-dose clinical lung CT examinations with average 2-yr follow-up scans. A verified cancer and its correspondence in the follow-up scan as well as their spatial locations (mass center) were identified in each examination. In addition to the computational efficiency, the accuracy of these registration procedures was assessed by computing the Euclidean distances between the corresponding nodules after the registration. To demonstrate the advantage of the developed algorithm, the authors also implemented a fast iterative closest point (ICP) based rigid algorithm and compared their performance. Results: Our experiments on the collected chest CT examinations showed that the nodule registration errors in 3D Euclidean distance for the developed rigid affine approach, the traditional ICP algorithm, and the refining nonrigid Demons algorithm were 9.6, 9.8, and 10.0 mm, respectively, and the corresponding computational costs in time were 5, 300, and 55 s, respectively. Conclusions: A rigid solution may be preferred in practice for the pulmonary nodule registration in longitudinal studies because of its relatively high efficiency and sufficient accuracy for the clinical need.",
keywords = "Demons algorithm, follow-up study, pulmonary nodule, rigid/nonrigid registration",
author = "Suicheng Gu and David Wilson and Jun Tan and Jiantao Pu",
year = "2011",
month = "1",
day = "1",
doi = "10.1118/1.3602457",
language = "English (US)",
volume = "38",
pages = "4406--4414",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "7",

}

TY - JOUR

T1 - Pulmonary nodule registration

T2 - Rigid or nonrigid?

AU - Gu, Suicheng

AU - Wilson, David

AU - Tan, Jun

AU - Pu, Jiantao

PY - 2011/1/1

Y1 - 2011/1/1

N2 - Purpose: The primary aim of this study is to investigate the performance difference of rigid and nonrigid registration schemes in matching corresponding pulmonary nodules depicted on sequential chest computed tomography (CT) examinations. Methods: A gradient descent based rigid registration algorithm with scaling was developed and it handled the involved geometric transformations (i.e., translation, rescaling, shearing, and rotation) separately instead of optimizing them in a single pass. Given two lung CT examinations, the scaling and translation parameters were simply estimated from the lung volume dimensions (e.g., size and mass center), while the rotation parameters were optimized progressively using gradient descent. To investigate the performance difference of rigid and nonrigid schemes in pulmonary nodule registration, the well-known nonrigid Demons algorithm was implemented and tested along with the developed schemes against 60 diverse low-dose clinical lung CT examinations with average 2-yr follow-up scans. A verified cancer and its correspondence in the follow-up scan as well as their spatial locations (mass center) were identified in each examination. In addition to the computational efficiency, the accuracy of these registration procedures was assessed by computing the Euclidean distances between the corresponding nodules after the registration. To demonstrate the advantage of the developed algorithm, the authors also implemented a fast iterative closest point (ICP) based rigid algorithm and compared their performance. Results: Our experiments on the collected chest CT examinations showed that the nodule registration errors in 3D Euclidean distance for the developed rigid affine approach, the traditional ICP algorithm, and the refining nonrigid Demons algorithm were 9.6, 9.8, and 10.0 mm, respectively, and the corresponding computational costs in time were 5, 300, and 55 s, respectively. Conclusions: A rigid solution may be preferred in practice for the pulmonary nodule registration in longitudinal studies because of its relatively high efficiency and sufficient accuracy for the clinical need.

AB - Purpose: The primary aim of this study is to investigate the performance difference of rigid and nonrigid registration schemes in matching corresponding pulmonary nodules depicted on sequential chest computed tomography (CT) examinations. Methods: A gradient descent based rigid registration algorithm with scaling was developed and it handled the involved geometric transformations (i.e., translation, rescaling, shearing, and rotation) separately instead of optimizing them in a single pass. Given two lung CT examinations, the scaling and translation parameters were simply estimated from the lung volume dimensions (e.g., size and mass center), while the rotation parameters were optimized progressively using gradient descent. To investigate the performance difference of rigid and nonrigid schemes in pulmonary nodule registration, the well-known nonrigid Demons algorithm was implemented and tested along with the developed schemes against 60 diverse low-dose clinical lung CT examinations with average 2-yr follow-up scans. A verified cancer and its correspondence in the follow-up scan as well as their spatial locations (mass center) were identified in each examination. In addition to the computational efficiency, the accuracy of these registration procedures was assessed by computing the Euclidean distances between the corresponding nodules after the registration. To demonstrate the advantage of the developed algorithm, the authors also implemented a fast iterative closest point (ICP) based rigid algorithm and compared their performance. Results: Our experiments on the collected chest CT examinations showed that the nodule registration errors in 3D Euclidean distance for the developed rigid affine approach, the traditional ICP algorithm, and the refining nonrigid Demons algorithm were 9.6, 9.8, and 10.0 mm, respectively, and the corresponding computational costs in time were 5, 300, and 55 s, respectively. Conclusions: A rigid solution may be preferred in practice for the pulmonary nodule registration in longitudinal studies because of its relatively high efficiency and sufficient accuracy for the clinical need.

KW - Demons algorithm

KW - follow-up study

KW - pulmonary nodule

KW - rigid/nonrigid registration

UR - http://www.scopus.com/inward/record.url?scp=79960270113&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960270113&partnerID=8YFLogxK

U2 - 10.1118/1.3602457

DO - 10.1118/1.3602457

M3 - Article

VL - 38

SP - 4406

EP - 4414

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 7

ER -