Subpopulation-based correspondence modelling for improved respiratory motion estimation in the presence of inter-fraction motion variations

Matthias Wilms, René Werner, Tokihiro Yamamoto, Heinz Handels, Jan Ehrhardt

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Correspondence modelling between low-dimensional breathing signals and internal organ motion is a prerequisite for application of advanced techniques in radiotherapy of moving targets. Patient-specific correspondence models can, for example, be built prior to treatment based on a planning 4D CT and simultaneously acquired breathing signals. Reliability of pre-treatment-built models depends, however, on the degree of patient-specific inter-fraction motion variations. This study investigates whether motion estimation accuracy in the presence of inter-fraction motion variations can be improved using correspondence models that incorporate motion information from different patients. The underlying assumption is that inter-patient motion variations resemble patient-specific inter-fraction motion variations for subpopulations of patients with similar breathing characteristics. The hypothesis is tested by integrating a sparse manifold clustering approach into a regression-based correspondence modelling framework that allows for automated identification of patient subpopulations. The evaluation is based on a total of 73 lung 4D CT data sets, including two cohorts of patients with repeat 4D CT scans (cohort 1: 14 patients; cohort 2: ten patients). The results are consistent for both cohorts: The subpopulation-based modelling approach outperforms general population modelling (models built on all data sets available) as well as pre-treatment-built models trained on only the patient-specific motion information. The results thereby support the hypothesis and illustrate the potential of subpopulation-based correspondence modelling.

Original languageEnglish (US)
Pages (from-to)5823-5839
Number of pages17
JournalPhysics in Medicine and Biology
Volume62
Issue number14
DOIs
StatePublished - Jun 26 2017

Fingerprint

Four-Dimensional Computed Tomography
Respiration
Cluster Analysis
Radiotherapy
Therapeutics
Lung
Population
Datasets

Keywords

  • motion modeling
  • motion variability
  • radiation therapy
  • spectral clustering

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

Subpopulation-based correspondence modelling for improved respiratory motion estimation in the presence of inter-fraction motion variations. / Wilms, Matthias; Werner, René; Yamamoto, Tokihiro; Handels, Heinz; Ehrhardt, Jan.

In: Physics in Medicine and Biology, Vol. 62, No. 14, 26.06.2017, p. 5823-5839.

Research output: Contribution to journalArticle

@article{f3a1dffd95a2485f8614ef4da9180104,
title = "Subpopulation-based correspondence modelling for improved respiratory motion estimation in the presence of inter-fraction motion variations",
abstract = "Correspondence modelling between low-dimensional breathing signals and internal organ motion is a prerequisite for application of advanced techniques in radiotherapy of moving targets. Patient-specific correspondence models can, for example, be built prior to treatment based on a planning 4D CT and simultaneously acquired breathing signals. Reliability of pre-treatment-built models depends, however, on the degree of patient-specific inter-fraction motion variations. This study investigates whether motion estimation accuracy in the presence of inter-fraction motion variations can be improved using correspondence models that incorporate motion information from different patients. The underlying assumption is that inter-patient motion variations resemble patient-specific inter-fraction motion variations for subpopulations of patients with similar breathing characteristics. The hypothesis is tested by integrating a sparse manifold clustering approach into a regression-based correspondence modelling framework that allows for automated identification of patient subpopulations. The evaluation is based on a total of 73 lung 4D CT data sets, including two cohorts of patients with repeat 4D CT scans (cohort 1: 14 patients; cohort 2: ten patients). The results are consistent for both cohorts: The subpopulation-based modelling approach outperforms general population modelling (models built on all data sets available) as well as pre-treatment-built models trained on only the patient-specific motion information. The results thereby support the hypothesis and illustrate the potential of subpopulation-based correspondence modelling.",
keywords = "motion modeling, motion variability, radiation therapy, spectral clustering",
author = "Matthias Wilms and Ren{\'e} Werner and Tokihiro Yamamoto and Heinz Handels and Jan Ehrhardt",
year = "2017",
month = "6",
day = "26",
doi = "10.1088/1361-6560/aa70cc",
language = "English (US)",
volume = "62",
pages = "5823--5839",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "14",

}

TY - JOUR

T1 - Subpopulation-based correspondence modelling for improved respiratory motion estimation in the presence of inter-fraction motion variations

AU - Wilms, Matthias

AU - Werner, René

AU - Yamamoto, Tokihiro

AU - Handels, Heinz

AU - Ehrhardt, Jan

PY - 2017/6/26

Y1 - 2017/6/26

N2 - Correspondence modelling between low-dimensional breathing signals and internal organ motion is a prerequisite for application of advanced techniques in radiotherapy of moving targets. Patient-specific correspondence models can, for example, be built prior to treatment based on a planning 4D CT and simultaneously acquired breathing signals. Reliability of pre-treatment-built models depends, however, on the degree of patient-specific inter-fraction motion variations. This study investigates whether motion estimation accuracy in the presence of inter-fraction motion variations can be improved using correspondence models that incorporate motion information from different patients. The underlying assumption is that inter-patient motion variations resemble patient-specific inter-fraction motion variations for subpopulations of patients with similar breathing characteristics. The hypothesis is tested by integrating a sparse manifold clustering approach into a regression-based correspondence modelling framework that allows for automated identification of patient subpopulations. The evaluation is based on a total of 73 lung 4D CT data sets, including two cohorts of patients with repeat 4D CT scans (cohort 1: 14 patients; cohort 2: ten patients). The results are consistent for both cohorts: The subpopulation-based modelling approach outperforms general population modelling (models built on all data sets available) as well as pre-treatment-built models trained on only the patient-specific motion information. The results thereby support the hypothesis and illustrate the potential of subpopulation-based correspondence modelling.

AB - Correspondence modelling between low-dimensional breathing signals and internal organ motion is a prerequisite for application of advanced techniques in radiotherapy of moving targets. Patient-specific correspondence models can, for example, be built prior to treatment based on a planning 4D CT and simultaneously acquired breathing signals. Reliability of pre-treatment-built models depends, however, on the degree of patient-specific inter-fraction motion variations. This study investigates whether motion estimation accuracy in the presence of inter-fraction motion variations can be improved using correspondence models that incorporate motion information from different patients. The underlying assumption is that inter-patient motion variations resemble patient-specific inter-fraction motion variations for subpopulations of patients with similar breathing characteristics. The hypothesis is tested by integrating a sparse manifold clustering approach into a regression-based correspondence modelling framework that allows for automated identification of patient subpopulations. The evaluation is based on a total of 73 lung 4D CT data sets, including two cohorts of patients with repeat 4D CT scans (cohort 1: 14 patients; cohort 2: ten patients). The results are consistent for both cohorts: The subpopulation-based modelling approach outperforms general population modelling (models built on all data sets available) as well as pre-treatment-built models trained on only the patient-specific motion information. The results thereby support the hypothesis and illustrate the potential of subpopulation-based correspondence modelling.

KW - motion modeling

KW - motion variability

KW - radiation therapy

KW - spectral clustering

UR - http://www.scopus.com/inward/record.url?scp=85021664054&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021664054&partnerID=8YFLogxK

U2 - 10.1088/1361-6560/aa70cc

DO - 10.1088/1361-6560/aa70cc

M3 - Article

VL - 62

SP - 5823

EP - 5839

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 14

ER -