Population-based Correspondence Models for Respiratory Motion Estimation in the Presence of Interfraction Motion Variations
Standard
Population-based Correspondence Models for Respiratory Motion Estimation in the Presence of Interfraction Motion Variations. / Wilms, Matthias; Werner, Rene; Yamamoto, Tokihiro; Handels, Heinz; Ehrhardt, Jan.
MICCAI workshop on Imaging and Computer Assistance in Radiation Therapy Workshop (ICART). 1. Aufl. 2015. S. 81-88.Publikationen: SCORING: Beitrag in Buch/Sammelwerk › SCORING: Beitrag in Sammelwerk › Forschung › Begutachtung
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Population-based Correspondence Models for Respiratory Motion Estimation in the Presence of Interfraction Motion Variations
AU - Wilms, Matthias
AU - Werner, Rene
AU - Yamamoto, Tokihiro
AU - Handels, Heinz
AU - Ehrhardt, Jan
PY - 2015/10
Y1 - 2015/10
N2 - Many respiratory motion compensation approaches in radiationtherapy of thoracic and abdominal tumors are guided by externalbreathing signals. Patient-specific correspondence models based on planning4D data are used to relate signal measurements to internal motion.The motion estimation accuracy of these models during a treatment fractiondepends on the degree of inter-fraction motion variations. Here, weinvestigate whether motion estimation accuracy in the presence of interfractionmotion variations can be improved by (sub)population models,which incorporate patient-specific motion information and motion datafrom selected additional patients. A sparse manifold clustering approachis integrated into a regression-based correspondence modeling frameworkfor automated identification of subpopulations of patients with similarmotion characteristics. In an evaluation with repeated 4D CT scans of 13patients, subpopulation models, on average, outperform patient-specificcorrespondence models in the presence of inter-fraction motion variations.
AB - Many respiratory motion compensation approaches in radiationtherapy of thoracic and abdominal tumors are guided by externalbreathing signals. Patient-specific correspondence models based on planning4D data are used to relate signal measurements to internal motion.The motion estimation accuracy of these models during a treatment fractiondepends on the degree of inter-fraction motion variations. Here, weinvestigate whether motion estimation accuracy in the presence of interfractionmotion variations can be improved by (sub)population models,which incorporate patient-specific motion information and motion datafrom selected additional patients. A sparse manifold clustering approachis integrated into a regression-based correspondence modeling frameworkfor automated identification of subpopulations of patients with similarmotion characteristics. In an evaluation with repeated 4D CT scans of 13patients, subpopulation models, on average, outperform patient-specificcorrespondence models in the presence of inter-fraction motion variations.
M3 - SCORING: Contribution to collected editions/anthologies
SP - 81
EP - 88
BT - MICCAI workshop on Imaging and Computer Assistance in Radiation Therapy Workshop (ICART)
ER -