Prediction of Respiratory Motion with Wavelet-based Multiscale Autoregression

Type of publication:  Artikel in einem Konferenzbericht
Buchtitel: MICCAI 2007, Part II
Serie: Lecture Notes in Computer Science
Band: 4792
Jahr: 2007
Monat: November
Seiten: 668--675
Verlag: Springer
Ort: Brisbane, Australia
Organisation: MICCAI
Notiz: Motion Compensation in Radiosurgery
Querverweis: MICCAI07:
DOI: 10.1007/978-3-540-75759-7\_81
Abriss: In robotic radiosurgery, a photon beam source, moved by a robot arm, is used to ablate tumors. The accuracy of the treatment can be improved by predicting respiratory motion to compensate for system delay. We extend the wavelet-based multiscale autoregressive prediction algorithm by introducing a new exponential averaging parameter and the use of the Moore-Penrose pseudo inverse to cope with long-term signal dependencies and system matrix irregularity, respectively. In test cases, this new algorithm outperforms normalized LMS predictors by as much as 50%. In settings with real data, we achieve an improvement around 5-10%.
Nutzerfelder: owner={ernst}, timestamp={2007.03.30}, file={ess_07.pdf:ess_07.pdf:PDF}
Autoren: Ernst, Floris
Schlaefer, Alexander
Schweikard, Achim
Herausgeber: Ayache, Nicholas
Ourselin, S.
Maeder, A.
  • ess_07.pdf