Publikationen Mitarbeiter
- Achim Schweikard
- Ralf Bruder
- Sven Böttger
- Alexander Derksen
- Floris Ernst
- Timo Hackbarth
- Jannis Hagenah
- Felix von Haxthausen
- Svenja Ipsen
- Phillip Jauer
- Nils Rottmann
- Elmar Rückert
- Verónica García Vázquez
- Honghu Xue
Publikationen ehemalige Mitarbeiter
- Mohammed Al-Badri
- Rehman Ansari
- Norbert Binder
- Christoph Bodensteiner
- Robert Dürichen
- Markus Finke
- Fernando Gasca
- Hamid Hadjar
- Maximilian Heinig
- Ivo Kuhlemann
- Nils Rottmann
- Volker Martens
- Lars Matthäus
- Christoph Metzner
- Lukas Ramrath
- Lars Richter
- Alexander Schlaefer
- Osama Shahin
- Birgit Stender
- Patrick Stüber
- Tiberiu Viulet
- Benjamin Wagner
- Christian Wilde
- Tobias Wissel
Controlling motion prediction errors in radiotherapy with relevance vector machine
| Type of publication: | Artikel |
| Zeitschrift: | International Journal of Computer Assisted Radiology and Surgery |
| Jahr: | 2014 |
| Seiten: | in press |
| Notiz: | Motion Compensation in Radiosurgery |
| DOI: | 10.1007/s11548-014-1008-x |
| Abriss: | Purpose: Robotic radiotherapy can precisely ablate moving tumors when time latencies have been compensated. Recently, relevance vector machines (RVM), a probabilistic regression technique, outperformed six other prediction algorithms for respiratory compensation. The method has the distinct advantage that each predicted point is assumed to be drawn from a normal distribution. Second order statistics, the predicted variance, were used to control RVM prediction error during a treatment and to construct hybrid prediction algorithms. Methods: First, the duty cycle and the precision were correlated to the variance by interrupting the treatment if the variance exceeds a threshold. Second, two hybrid algorithms based on the variance were developed, one consisting of multiple RVMs (HYB R V M) and the other of a combination between a wavelet based least mean square algorithm (wLMS) and a RVM (HYB w LM S − R V M). The variance for different motion traces was analyzed to reveal a characteristic variance pattern which gives insight in what kind of prediction errors can be controlled by the variance. Results: Limiting the variance by a threshold resulted in an increased precision with a decreased duty cycle. All hybrid algorithms showed an increased prediction accuracy compared to using only their individual algorithms. The best hybrid algorithm, HYB R V M, can decrease the mean RMSE over all 304 motion traces from 0 .18 mm for a linear RVM to 0 .17 mm. Conclusions: The predicted variance was shown to be an efficient metric to control prediction errors, resulting in a more robust radiotherapy treatment. The hybrid algorithm HYB R V M could be translated to clinical practice. It do es not require further parameters, can b e completely parallelised and easily further extended. |
| Schlagworte: | Computer-assisted radiation therapy, Relevance vector machines, Respiratory motion compensation, Uncertainty measures |
| Autoren: | |
|
Anhänge
|
|
|
|
| [Bib|RIS] | |
|
|
|
