Please use this identifier to cite or link to this item: https://doi.org/10.15480/882.2975
Publisher DOI: 10.1002/mp.14331
Title: Feasibility and analysis of CNN-based candidate beam generation for robotic radiosurgery
Language: English
Authors: Gerlach, Stefan 
Fürweger, Christoph 
Hofmann, Theresa 
Schlaefer, Alexander 
Keywords: beam optimization;machine learning;radiation therapy;robotic radiosurgery;treatment planning
Issue Date: 16-Jun-2020
Publisher: Wiley
Source: Medical Physics 9 (47): 3806-3815 (2020-09-01)
Journal or Series Name: Medical physics 
Abstract (english): Purpose: Robotic radiosurgery offers the flexibility of a robotic arm to enable high conformity to the target and a steep dose gradient. However, treatment planning becomes a computationally challenging task as the search space for potential beam directions for dose delivery is arbitrarily large. We propose an approach based on deep learning to improve the search for treatment beams. Methods: In clinical practice, a set of candidate beams generated by a randomized heuristic forms the basis for treatment planning. We use a convolutional neural network to identify promising candidate beams. Using radiological features of the patient, we predict the influence of a candidate beam on the delivered dose individually and let this prediction guide the selection of candidate beams. Features are represented as projections of the organ structures which are relevant during planning. Solutions to the inverse planning problem are generated for random and CNN-predicted candidate beams. Results: The coverage increases from 95.35% to 97.67% for 6000 heuristically and CNN-generated candidate beams, respectively. Conversely, a similar coverage can be achieved for treatment plans with half the number of candidate beams. This results in a patient-dependent reduced averaged computation time of 20.28%–45.69%. The number of active treatment beams can be reduced by 11.35% on average, which reduces treatment time. Constraining the maximum number of candidate beams per beam node can further improve the average coverage by 0.75 percentage points for 6000 candidate beams. Conclusions: We show that deep learning based on radiological features can substantially improve treatment plan quality, reduce computation runtime, and treatment time compared to the heuristic approach used in clinics.
URI: http://hdl.handle.net/11420/7545
DOI: 10.15480/882.2975
ISSN: 0094-2405
Institute: Medizintechnische Systeme E-1 
Type: (wissenschaftlicher) Artikel
Funded by: This work was partially funded by Deutsche Forschungsgemeinschaft (grant SCHL 1844/3-1).
Project: Robotisierte Ultraschall-gestützte Bildgebung zur Echtzeit-Bewegungskompensation in der Strahlentherapie (RobUST) 
License: CC BY 4.0 (Attribution) CC BY 4.0 (Attribution)
Appears in Collections:Publications with fulltext

Files in This Item:
File Description SizeFormat
mp.14331.pdfVerlags-PDF652,81 kBAdobe PDFThumbnail
View/Open
Show full item record

Google ScholarTM

Check

Note about this record

Export

This item is licensed under a Creative Commons License Creative Commons