Towards real-time EPID-based 3D in vivo dosimetry for IMRT with Deep Neural Networks: A feasibility study
Physica Medica · 2023-10 · 114 · 103148
DOI: 10.1016/j.ejmp.2023.103148 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physica Medica, 2023-10. Verfasst von Juliana Cristina Martins und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Am Coulombwall 1, Garching b. München, 85748, Germany. Ele…. Hauptthemen laut MEDLINE: Radiotherapy, Intensity-Modulated, In Vivo Dosimetry. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 69 Literaturangaben.
Abstract (Originalsprache)
We investigate the potential of the Deep Dose Estimate (DDE) neural network to predict 3D dose distributions inside patients with Monte Carlo (MC) accuracy, based on transmitted EPID signals and patient CTs. The network was trained using as input patient CTs and first-order dose approximations (FOD). Accurate dose distributions (ADD) simulated with MC were given as training targets. 83 pelvic CTs were used to simulate ADDs and respective EPID signals for subfields of prostate IMRT plans (gantry at 0∘). FODs were produced as backprojections from the EPID signals. 581 ADD-FOD sets were produced and divided into training and test sets. An additional dataset simulated with gantry at 90∘ (lateral set) was used for evaluating the performance of the DDE at different beam directions. The quality of the FODs and DDE-predicted dose distributions (DDEP) with respect to ADDs, from the test and lateral sets, was evaluated with gamma analysis (3%,2 mm). The passing rates between FODs and ADDs were as low as 46%, while for DDEPs the passing rates were above 97% for the test set. Meaningful improvements were also observed for the lateral set. The high passing rates for DDEPs indicate that the DDE is able to convert FODs into ADDs. Moreover, the trained DDE predicts the dose inside a patient CT within 0.6 s/subfield (GPU), in contrast to 14 h needed for MC (CPU-cluster). 3D in vivo dose distributions due to clinical patient irradiation can be obtained within seconds, with MC-like accuracy, potentially paving the way towards real-time EPID-based in vivo dosimetry.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Am Coulombwall 1, Garching b. München, 85748, Germany. Electronic address: Juliana.Martins@physik.uni-muenchen.de.
- German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, Heidelberg, 69120, Germany. Electronic address: joscha.maier@dkfz.de.
- Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Am Coulombwall 1, Garching b. München, 85748, Germany. Electronic address: Chiara.Gianoli@physik.uni-muenchen.de.
- Department of Radiation Oncology, University Hospital, LMU Munich, Marchioninistraße 15, Munich, 81377, Germany. Electronic address: sebastian.neppl@uk-koeln.de.
- Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Am Coulombwall 1, Garching b. München, 85748, Germany. Electronic address: G.Dedes@physik.uni-muenchen.de.
- Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Am Coulombwall 1, Garching b. München, 85748, Germany. Electronic address: Aalhazmi@ksu.edu.sa.
Zitieren
APA
Martins, J. C., Maier, J., Gianoli, C., Neppl, S., Dedes, G., Alhazmi, A., Veloza, S., Reiner, M., Belka, C., Kachelrieß, M., & Parodi, K. (2023). Towards real-time EPID-based 3D in vivo dosimetry for IMRT with Deep Neural Networks: A feasibility study. Physica Medica, 114, 103148. https://doi.org/10.1016/j.ejmp.2023.103148
Vancouver
Martins JC, Maier J, Gianoli C, Neppl S, Dedes G, Alhazmi A, et al. Towards real-time EPID-based 3D in vivo dosimetry for IMRT with Deep Neural Networks: A feasibility study. Physica Medica. 2023;114:103148. doi:10.1016/j.ejmp.2023.103148
BibTeX
@article{Martins2023,
author = {Martins, Juliana Cristina and Maier, Joscha and Gianoli, Chiara and Neppl, Sebastian and Dedes, George and Alhazmi, Abdulaziz and Veloza, Stella and Reiner, Michael and Belka, Claus and Kachelrieß, Marc and Parodi, Katia},
title = {Towards real-time EPID-based 3D in vivo dosimetry for IMRT with Deep Neural Networks: A feasibility study},
journal = {Physica Medica},
year = {2023},
volume = {114},
pages = {103148},
doi = {10.1016/j.ejmp.2023.103148}
}
EUVIMED