Abstract: Abstract: Modern radiotherapy techniques can deliver highly conformal dose distributions, with steep dose gradients between the target and organs at risk. This increases the demands on proper quality assurance and dose verification before (pre-treatment) and during (in vivo) patient irradiation. In this seminar, we present a methodology for EPID-based in vivo dosimetry, combining the accuracy of Monte Carlo (MC) methods for dose simulation in patient geometry, with the time-efficiency of deep neural networks. The Deep Dose Estimation (DDE) 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 radiotherapy plans (irradiation from 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 (irradiation from 90˚) was also created and used for evaluating the performance of the DDE at different beam directions. Promising results demonstrate that the trained DDE is able to convert FODs into ADDs, and predict dose distributions with MC accuracy within 0.6 s (GPU), potentially paving the way towards real-time EPID-based in vivo dosimetry.
Coordinate ZOOM