Abstract
A deep-neural-network (DNN) was successfully used to predict clinically-acceptable dose distributions from organ contours for intensity-modulated radiotherapy (IMRT). To provide the next step in the DNN-based plan automation, we propose a DNN that directly generates beam fluence maps from the organ contours and volumetric dose distributions, without inverse planning. We collected 240 prostate IMRT plans and used to train a DNN using organ contours and dose distributions. After training was done, we made 45 synthetic plans (SPs) using the generated fluence-maps and compared them with clinical plans (CP) using various plan quality metrics including homogeneity and conformity indices for the target and dose constraints for organs at risk, including rectum, bladder, and bowel. The network was able to generate fluence maps with small errors. The qualities of the SPs were comparable to the corresponding CPs. The homogeneity index of the target was slightly worse in the SPs, but there was no difference in conformity index of the target, V60Gy of rectum, the V60Gy of bladder and the V45Gy of bowel. The time taken for generating fluence maps and qualities of SPs demonstrated the proposed method will improve efficiency of the treatment planning and help maintain the quality of plans.
Highlights
A deep-neural-network (DNN) was successfully used to predict clinically-acceptable dose distributions from organ contours for intensity-modulated radiotherapy (IMRT)
We compared the generated fluence maps and the dose distribution calculated from the fluence map to the clinical fluence maps and the clinical dose distribution, respectively
Since we only considered the initial treatment in this study, we scaled up the initial 44 Gy dose distribution to the total 72.6 Gy to apply the constraints
Summary
A deep-neural-network (DNN) was successfully used to predict clinically-acceptable dose distributions from organ contours for intensity-modulated radiotherapy (IMRT). To improve the quality of automated plans, some studies have predicted the spatial dose distribution from patient images or contour data[7,8,9]. Those studies predicting DVHs4 or spatial dose distributions[9] by using hand-crafted features from statistical analysis, such as the distance from the target or organs-at-risk (OARs), and the volume of the target and learning-based methods trained by the hand-crafted features. The predicted dose distributions or DVHs were used to identify suboptimal plans or to guide the plan optimisation process, to reduce time consumption and help planners to improve their plans and maintain quality between different planners. It will help to reduce variation between planners and help to maintain the quality of treatment plans
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
