Purpose Various dose calculation algorithms are available for radiation therapy for cancer patients. However, these algorithms are faced with the tradeoff between efficiency and accuracy. The fast algorithms are generally less accurate, while the accurate dose engines are often time consuming. In this work, we try to resolve this dilemma by exploring deep learning (DL) for dose calculation. Methods We developed a new radiotherapy dose calculation engine based on a modified Hierarchically Densely Connected U‐net (HD U‐net) model and tested its feasibility with prostate intensity‐modulated radiation therapy (IMRT) cases. Mapping from an IMRT fluence map domain to a three‐dimensional (3D) dose domain requires a deep neural network of complicated architecture and a huge training dataset. To solve this problem, we first project the fluence maps to the dose domain using a broad beam ray‐tracing (RT) algorithm, and then we use the HD U‐net to map the RT dose distribution into an accurate dose distribution calculated using a collapsed cone convolution/superposition (CS) algorithm. The model is trained on 70 patients with fivefold cross validation, and tested on a separate 8 patients. Results It takes about 1 s to compute a 3D dose distribution for a typical 7‐field prostate IMRT plan, which can be further reduced to achieve real‐time dose calculation by optimizing the network. The average Gamma passing rate between DL and CS dose distributions for the 8 test patients are 98.5% (±1.6%) at 1 mm/1% and 99.9% (±0.1%) at 2 mm/2%. For comparison of various clinical evaluation criteria (dose‐volume points) for IMRT plans between two dose distributions, the average difference for dose criteria is less than 0.25 Gy while for volume criteria is <0.16%, showing that the DL dose distributions are clinically identical to the CS dose distributions. Conclusions We have shown the feasibility of using DL for calculating radiotherapy dose distribution with high accuracy and efficiency.
Pencil beam (PB) dose calculation is fast but inaccurate due to the approximations when dealing with inhomogeneities. Monte Carlo (MC) dose calculation is the most accurate method but it is time consuming. The aim of this study was to develop a deep learning model that can boost the accuracy of PB dose calculation to the level of MC dose by converting PB dose to MC dose for different tumor sites. The proposed model uses the PB dose and computed tomography image as inputs to generate the MC dose. We used 290 patients (90 head and neck, 93 liver, 75 prostate and 32 lung) to train, validate, and test the model. For each tumor site, we performed four numerical experiments to explore various combinations of training datasets. Training the model on data from all tumor sites together and using the dose distribution of each individual beam as input yielded the best performance for all four tumor sites. The average gamma passing rate (1 mm/1%) between the converted and the MC dose was 92.8%, 92.7%, 89.7% and 99.6% for head and neck, liver, lung, and prostate test patients, respectively. The average dose conversion time for a single field was less than 4 s. The trained model can be adapted to new datasets through transfer learning. Our deep learning-based approach can quickly boost the accuracy of PB dose to that of MC dose. The developed model can be added to the clinical workflow of proton treatment planning to improve dose calculation accuracy.
In radiotherapy, a trade-off exists between computational workload/speed and dose calculation accuracy. Calculation methods like pencil-beam convolution can be much faster than Monte-Carlo methods, but less accurate. The dose difference, mostly caused by inhomogeneities and electronic disequilibrium, is highly correlated with the dose distribution and the underlying anatomical tissue density. We hypothesize that a conversion scheme can be established to boost low-accuracy doses to highaccuracy, using intensity information obtained from computed tomography (CT) images. A deep learning-driven framework was developed to test the hypothesis by converting between two commercially available dose calculation methods: Anisotropic analytic algorithm (AAA) and Acuros XB (AXB). A hierarchically dense U-Net model was developed to boost the accuracy of AAA dose toward the AXB level. The network contained multiple layers of varying feature sizes to learn their dose differences, in relationship to CT, both locally and globally. Anisotropic analytic algorithm and AXB doses were calculated in pairs for 120 lung radiotherapy plans covering various treatment techniques, beam energies, tumor locations, and dose levels. For each case, the CT and the AAA dose were used as the input and the AXB dose as the "ground-truth" output, to train and test the model. The mean squared errors (MSEs) and gamma passing rates (2 mm/2% & 1 mm/1%) were calculated between the boosted AAA doses and the "ground-truth" AXB doses. The boosted AAA doses demonstrated substantially improved match to the "ground-truth" AXB doses, with average (± s.d.) gamma passing rate (1 mm/1%) 97.6% (±2.4%) compared to 87.8% (±9.0%) of the original AAA doses. The corresponding average MSE was 0.11(±0.05) vs 0.31(±0.21). Deep learning is able to capture the differences between dose calculation algorithms to boost the low-accuracy algorithms. By combining a less accurate dose calculation algorithm with a trained deep learning model, dose calculation can potentially achieve both high accuracy and efficiency.
Purpose:To quantify the accuracy in predicting the Bragg peak position using simulated in‐room measurements of prompt gamma (PG) emissions for realistic treatment error scenarios that combine several sources of errors.Methods:Prompt gamma measurements by a knife‐edge slit camera were simulated using an experimentally validated analytical simulation tool. Simulations were performed, for 143 treatment error scenarios, on an anthropomorphic phantom and a pencil beam scanning plan for nasal cavity. Three types of errors were considered: translation along each axis, rotation around each axis, and CT‐calibration errors with magnitude ranging respectively, between −3 and 3 mm, −5 and 5 degrees, and between −5 and +5%. We investigated the correlation between the Bragg peak (BP) shift and the horizontal shift of PG profiles. The shifts were calculated between the planned (reference) position and the position by the error scenario. The prediction error for one spot was calculated as the absolute difference between the PG profile shift and the BP shift.Results:The PG shift was significantly and strongly correlated with the BP shift for 92% of the cases (p<0.0001, Pearson correlation coefficient R>0.8). Moderate but significant correlations were obtained for all cases that considered only CT‐calibration errors and for 1 case that combined translation and CT‐errors (p<0.0001, R ranged between 0.61 and 0.8). The average prediction errors for the simulated scenarios ranged between 0.08±0.07 and 1.67±1.3 mm (grand mean 0.66±0.76 mm). The prediction error was moderately correlated with the value of the BP shift (p=0, R=0.64). For the simulated scenarios the average BP shift ranged between −8±6.5 mm and 3±1.1 mm. Scenarios that considered combinations of the largest treatment errors were associated with large BP shifts.Conclusion:Simulations of in‐room measurements demonstrate that prompt gamma profiles provide reliable estimation of the Bragg peak position for complex error scenarios.Yafei Xing and Luiza Bondar are funded by BEWARE grants from the Walloon Region.The work presents simulations results for a prompt gamma camera prototype developed by IBA.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.