The dose verification in radiotherapy quality assurance (QA) is time-consuming and places a heavy workload on medical physicists. To provide a clinical tool to perform patient specific QA accurately, the UNet++ is investigated to classify failed or pass fields (the GPR lower than 85% is considered “failed” while the GPR higher than 85% is considered “pass”), predict gamma passing rates (GPR) for different gamma criteria, and predict dose difference from virtual patient-specific quality assurance in radiotherapy. UNet++ was trained and validated with 473 fields and tested with 95 fields. All plans used Portal Dosimetry for dose verification pre-treatment. Planar dose distribution of each field was used as the input for UNet++, with QA classification results, gamma passing rates of different gamma criteria, and dose difference were used as the output. In the test set, the accuracy of the classification model was 95.79%. The mean absolute error (MAE) were 0.82, 0.88, 2.11, 2.52, and the root mean squared error (RMSE) were 1.38, 1.57, 3.33, 3.72 for 3%/3mm, 3%/2 mm, 2%/3 mm, 2%/2 mm, respectively. The trend and position of the predicted dose difference were consistent with the measured dose difference. In conclusion, the Virtual QA based on UNet++ can be used to classify the field passed or not, predict gamma pass rate for different gamma criteria, and predict dose difference. The results show that UNet++ based Virtual QA is promising in quality assurance for radiotherapy.
Purpose The number of dose‐limiting shells in the optimization process is one of the key factors determining the quality of stereotactic body radiotherapy (SBRT) auto‐planning in the Pinnacle treatment planning system (TPS). This study attempted to derive the optimal number of shells by evaluating the auto‐plans designed with different number of shells for peripheral lung cancer patients treated with SBRT. Methods Identical treatment technique, optimization process, constraints, and dose calculation algorithm in the Pinnacle TPS were retrospectively applied to 50 peripheral lung cancer patients who underwent SBRT in our center. For each of the patients, auto‐plans were optimized based on two shells, three shells, four shells, five shells, six shells, seven shells, eight shells, respectively. The optimal number of shells for the SBRT auto‐planning was derived through the evaluations and comparisons of various dosimetric parameters of planning target volume (PTV) and organs at risk (OARs), monitor units (MU), and optimization time of the plans. Results The conformity index (CI) and the gradient index (GI) of PTV, the maximum dose outside the 2 cm of PTV (D2cm), Dmax of spinal cord (SCmax), the percentage of volume of total lung excluding ITV receiving 20 Gy (V20) and 10 Gy (V10), and the mean lung dose (MLD) were improved when the number of shell increased, but the improvement became not significant as the number of shell reached six. The monitor units (MUs) varied little among different plans where no statistical differences were found. However, as the number of shell increased, the auto‐plan optimization time increased significantly. Conclusions It appears that for peripheral lung SBRT plan using six shells can yield satisfactory plan quality with acceptable beam MUs and optimization time in the Pinnacle TPS.
Objective: A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning. Methods: In this paper, a hybrid convolution neural network (CNN) combining 2D CNN and 3D CNN was implemented for the automatic lung tumor delineation using CT images. 3D CNN used V-Net model for the extraction of tumor context information from CT sequence images. 2D CNN used an encoder–decoder structure based on dense connection scheme, which could expand information flow and promote feature propagation. Next, 2D features and 3D features were fused through a hybrid module. Meanwhile, the hybrid CNN was compared with the individual 3D CNN and 2D CNN, and three evaluation metrics, Dice, Jaccard and Hausdorff distance (HD), were used for quantitative evaluation. The relationship between the segmentation performance of hybrid network and the GTV volume size was also explored. Results: The newly introduced hybrid CNN was trained and tested on a dataset of 260 cases, and could achieve a median value of 0.73, with mean and stand deviation of 0.72 ± 0.10 for the Dice metric, 0.58 ± 0.13 and 21.73 ± 13.30 mm for the Jaccard and HD metrics, respectively. The hybrid network significantly outperformed the individual 3D CNN and 2D CNN in the three examined evaluation metrics (p < 0.001). A larger GTV present a higher value for the Dice metric, but its delineation at the tumor boundary is unstable. Conclusions: The implemented hybrid CNN was able to achieve good lung tumor segmentation performance on CT images. Advances in knowledge: The hybrid CNN has valuable prospect with the ability to segment lung tumor.
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.