Background and purposes: To compare the dosimetry for the left-sided breast cancer treatment using five different radiotherapy techniques. Materials and methods: Twenty patients with left sided breast cancer were treated with conservative surgery followed by radiotherapy. They were planned using five different radiotherapy techniques, including: 1) conventional tangential wedge-based fields (TW); 2) field-in-field (FIF) technique; 3) tangential inverse planning intensity-modulated radiation therapy (T-IMRT); 4) multi-field IMRT (M-IMRT); and 5) volumetric modulated arc therapy (VMAT). The CTV, PTV and OARs including the heart, the regions of coronary artery (CA), the contralateral breast, the left and right lung were delineated. The PTV dose was prescribed 50Gy and V_47.5≥95%. Same dose constraint was used for all five plans. The planned volumetric dose of PTV and PRV-OARs were compared and analyzed. Results: Except VMAT (Average V_47.5 was 94.72%±1.2%), all the other four plans were able to meet the V95% (V_47.5) requirement. T-IMRT plan improved the PTV dose homogeneity index (HI) by 0.02 and 0.03 when compared to TW plan and VMAT plan, and decreased the V₅, V₁₀ and V₂₀ of all PRV-OARs. However, the high dose volume (≥ 30Gy) of the PRV-OARs in T-IMRT plan had no statistically significant difference compared with the other two inverse plans. In all five plans, the dose volume of coronary artery area showed a strong correlation to the dose volume of the heart (the correlation coefficients were 0.993, 0.996, 1.000, 0.995 and 0.986 respectively). Conclusion: Compared to other techniques, the T-IMRT technology reduced radiation dose exposure to normal tissues and maintained reasonable target homogeneity, VMAT is not recommended for left-sided breast cancer treatment. In five techniques, the dose-volume histogram (DVH) of the heart can be used to predict the dose-volume histogram (DVH) of the coronary artery.

This study aims to utilize a deep convolutional neural network (DCNN) for synthesized CT image generation based on cone-beam CT (CBCT) and to apply the images to dose calculations for nasopharyngeal carcinoma (NPC). An encoder-decoder 2D U-Net neural network was produced. A total of 70 CBCT/CT paired images of NPC cancer patients were used for training (50), validation (10) and testing (10) datasets. The testing datasets were treated with the same prescription dose (70 Gy to PTVnx70, 68 Gy to PTVnd68, 62 Gy to the PTV62 and 54 Gy to the PTV54). The mean error (ME) and mean absolute error (MAE) for the true CT images were calculated for image quality evaluation of the synthesized CT. The dose-volume histogram (DVH) dose metric difference and 3D gamma pass rate for the true CT images were calculated for dose analysis, and the results were compared with those for the CBCT images (original CBCT images without any correction) and a patient-specific calibration (PSC) method. Compared with CBCT, the range of the MAE for synthesized CT images improved from (60, 120) to (6, 27) Hounsfield units (HU), and the ME improved from (−74, 51) to (−26, 4) HU. Compared with the true CT method, the average DVH dose metric differences for the CBCT, PSC and synthesized CT methods were 0.8% ± 1.9%, 0.4% ± 0.7% and 0.2% ± 0.6%, respectively. The 1%/1 mm gamma pass rates within the body for the CBCT, PSC and synthesized CT methods were 90.8% ± 6.2%, 94.1% ± 4.4% and 95.5% ± 1.6%, respectively, and the rates within the PTVnx70 were 80.3% ± 16.6%, 87.9% ± 19.7%, 98.6% ± 2.9%, respectively. The DCNN model can generate high-quality synthesized CT images from CBCT images and be used for accurate dose calculations for NPC patients. This finding has great significance for the clinical application of adaptive radiotherapy for NPC.

Background: In this study, a deep convolutional neural network (CNN)-based automatic segmentation technique was applied to multiple organs at risk (OARs) depicted in computed tomography (CT) images of lung cancer patients, and the results were compared with those generated through atlas-based automatic segmentation. Materials and methods: An encoder-decoder U-Net neural network was produced. The trained deep CNN performed the automatic segmentation of CT images for 36 cases of lung cancer. The Dice similarity coefficient (DSC), the mean surface distance (MSD) and the 95% Hausdorff distance (95% HD) were calculated, with manual segmentation results used as the standard, and were compared with the results obtained through atlas-based segmentation. Results: For the heart, lungs and liver, both the deep CNN-based and atlas-based techniques performed satisfactorily (average values: 0.87 < DSC < 0.95, 1.8 mm < MSD < 3.8 mm, 7.9 mm < 95% HD <11 mm). For the spinal cord and the oesophagus, the two methods had statistically significant differences. For the atlas-based technique, the average values were 0.54 < DSC < 0.71, 2.6 mm < MSD < 3.1 mm and 9.4 mm < 95% HD <12 mm. For the deep CNN-based technique, the average values were 0.71 < DSC < 0.79, 1.2 mm < MSD <2.2 mm and 4.0 mm < 95% HD < 7.9 mm. Conclusion: Our results showed that automatic segmentation based on a deep convolutional neural network enabled us to complete automatic segmentation tasks rapidly. Deep convolutional neural networks can be satisfactorily adapted to segment OARs during radiation treatment planning for lung cancer patients.

To use a graphic processing unit (GPU) calculation engine to implement a fast 3D pre-treatment dosimetric verification procedure based on an electronic portal imaging device (EPID). The GPU algorithm includes the deconvolution and convolution method for the fluence-map calculations, the collapsed-cone convolution/superposition (CCCS) algorithm for the 3D dose calculations and the 3D gamma evaluation calculations. The results of the GPU-based CCCS algorithm were compared to those of Monte Carlo simulations. The planned and EPID-based reconstructed dose distributions in overridden-to-water phantoms and the original patients were compared for 6 MV and 10 MV photon beams in intensity-modulated radiation therapy (IMRT) treatment plans based on dose differences and gamma analysis. The total single-field dose computation time was less than 8 s, and the gamma evaluation for a 0.1-cm grid resolution was completed in approximately 1 s. The results of the GPU-based CCCS algorithm exhibited good agreement with those of the Monte Carlo simulations. The gamma analysis indicated good agreement between the planned and reconstructed dose distributions for the treatment plans. For the target volume, the differences in the mean dose were less than 1.8%, and the differences in the maximum dose were less than 2.5%. For the critical organs, minor differences were observed between the reconstructed and planned doses. The GPU calculation engine was used to boost the speed of 3D dose and gamma evaluation calculations, thus offering the possibility of true real-time 3D dosimetric verification.

The purpose of this work is to evaluate the performance of applying patient dosimetric information induced by individual uniform-intensity radiation fields in organ-at risk (OAR) dose-volume histogram (DVH) prediction, and extend to DVH prediction of planning target volume (PTV). Ninety nasopharyngeal cancer intensity-modulated radiation therapy (IMRT) plans and 60 rectal cancer volumetric modulated arc therapy (VMAT) plans were employed in this study. Of these, 20 nasopharyngeal cancer cases and 15 rectal cancer cases were randomly selected as the testing data. The DVH prediction was performed using two methods. One method applied the individual dose-volume histograms (IDVHs) induced by a series of fields with uniform-intensity irradiation and the other method applied the distance-to-target histogram and the conformal-plan-dose-volume histogram (DTH + CPDVH). The determination coefficient R² and mean absolute error (MAE) were used to evaluate DVH prediction accuracy. The PTV DVH prediction was performed using the IDVHs. The PTV dose coverage was evaluated using D₉₈, D₉₅, D₁ and uniformity index (UI). The OAR dose was compared using the maximum dose, V₃₀ and V₄₀. The significance of the results was examined with the Wilcoxon signed rank test. For PTV DVH prediction using IDVHs, the clinical plan and IDVHs prediction method achieved mean UI values of 1.07 and 1.06 for nasopharyngeal cancer, and 1.04 and 1.05 for rectal cancer, respectively. No significant difference was found between the clinical plan results and predicted results using the IDVHs method in achieving PTV dose coverage (D_98,D_95,D₁ and UI) for both nasopharyngeal cancer and rectal cancer (p-values ≥ 0.052). For OAR DVH prediction, no significant difference was found between the IDVHs and DTH + CPDVH methods for the R², MAE, the maximum dose, V₃₀ and V₄₀ (p-values ≥ 0.087 for all OARs). This work evaluates the performance of dosimetric information of several individual fields with uniform-intensity radiation for DVH prediction, and extends its application to PTV DVH prediction. The results indicated that the IDVHs method is comparable to the DTH + CPDVH method in accurately predicting the OAR DVH. The IDVHs method quantified the input features of the PTV and showed reliable PTV DVH prediction, which is helpful for plan quality evaluation and plan generation.

The three‐dimensional dose (3D) distribution of intensity‐modulated radiation therapy (IMRT) was verified based on electronic portal imaging devices (EPIDs), and the results were analyzed. Thirty IMRT plans of different lesions were selected for 3D EPID‐based dose verification. The gamma passing rates of the 3D dose verification‐based EPID system (Edose, Version 3.01, Raydose, Guangdong, China) and Delta4 measurements were then compared with treatment planning system (TPS) calculations using global gamma criteria of 5%/3 mm, 3%/3 mm, and 2%/2 mm. Furthermore, the dose–volume histograms (DVHs) for planning target volumes (PTVs) as well as organs at risk (OARs) were analyzed using Edose. For dose verification of the 30 treatment plans, the average gamma passing rates of Edose reconstructions under the gamma criteria of 5%/3 mm, 3%/3 mm, and 2%/2 mm were (98.58 ± 0.93)%, (95.67 ± 1.97)%, and (83.13 ± 4.53)%, respectively, whereas the Delta4 measurement results were (99.14% ± 1.16)%, (95.81% ± 2.88)%, and (84.74% ± 7.00)%, respectively. The dose differences between Edose reconstructions and TPS calculations were within 3% for D_95%, D_98%, and D_mean in each PTV, with the exception that the D_98% of the PTV‐clinical target volume (CTV) in esophageal carcinoma cases was (3.21 ± 2.33)%. However, the larger dose deviations in OARs (such as lens, parotid gland, optic nerve, and spinal cord) can be determined based on DVHs. The difference was particularly obvious for OARs with small volumes; for example, the maximum dose deviation for the lens reached (−6.12 ± 5.28)%. A comparison of the results obtained with Edose and Delta4 indicated that the Edose system could be applied for 3D pretreatment dose verification of IMRT. This system could also be utilized to evaluate the gamma passing rate of each treatment plan. Furthermore, the detailed dose distributions of PTVs and OARs could be indicated based on DVHs, providing additional reliable data for quality assurance in a clinic setting.