Objective:To investigate the application of the conjugate gradient (CG) algorithm to treatment plan optimization for intensity-modulated brachytherapy (IMBT).Methods:The general Monte Carlo software TOPAS was utilized to simulate the 192Ir source of IMBT, and the unit dose contribution matrix was calculated. An objective function was established using the weighted least squares method and was solved using the CG algorithm to achieve optimized IMBT treatment plans. The optimization was validated using five clinical cervical cancer cases under modulation width 60°. The dose distributions of IMBT treatment plans under 45°, 60°, 90°, 120°, and 180° modulation widths were compared using the Wilcoxon test to determine the optimal IMBT treatment plan for cervical cancer treatment. Results:The CG algorithm successfully optimized IMBT treatment plans under modulation width 60° for five cases within 22.2 s on average. On the premise of sufficient target dose coverage, the average D2 cm 3 values of the bladder and rectum in IMBT treatment plans were 3.66 and 1.97 Gy, respectively, representing reductions of 0.54 and 0.69 Gy compared to traditional brachytherapy plans. For the five modulation widths, the D90% values of all IMBT treatment plans reached 6 Gy, without statistically significant differences ( P > 0.05). The average D2 cm 3 values of the bladder in IMBT treatment plans were significantly lower than those in the traditional brachytherapy plans( P<0.05), with modulation width 60° associated with the greatest reduction of 0.61 Gy. In contrast, the average D2 cm 3 values of the rectum under 45°, 60°, and 90° modulation widths decreased by 0.63, 0.54, and 0.45 Gy, respectively, compared to traditional plans, with statistically significant differences( P<0.05). Conclusions:The CG method enables rapid achievement of optimized IMBT treatment plans that meet clinical requirements, and modulation width 60° contributes to valid dosimetric optimization. This study can serve as a guide for the clinical implementation of IMBT.

Objective:To rapidly and accurately detect volumetric modulated arc therapy (VMAT) plans with potentially inaccurate radiation doses.Methods:The measurement-based dosimetric verification result of 196 VMAT plans obtained using ArcCHECK phantoms were retrospectively collected. Independent dosimetric calculation and verification were conducted for these plans using the ArcherQA system based on a fast Monte Carlo algorithm. The gamma passing rates of dosimetric verification using ArcCHECK phantom and the ArcherQA system were compared, followed by their correlation analysis and linear regression fitting. The ArcherQA system′s gamma passing rate threshold used to detect positive dosimetric verification result obtained using ArcCHECK phantoms, as well as the specificity of the detection, were calculated. Based on this gamma passing rate threshold, another 50 VMAT plans were selected as a test set to assess the ArcherQA system′s ability to detect positive measurement-based dosimetric verification result.Results:The average gamma passing rates for the dosimetric verification of the VMAT plans using the ArcherQA system and ArcCHECK phantoms were 97.28% and 96.57% (3%/3 mm, TH=10%), respectively. Both rates had a correlation coefficient of 0.71 ( P < 0.01) and a linear fitting coefficient of 0.54 ( R2=0.51). When the gamma passing rate for dosimetric verification using ArcCHECK phantoms was set at 90% (3%/2 mm, TH=10%), the gamma passing rate threshold for dosimetric verification using the ArcherQA system should be adjusted to 94.8% to detect all VMAT plans with positive dosimetric verification result obtained using ArcCHECK phantoms, with a specificity of 67.8%. Using this threshold, the ArcherQA system detected all VMAT plans in the test set for which ArcCHECK phantom-based measurement yielded positive dosimetric verification result. Conclusions:By determining an appropriate gamma passing rate threshold, the ArcherQA system can rapidly and accurately detect VMAT plans with potentially inaccurate doses, thus ensuring treatment accuracy and improving work efficiency.

Stereotactic radiotherapy is widely favored because of its high treatment precision and less fractionations.ZND-A is a new domestic gamma-ray cone-beam focused stereotactic radiotherapy system.Herein the technical characteristics of ZND-A system are described in detail from the aspects of the treatment frame,gamma-ray module,collimator module,six-dimensional treatment couch module and image-guided system module,and the main parameters are compared with the mainstream gamma knife equipments at home and abroad.With reference to Response Evaluation Criteria in Solid Tumors(RECIST 1.1),the initial efficacy of the patients treated by the ZND-A system is analyzed to evaluate the advantages and disadvantages of the ZND-A system for providing a reference for the hospital clinical use of this type of gamma knife.

Objective To develop a deep learning-based denoising model for accelerating Monte Carlo(MC)simulation of electronic portal imaging device(EPID)transit dose images.Methods A total of 500 EPID fields were collected from 100 lung cancer patients undergoing 5-field intensity-modulated radiotherapy,with 400 fields randomly selected as training set,50 fields as validation set,and 50 fields as test set.EPID transit dose image datasets with low particle counts(1×107)and high particle counts(1×109)were simulated using the GPU-accelerated MC dose calculation engine ARCHER.A denoising network model named SUNet was constructed based on Swin Transformer and U-Net,and trained using low-particle-count images as input and high-particle-count images as output.Following training,SUNet model was used to denoise low-particle-count EPID images in the test set.Denoising performance was evaluated using structural similarity index(SSIM),peak signal-to-noise ratio(PSNR),and Gamma passing rates(3%/2 mm),and the computational efficiency of MC simulation combined with SUNet model was analyzed.Results Compared with the original low-particle-count images,the SUNet-denoised images showed significantly improved quality,reduced noise points,and smoother dose distribution.When benchmarked against high-particle-count images,the SUNet-denoised images achieved an average SSIM greater than 0.9,an average PSNR higher than 32 dB,and an average gamma passing rate exceeding 90%.The MC simulation combined with SUNet model required only 1.88 s to simulate a single EPID transit dose image,representing an approximate 40-fold improvement in computational efficiency as compared with high-particle-count MC simulation.Conclusion The deep learning-based denoising model substantially accelerates MC simulation of EPID transit dose images while preserving both image quality and dose accuracy,which provides possibilities for EPID-basedin vivodose verification.

Objective To develop a deep learning-based denoising model for accelerating Monte Carlo(MC)simulation of electronic portal imaging device(EPID)transit dose images.Methods A total of 500 EPID fields were collected from 100 lung cancer patients undergoing 5-field intensity-modulated radiotherapy,with 400 fields randomly selected as training set,50 fields as validation set,and 50 fields as test set.EPID transit dose image datasets with low particle counts(1×107)and high particle counts(1×109)were simulated using the GPU-accelerated MC dose calculation engine ARCHER.A denoising network model named SUNet was constructed based on Swin Transformer and U-Net,and trained using low-particle-count images as input and high-particle-count images as output.Following training,SUNet model was used to denoise low-particle-count EPID images in the test set.Denoising performance was evaluated using structural similarity index(SSIM),peak signal-to-noise ratio(PSNR),and Gamma passing rates(3%/2 mm),and the computational efficiency of MC simulation combined with SUNet model was analyzed.Results Compared with the original low-particle-count images,the SUNet-denoised images showed significantly improved quality,reduced noise points,and smoother dose distribution.When benchmarked against high-particle-count images,the SUNet-denoised images achieved an average SSIM greater than 0.9,an average PSNR higher than 32 dB,and an average gamma passing rate exceeding 90%.The MC simulation combined with SUNet model required only 1.88 s to simulate a single EPID transit dose image,representing an approximate 40-fold improvement in computational efficiency as compared with high-particle-count MC simulation.Conclusion The deep learning-based denoising model substantially accelerates MC simulation of EPID transit dose images while preserving both image quality and dose accuracy,which provides possibilities for EPID-basedin vivodose verification.

Objective:To investigate the application of the conjugate gradient (CG) algorithm to treatment plan optimization for intensity-modulated brachytherapy (IMBT).Methods:The general Monte Carlo software TOPAS was utilized to simulate the 192Ir source of IMBT, and the unit dose contribution matrix was calculated. An objective function was established using the weighted least squares method and was solved using the CG algorithm to achieve optimized IMBT treatment plans. The optimization was validated using five clinical cervical cancer cases under modulation width 60°. The dose distributions of IMBT treatment plans under 45°, 60°, 90°, 120°, and 180° modulation widths were compared using the Wilcoxon test to determine the optimal IMBT treatment plan for cervical cancer treatment. Results:The CG algorithm successfully optimized IMBT treatment plans under modulation width 60° for five cases within 22.2 s on average. On the premise of sufficient target dose coverage, the average D2 cm 3 values of the bladder and rectum in IMBT treatment plans were 3.66 and 1.97 Gy, respectively, representing reductions of 0.54 and 0.69 Gy compared to traditional brachytherapy plans. For the five modulation widths, the D90% values of all IMBT treatment plans reached 6 Gy, without statistically significant differences ( P > 0.05). The average D2 cm 3 values of the bladder in IMBT treatment plans were significantly lower than those in the traditional brachytherapy plans( P<0.05), with modulation width 60° associated with the greatest reduction of 0.61 Gy. In contrast, the average D2 cm 3 values of the rectum under 45°, 60°, and 90° modulation widths decreased by 0.63, 0.54, and 0.45 Gy, respectively, compared to traditional plans, with statistically significant differences( P<0.05). Conclusions:The CG method enables rapid achievement of optimized IMBT treatment plans that meet clinical requirements, and modulation width 60° contributes to valid dosimetric optimization. This study can serve as a guide for the clinical implementation of IMBT.

Objective:To rapidly and accurately detect volumetric modulated arc therapy (VMAT) plans with potentially inaccurate radiation doses.Methods:The measurement-based dosimetric verification result of 196 VMAT plans obtained using ArcCHECK phantoms were retrospectively collected. Independent dosimetric calculation and verification were conducted for these plans using the ArcherQA system based on a fast Monte Carlo algorithm. The gamma passing rates of dosimetric verification using ArcCHECK phantom and the ArcherQA system were compared, followed by their correlation analysis and linear regression fitting. The ArcherQA system′s gamma passing rate threshold used to detect positive dosimetric verification result obtained using ArcCHECK phantoms, as well as the specificity of the detection, were calculated. Based on this gamma passing rate threshold, another 50 VMAT plans were selected as a test set to assess the ArcherQA system′s ability to detect positive measurement-based dosimetric verification result.Results:The average gamma passing rates for the dosimetric verification of the VMAT plans using the ArcherQA system and ArcCHECK phantoms were 97.28% and 96.57% (3%/3 mm, TH=10%), respectively. Both rates had a correlation coefficient of 0.71 ( P < 0.01) and a linear fitting coefficient of 0.54 ( R2=0.51). When the gamma passing rate for dosimetric verification using ArcCHECK phantoms was set at 90% (3%/2 mm, TH=10%), the gamma passing rate threshold for dosimetric verification using the ArcherQA system should be adjusted to 94.8% to detect all VMAT plans with positive dosimetric verification result obtained using ArcCHECK phantoms, with a specificity of 67.8%. Using this threshold, the ArcherQA system detected all VMAT plans in the test set for which ArcCHECK phantom-based measurement yielded positive dosimetric verification result. Conclusions:By determining an appropriate gamma passing rate threshold, the ArcherQA system can rapidly and accurately detect VMAT plans with potentially inaccurate doses, thus ensuring treatment accuracy and improving work efficiency.

Stereotactic radiotherapy is widely favored because of its high treatment precision and less fractionations.ZND-A is a new domestic gamma-ray cone-beam focused stereotactic radiotherapy system.Herein the technical characteristics of ZND-A system are described in detail from the aspects of the treatment frame,gamma-ray module,collimator module,six-dimensional treatment couch module and image-guided system module,and the main parameters are compared with the mainstream gamma knife equipments at home and abroad.With reference to Response Evaluation Criteria in Solid Tumors(RECIST 1.1),the initial efficacy of the patients treated by the ZND-A system is analyzed to evaluate the advantages and disadvantages of the ZND-A system for providing a reference for the hospital clinical use of this type of gamma knife.

Objective: To explore the clinical dosimetry advantages of automated plan of IMRT for postoperative esophageal cancer and the dose prediction accuracy of the constructed 3D U-Res-Net model． Methods: A total of 110 postoperative esophageal cancer (middle and upper) cases treated by IMRT were considered in the study，of which 90 cases were randomly selected for training of deep learning prediction model．The deep learning prediction model and Auto-Plan module ( Philips pinnacle3 16. 2 ) were used to predict the three-dimension dose distribution and redesigned the remaining 20 cases respectively ，and the results obtained were compared with manual plan. Results : The average DSC value between the deep learning prediction plan and the manual plan was greater than 0. 92 in isodose surface，and the average Hausdorff distance HD95 of the isodose surface was 0. 58－0. 62 cm ; The V20 ，V30 ，Dmean of total lung were slightly lower than those of manual plan (P ＜0. 05 ) for the prediction model， meanwhile，the D2 ，D50 ，Dmean，HI of the target area and V30 of total lungs were better than those of manual plan(P ＜0. 05) for Auto-Plan ; Three-dimensional dose distribution of the three groups and the corresponding DVH curve showed that the three-dimensional dose distribution of the three groups had a little differences，and the DVH curves of the target area and organs at risk had a good agreement． Conclusion Auto-Plan can realize the design of automated plan for postoperative esophageal cancer，while the deep learning prediction model can realize the accurate prediction of the 3D dose distribution.

Objective:To propose a deep learning network model 2D-PE-GAN to automatically delineate the target area of nasopharyngeal carcinoma and improve the efficiency of target area delineation.Methods:The model adopted the architecture of generative adversarial networks which used a UNet similar structure as the generator, and 2D-PE-block was added after each layer of convolution operation of the generator to improve the accuracy of delineation. The experimental data included CT images from 130 cases of nasopharyngeal carcinoma. The images were preprocessed before model training. In addition, three models of UNet, GAN, and GAN with an attention mechanism were compared, and Dice similarity coefficient, Hausdorff distance, accuracy, Matthews correlation coefficient, Jaccard distance were employed to evaluate network performance.Results:Compared with UNet, GAN and GAN with the attention mechanism, the average Dice similarity coefficient of 2D-PE-GAN network segmentation of CTV was increased by 26%, 4% and 2%. The average Dice similarity coefficient of GTV segmentation was increased by 21%, 4%, 2%, respectively. Compared with the GAN network with the attention mechanism, the parameters and time of 2D-PE-GAN were reduced by 0.16% and 18%, respectively.Conclusions:Compared with the above three networks, 2D-PE-GAN network can increase the segmentation accuracy of nasopharyngeal carcinoma target area delineation. At the same time, compared with the attention mechanism with similar reasons, 2D-PE-GAN network can reduce the occupation of computing resources when the segmentation accuracy is not much different.