OBJECTIVE: To analyze the time characteristics of the Ethos online adaptive radiotherapy (OART) process in clinical practice and provide guidance for the comprehensive optimization of each stage of adaptive radiotherapy. METHODS: The study involved 61 patients with cervical, rectal, gastric, lung, esophageal, and breast cancers who underwent Ethos OART. The mean ± standard deviation of segmental time, total time, and target volume for these patients were tracked. The time characteristics for different cancer types were evaluated, and the average time for target and organ at risk (OAR) modifications was compared with the average target volume for each cancer type. RESULTS: Cervical cancer born the longest total treatment time, while breast cancer had the shortest. For all cancer types except breast cancer, the modification time for target and OAR was the most time-consuming segment. The average time for target and OAR modifications aligned with the trend of the average target volume. CONCLUSION The total treatment time for various cancers ranges from 15 to 35 minutes, indicating room for improvement.
Humans ; Radiotherapy Planning, Computer-Assisted/methods* ; Neoplasms/radiotherapy* ; Female

Objective:To assess performance advantages of voxel-less optimization(VoLO)algorithm of CyberKnife-based S7 treatment plan system for the optimization of stereotactic body radiation therapy(SBRT)for liver cancer.Methods:The case data of 20 patients with hepatocellular carcinoma from Chinese PLA General Hospital during June 2022 and April 2023 were retrospectively selected,which included 10 patients with large hepatocellular carcinoma and 10 patients with small hepatocellular carcinoma.All patients adopted respectively sequential optimization(SO)and VoLO to conduct optimization for plan.The optimized quality of plan and execution efficiency of two kinds of algorithms were assessed,and the influences of different tumor volumes also were considered.The planed quality assessment included dosimetric parameters of the target region and organ at risk(OAR).The assessment parameters of execution efficiency included the numbers of monitor units(MUs),nodes and beams,and estimated treatment time.Paired t-test method was adopted to analyze quality of plan and treatment efficiency.Results:On the aspect of the dose of target region,for small hepatocellular carcinoma,the conformity index(CI)value(1.08±0.05)of target region of VoLO algorithm was significantly better than(1.17±0.06)of SO algorithm(t=4.631,P<0.05).The gradient index(GI),coverage rate and dose by 95%(D95%)of VoLO algorithm were better than those of SO algorithm,while the differences were not significant(P>0.05).According to the defined standards of liver surgery,for large hepatocellular carcinoma,the differences in CI,GI,coverage rate and D95%of target region between two kinds of algorithms were significant(t=3.337,4.238,-3.359,-3.311,P<0.05),respectively.On the aspect of dosimetry for OAR,for the target region of large hepatocellular carcinoma,the differences of liver Dmean and D700 cm3 between two kinds of algorithms were significant(t=4.114,3.415,P<0.05).However,for small hepatocellular carcinoma,there was no significant statistical difference in dosimetry parameters of OAR between two kinds of algorithms(P>0.05).The execution efficiency of the plan of VoLO group was obviously higher than that of SO group,and the differences of MU number,node number,beam number and estimated treatment time between two groups were significant(t=12.661,4.423,5.024,9.487,P<0.05).Conclusion:The quality of VoLO plan is significantly better than that of SO,which has a significant improvement in execution efficiency of treatment.For the cases of large hepatocellular carcinoma with more complexity,the VoLO optimization shows better advantages on the aspect of dose on target region,and protection for normal liver.

Objective:To assess performance advantages of voxel-less optimization(VoLO)algorithm of CyberKnife-based S7 treatment plan system for the optimization of stereotactic body radiation therapy(SBRT)for liver cancer.Methods:The case data of 20 patients with hepatocellular carcinoma from Chinese PLA General Hospital during June 2022 and April 2023 were retrospectively selected,which included 10 patients with large hepatocellular carcinoma and 10 patients with small hepatocellular carcinoma.All patients adopted respectively sequential optimization(SO)and VoLO to conduct optimization for plan.The optimized quality of plan and execution efficiency of two kinds of algorithms were assessed,and the influences of different tumor volumes also were considered.The planed quality assessment included dosimetric parameters of the target region and organ at risk(OAR).The assessment parameters of execution efficiency included the numbers of monitor units(MUs),nodes and beams,and estimated treatment time.Paired t-test method was adopted to analyze quality of plan and treatment efficiency.Results:On the aspect of the dose of target region,for small hepatocellular carcinoma,the conformity index(CI)value(1.08±0.05)of target region of VoLO algorithm was significantly better than(1.17±0.06)of SO algorithm(t=4.631,P<0.05).The gradient index(GI),coverage rate and dose by 95%(D95%)of VoLO algorithm were better than those of SO algorithm,while the differences were not significant(P>0.05).According to the defined standards of liver surgery,for large hepatocellular carcinoma,the differences in CI,GI,coverage rate and D95%of target region between two kinds of algorithms were significant(t=3.337,4.238,-3.359,-3.311,P<0.05),respectively.On the aspect of dosimetry for OAR,for the target region of large hepatocellular carcinoma,the differences of liver Dmean and D700 cm3 between two kinds of algorithms were significant(t=4.114,3.415,P<0.05).However,for small hepatocellular carcinoma,there was no significant statistical difference in dosimetry parameters of OAR between two kinds of algorithms(P>0.05).The execution efficiency of the plan of VoLO group was obviously higher than that of SO group,and the differences of MU number,node number,beam number and estimated treatment time between two groups were significant(t=12.661,4.423,5.024,9.487,P<0.05).Conclusion:The quality of VoLO plan is significantly better than that of SO,which has a significant improvement in execution efficiency of treatment.For the cases of large hepatocellular carcinoma with more complexity,the VoLO optimization shows better advantages on the aspect of dose on target region,and protection for normal liver.

Objective:To evaluate the dosimetric characteristics of Zap-X system and CyberKnife (CK) G4 system of stereotactic radiosurgery (SRS) for single brain metastasis.Methods:Twelve patients with single brain metastasis had been treated with CK were selected retrospectively. The prescribed dose of planning target volume (PTV) was 18-24 Gy for 1-3 fractions. The PTV was ranged from 0.44 to 11.52 cm 3. The 12 patients were re-planned in the Zap-X planning system using the same prescription dose and organs at risk constraints, and the prescription dose of PTV was normalized to 70% for both Zap-X and CK. The planning parameters and dosimetric parameters of PTV and organs at risk were compared and evaluated between two plans. All data were read at MIM Maestro. A paired Wilcoxon' signed-rank test was adopted for statistical analysis. A P value of less than 0.05 was considered as statistical significance. Results:For the target coverage, CK was significantly higher than Zap-X (99.14±0.57% vs. 97.55±1.34%, P<0.01), but Zap-X showed a higher conformity index (0.81±0.05 vs. 0.77±0.07, P<0.05), a lower Paddick gradient index (2.98±0.24 vs. 3.15±0.38), and a higher gradient score index (GSI) than CK. The total monitor unit (MU) of Zap-X was significantly lower than that of CK (11 627.63 ±5 039.53 vs. 23 522.16 ±4 542.12, P<0.01) and the treatment time was shorter than that of CK [(25.08 ±6.52) vs. (38.08 ±4.74) min, P<0.01]. Zap-X had lower dose volumes than CK for the dose of brain ( P<0.05). Zap-X had a lower D mean and D max of brainstem (both P<0.05), but a higher value of eyes and lens. For optic nerves and optic chiasm, there were no significant differences between two groups. In addition, for the protection of skin (V 22.5 Gy), Zap-X seemed better than CK [(4.15±4.48) vs. (4.37±4.50) cm 3, P<0.05]. Conclusions:For SRS treating single brain metastasis, Zap-X could provide a high quality plan equivalent to or even better than CK, especially reducing the treatment time. With continuous improvement and upgrading of Zap-X system, it may become a new SRS platform for the treatment of brain metastasis.

Objective:To compare the dosimetric characteristics of beams between Zap-X and G4 CyberKnife and provide reference for clinical application of Zap-X.Methods:PTW three-dimensional water tank and dosimetry diode ionization chamber were used to measure the two orthogonal off-axis ratio and field size at isocenter of 7 different collimators (5 mm, 7.5 mm, 10 mm, 12.5 mm, 15 mm, 20 mm and 25 mm) of Zap-X and CyberKnife at the water depth of maximum dose, 50 mm, 100 mm, and 200 mm. The penumbra, flatness, symmetry and field size under each parameter condition were analyzed by using PTW supporting software PTW MEPHYSTO (version 5.1). Data analysis and graph were performed using Origin 2021 software.Results:With the same collimator, the dose plateau area of Zap-X was wider than that of G4 CyberKnife, and the dose fall-off at the field edge of Zap-X system was faster. With the increase of the collimator, the penumbra of Zap-X and CyberKnife tended to become larger, and the flatness tended to become smaller, the penumbra and flatness of Zap-X were significantly smaller than those of CyberKnife. Both of them had excellent symmetry (<1%), and the symmetry results of CyberKnife (<0.39%) were better than that of Zap-X (0.99%). The accuracy of Zap-X collimator size at isocenter was better than that of CyberKnife.Conclusion:Compared with G4 CyberKnife, Zap-X system has smaller penumbra, better flatness and higher accuracy of collimator size, which is suitable for stereotactic radiosurgery.

CT image based organ segmentation is essential for radiotherapy treatment planning, and it is laborious and time consuming to outline the endangered organs and target areas before making radiation treatment plans. This study proposes a fully automated segmentation method based on fusion convolutional neural network to improve the efficiency of physicians in outlining the endangered organs and target areas. The CT images of 170 postoperative cervical cancer stage IB and IIA patients were selected for network training and automatic outlining of bladder, rectum, femoral head and CTV, and the neural network was used to localize easily distinguishable vessels around the target area to achieve more accurate outlining of CTV.
Female ; Humans ; Image Processing, Computer-Assisted ; Neural Networks, Computer ; Organs at Risk ; Pelvis ; Tomography, X-Ray Computed ; Uterine Cervical Neoplasms/surgery*

When applying deep learning to the automatic segmentation of organs at risk in medical images, we combine two network models of Dense Net and V-Net to develop a Dense V-network for automatic segmentation of three-dimensional computed tomography (CT) images, in order to solve the problems of degradation and gradient disappearance of three-dimensional convolutional neural networks optimization as training samples are insufficient. This algorithm is applied to the delineation of pelvic endangered organs and we take three representative evaluation parameters to quantitatively evaluate the segmentation effect. The clinical result showed that the Dice similarity coefficient values of the bladder, small intestine, rectum, femoral head and spinal cord were all above 0.87 (average was 0.9); Jaccard distance of these were within 2.3 (average was 0.18). Except for the small intestine, the Hausdorff distance of other organs were less than 0.9 cm (average was 0.62 cm). The Dense V-Network has been proven to achieve the accurate segmentation of pelvic endangered organs.
Algorithms ; Humans ; Image Processing, Computer-Assisted ; Imaging, Three-Dimensional ; Neural Networks, Computer ; Organs at Risk ; Pelvis ; Tomography, X-Ray Computed

Objective:To resolve the issue of poor automatic segmentation of the bowel in women with pelvic tumors, a Dense V-Network model was established, trained and evaluated to accurately and automatically delineate the bowel of female patients with pelvic tumors.Methods:Dense Net and V-Net network models were combined to develop a Dense V-Network algorithm for automatic segmentation of 3D CT images. CT data were collected from 160 patients with cervical cancer, 130 of which were randomly selected as the training set to adjust the model parameters, and the remaining 30 were used as test set to evaluate the effect of automatic segmentation.Results:Eight parameters including Dice similarity coefficient (DSC) were utilized to quantitatively evaluate the segmentation effect. The DSC value, JD, ΔV, SI, IncI, HD (cm), MDA (mm), and DC (mm) of the small intestine were 0.86±0.03, 0.25±0.04, 0.10±0.07, 0.88±0.05, 0.85±0.05, 2.98±0.61, 2.40±0.45 and 4.13±1.74, which were better than those of any other single algorithm.Conclusion:Dense V-Network algorithm proposed in this paper can deliver accurate segmentation of the bowel organs. It can be applied in clinical practice after slight revision by physicians.

We use a dense and fully connected convolutional network with good feature learning in small samples, to automatically pre-deline CTV of cervical cancer patients based on CT images and evaluate the effect. The CT data of stage IB and IIA postoperative cervical cancer with similar delineation scope were selected to be used to evaluate the pre-sketching accuracy from three aspects:sketching similarity, sketching offset and sketching volume difference. It has been proved that the 8 most representative parameters are superior to those with single network and reported internationally before. Dense V-Net can accurately predict CTV pre-delineation of cervical cancer patients, which can be used clinically after simple modification by doctors.
Automation ; Female ; Humans ; Machine Learning ; Patients ; Tomography, X-Ray Computed ; Uterine Cervical Neoplasms/diagnostic imaging*

Objective To evaluate the accuracy and validate the feasibility of auto-segmentation based on self-registration and Atlas in adaptive radiotherapy for cervical cancer using MIM-Maestro software.Methods The CT scan images and delineation results of 60 cervical cancer patients were obtained to establish the Atlas template database.The planning CT (pCT) and replanning CT (rCT) images were randomly selected from 15 patients for the contouring of clinical target volume (CTV) and organs at risk (OAR) by an experienced radiation oncologist.The rCT images of 15 patients were auto-contoured using Atlas-based auto-segmentation (Atlas group),and mapping contours from the pCT to the rCT images was performed by rigid and deformable image registration (rigid group and deformable group).The time for the three methods of auto-segmentation was also recorded.The similarity of the auto-contours and reference contours was assessed using dice similarity coefficient (DSC),overlap index (OI),the average hausdorff distance (AHD) and the deviation of centroid (DC),and the results were statistically compared among three groups by using one-way analysis of variance.Results The mean time was 89.2 s,22.4 s and 42.6 s in the Atlas,rigid and deformable groups respectively.The DSC,OI and AHD for the CTV and rectum in the rigid and deformable groups significantly differed from those in the Atlas group (all P＜0.001).In the rigid and deformable groups,the OI for the intestine significantly differed from that in the Atlas group.The mean DSC for CTV was 0.89 in the rigid and deformable groups,and 0.76 in the Atlas group.The optimal delineation of the bladder,pelvis and femoral heads was obtained in the deformable group.Conclusions AIl three methods of auto-segmentation can automatically and rapidly contour the CTV and OARs.The performance in the deformable group is better than that in the rigid and Atlas groups.