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*

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*

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.

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.

Objective To discuss and evaluate the dosimetric characteristics of different plans implementing stereotactic radiotherapy(SRT)for intracranial tumors using Fixed and Iris collimators of CyberKnife VSI.Methods Twenty patients with intracranial tumors were selected and divided into group A with a small target volume(≤30 cm3)and group B with a large target volume(≥30 cm3). There were 10 patients in each group,and the prescribed dose to the target was 21 Gy in 3 fractions. For each patient, two treatment plans were designed using Fixed and Iris collimators. By analyzing the dosimetric parameters such as conformity index(CI),homogeneity index(HI), gradient index(GI), gradient score index(GSI), and organs at risk (OAR),the quality and efficiency of the plans were evaluated in order to discuss the beam characteristics for two sets of collimators. The difference was analyzed with the paired t-test. Results The mean time of Iris plan for delivering was significantly less than that of Fixed plan(group A:P=0.001;group B:P=0.000). In group B,the peripheral dose(20% and 10% of the prescribed dose)volumes of Fixed plan were significantly less than those of Iris plan(P=0.001 and 0.009). For OAR,D minof the visual pathway and D meanor D minof the eyeball in group B were significantly different between Fixed and Iris plans(all P<0.05), while in group A, only D minof the optic chiasm was significantly different between the two plans(P=0.043). For the other parameters of targets,there were no significant differences between Fixed and Iris plans in both groups(all P>0.05). Conclusions Apart from less treatment time in the Iris plan, there are no significant dosimetric differences between the two collimator plans of CyberKnife VSI in treating small intracranial tumor. For the large and complex tumor,although Iris plan meets the requirement for OAR dose constraints,its low-dose volumes are larger than those of Fixed plan. Further studies of the dosimetric characteristics in CyberKnife should be done.

Objective Evaluation of intensity-modulated radiation therapy(IMRT) delivery quality assurance(DQA) using EDOSE software based on accelerator electronic portal imaging device (EPID).Methods Analysed the dose response uniformity correction of EPID imaging plate in different fields and the gamma pass rates about the fields; And compared the calculated parameters of the EDOSE and the Pinnacle planning station.Results The uniformities on the homogeneous region of thefi elds are good after who corrected by EDOSE. The gamma(γ, 3mm/3%) pass rates are in the ideal range. The volume of the organs at risk(OAR) have no statistical signifi cance except the right lung; A part of the parameters have statistical signifi cance.Conclusions The results of the calculation and analysis of EDOSE has a high agreement with the planning system.

Objective: To evaluate the feasibility of hypofractionated intensity-modulated radiation therapy (IMRT) combined with concurrent chemotherapy in patients with locally advanced squamous cell carcinoma of the hypopharynx. Methods:Patients with stageⅢ-ⅣA carcinoma of the hypopharynx were treated with IMRT and cisplatin-based concurrent chemotherapy. Two groups were di-vided according to the prescription dose to the primary gross tumor volume, as follows:Cohort-1 comprised patients who were recruit-ed before February 2013 (70 Gy/33 F and 2.12 Gy/F);and Cohort-2 comprised patients who were recruited since February 2013 (69 Gy/30 F and 2.30 Gy/F). Acute toxicities were evaluated. This study was registered with the number ChiCTR-ONRC-14004240. Results:Between August 2008 and December 2014, a total of 76 patients (35 in Cohort-1 and 41 in Cohort-2) were recruited. No xerostomia of grade 3 and higher was observed in all patients, who showed low incidences of grade 3 skin reaction, oral mucositis, and dysphagia. All patients did not show acute toxicities of higher than grade 4. No statistical differences in acute toxicities were observed between the two cohorts. No statistical difference was observed in acute toxicities between the IMRT techniques. Induction chemotherapy was the inde-pendent prognostic factor for grade 2 xerostomia (P=0.002). Conclusion:The 69 Gy/30 F hypofractionated IMRT was safe and effec-tive in the treatment of locally advanced squamous cell carcinoma of the hypopharynx. Late toxicities and long-term outcome need to be investigated further.