Purpose Radiation therapy is an essential treatment modality for cervical cancer, while accurate and efficient segmentation methods are needed to improve the workflow. In this study, a three‐dimensional V‐net model is proposed to automatically segment clinical target volume (CTV) and organs at risk (OARs), and to provide prospective guidance for low lose area. Material and methods A total of 130 CT datasets were included. Ninety cases were randomly selected as the training data, with 10 cases used as the validation data, and the remaining 30 cases as testing data. The V‐net model was implemented with Tensorflow package to segment the CTV and OARs, as well as regions of 5 Gy, 10 Gy, 15 Gy, and 20 Gy isodose lines covered. The auto‐segmentation by V‐net was compared to auto‐segmentation by U‐net. Four representative parameters were calculated to evaluate the accuracy of the delineation, including Dice similarity coefficients (DSC), Jaccard index (JI), average surface distance (ASD), and Hausdorff distance (HD). Results The V‐net and U‐net achieved the average DSC value for CTV of 0.85 and 0.83, average JI values of 0.77 and 0.75, average ASD values of 2.58 and 2.26, average HD of 11.2 and 10.08, respectively. As for the OARs, the performance of the V‐net model in the colon was significantly better than the U‐net model (p = 0.046), and the performance in the kidney, bladder, femoral head, and pelvic bones were comparable to the U‐net model. For prediction of low‐dose areas, the average DSC of the patients’ 5 Gy dose area in the test set were 0.88 and 0.83, for V‐net and U‐net, respectively. Conclusions It is feasible to use the V‐Net model to automatically segment cervical cancer CTV and OARs to achieve a more efficient radiotherapy workflow. In the delineation of most target areas and OARs, the performance of V‐net is better than U‐net. It also offers advantages with its feature of predicting the low‐dose area prospectively before radiation therapy (RT).

Purpose: With the widespread prevalence of Corona Virus Disease 2019 (COVID-19), cancer patients are suggested to wear a surgical mask during radiation treatment. In this study, cone beam CT (CBCT) was used to investigate the effect of surgical mask on setup errors in head and neck radiotherapy. Methods: A total of 91 patients with head and neck tumors were selected. CBCT was performed to localize target volume after patient set up. The images obtained by CBCT before treatment were automatically registered with CT images and manually fine-tuned. The setup errors of patients in 6 directions of Vrt, Lng, Lat, Pitch, Roll and Rotation were recorded. The patients were divided into groups according to whether they wore the surgical mask, the type of immobilization mask used and the location of the isocenter. The setup errors of patients were calculated. A t-test was performed to detect whether it was statistically significant. Results: In the 4 groups, the standard deviation in the directions of Lng and Pitch of the with surgical mask group were all higher than that in the without surgical mask group. In the head-neck-shoulder mask group, the mean in the Lng direction of the with surgical mask group was larger than that of the without surgical mask group. In the lateral isocenter group, the mean in the Lng and Pitch directions of the with surgical mask group were larger than that of the without surgical mask group. The t-test results showed that there was significant difference in the setup error between the 2 groups ( p = 0.043 and p = 0.013, respectively) only in the Lng and Pitch directions of the head-neck-shoulder mask group. In addition, the setup error of 6 patients with immobilization open masks exhibited no distinguished difference from that of the patients with regular immobilization masks. Conclusion: In the head and neck radiotherapy patients, the setup error was affected by wearing surgical mask. It is recommended that the immobilization open mask should be used when the patient cannot finish the whole treatment with a surgical mask.