We introduced and evaluated an end-to-end organs-at-risk (OARs) segmentation model that can provide accurate and consistent OARs segmentation results in much less time. We collected 105 patients' Computed Tomography (CT) scans that diagnosed locally advanced cervical cancer and treated with radiotherapy in one hospital. Seven organs, including the bladder, bone marrow, left femoral head, right femoral head, rectum, small intestine and spinal cord were defined as OARs. The annotated contours of the OARs previously delineated manually by the patient's radiotherapy oncologist and confirmed by the professional committee consisted of eight experienced oncologists before the radiotherapy were used as the ground truth masks. A multi-class segmentation model based on U-Net was designed to fulfil the OARs segmentation task. The Dice Similarity Coefficient (DSC) and 95th Hausdorff Distance (HD) are used as quantitative evaluation metrics to evaluate the proposed method. The mean DSC values of the proposed method are 0.924, 0.854, 0.906, 0.900, 0.791, 0.833 and 0.827 for the bladder, bone marrow, femoral head left, femoral head right, rectum, small intestine, and spinal cord, respectively. The mean HD values are 5.098, 1.993, 1.390, 1.435, 5.949, 5.281 and 3.269 for the above OARs respectively. Our proposed method can help reduce the inter-observer and intra-observer variability of manual OARs delineation and lessen oncologists' efforts. The experimental results demonstrate that our model outperforms the benchmark U-Net model and the oncologists' evaluations show that the segmentation results are highly acceptable to be used in radiation therapy planning.

The delineation of the clinical target volume (CTV) is a crucial, laborious and subjective step in cervical cancer radiotherapy. The aim of this study was to propose and evaluate a novel end-to-end convolutional neural network (CNN) for fully automatic and accurate CTV in cervical cancer. A total of 237 computed tomography (CT) scans of patients with locally advanced cervical cancer were collected and evaluated. A novel 2.5D CNN network, called DpnUNet, was developed for CTV delineation and further applied for CTV and organ-at-risk (OAR) delineation simultaneously. Comprehensive comparisons and experiments were performed. The mean Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD) and subjective evaluation were used to assess the performance of this method. The mean DSC and 95HD values were 0.86 and 5.34mm for the delineated CTVs. The clinical experts' subjective assessments showed that 90% of the predicted contours were acceptable for clinical usage. The mean DSC and 95HD values were 0.91 and 4.05mm for bladder, 0.85 and 2.16mm for bone marrow, 0.90 and 1.27mm for left femoral head, 0.90 and 1.51mm for right femoral head, 0.82 and 4.29mm for rectum, 0.85 and 4.35mm for bowel bag, 0.82 and 4.96mm for spinal cord respectively. The average delineation time for one patient's CT images was within 15 seconds. The experimental results demonstrate that the CTV and OARs delineated for cervical cancer by DpnUNet was in close agreement with the ground truth. DpnUNet could significantly reduce the radiation oncologists' contouring time.

Concurrent chemoradiotherapy (CCRT) is the standard treatment for local advanced cervical cancer. However, for elderly patients, studies are limited and the outcomes are controversial. We retrospectively analyzed the efficacy and tolerance of radical radiotherapy (RT) or CCRT in elderly cervical cancer patients and performed comparisons between them. We retrospectively analyzed the elderly cervical cancer patients (≥70 years old) treated with radical RT or CCRT between January 2006 and December 2014. For external beam radiotherapy, 50Gy in 25 fractions or 50.4Gy in 28 fractions were delivered via 3-dimensional conformal radiation therapy or intensity modulated radiation therapy. High-dose-rate intracavitary brachytherapy was performed with a dose of 30-36Gy in 5–7 fractions to point A. Concurrent chemotherapy regimens included weekly cisplatin and paclitaxel. Seventy-three patients were eligible for this study. Twenty-one(28.8%) and 52(71.2%) patients suffered with FIGO stage IB-IIA and IIB-IVA disease, respectively. Twenty-four (32.9%) patients received CCRT. The median duration of follow-up was 32.4 months (4.8–118.8 months). The 3-year overall survival (OS), cancer-specific survival (CSS) and disease-free survival (DFS) were 64.9%, 67.8% and 66.5%, respectively. By multivariate analysis, CCRT was a significant predictive factor of OS(p = 0.023, 95% confidence interval [CI]: 1.172–8.860), CSS(p = 0.031, 95% CI: 1.131–13.908)and DFS(p = 0.045, 95% CI: 1.023 ~ 6.430). The 3-year OS of patients received RT and CCRT were 54.3% and 83.1%, CSS were 56.8% and 87.1%, DFS were 57.6% and 83.3%. There was no treatment related death. Grade 3–4 acute hematological, gastrointestinal and urinary toxicity incidences were 31.5%, 19.1% and 12.3%, respectively. For grade 3–4 chronic gastrointestinal and genitourinary toxicities, the incidences were 4.1% and 2.7%, respectively. Compared with RT, CCRT was related with high grade 3–4 hematological toxicity (16.3% and 62.5% respectively, p < 0.001), respectively. However, acute nonhematological toxicity and chronic toxicity were not significantly different. Elderly cervical cancer patients could tolerate radical RT and CCRT very well and get a favored survival. Compared with RT, CCRT could improve the survival of elder cervical cancer patients with similar nonhematological toxicity. CCRT should be considered in elderly cervical cancer patients.

Background: Delineation of clinical target volume (CTV) for radiotherapy is a time‐consuming and labor‐intensive work. This study aims to propose a novel convolutional neural network (CNN)‐based model for fast auto‐segmentation of CTV. To evaluate its performance and clinical utility, a blind randomized validation method was used.Methods: Our proposed model was based on the generally accepted U‐Net architecture using computed tomography slices with CTV contours delineated by experienced radiation clinicians from 135 rectal patients receiving neoadjuvant radiotherapy. The Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (95HD) were used to measure segmentation performance. The validated dataset of additional 20 patients for clinical evaluation by 10 experienced oncology clinicians from 7 centers was randomly and blindly divided into two groups for clinicians' scoring and Turing test, respectively. Second evaluation was performed with different randomization after 2 weeks.Results: The mean DSC and 95HD values of the proposed model were 0.90 ± 0.02 and 8.11 ± 1.93 mm for CTV of rectal cancer patients, respectively. The average time for automatic segmentation in the validation groups was 15 s per patient. By clinicians' scoring, the AI model performed better than manually delineating, though the differences were not significant (Week 0: 2.59 vs. 2.52, p = 0.086; Week 2: 2.55 vs. 2.47, p = 0.115). Additionally, the mean positive rates in the Turing test were 40.5% in Week 0 and 45.2% in Week 2, which demonstrated the great intelligence of our model.Conclusions: Our proposed model can be used clinically for assisting contouring of CTVs in rectal cancer patients receiving neoadjuvant radiotherapy, which improves the efficiency and consistency of radiation clinicians' work.

Objective: Delineation of clinical target volume (CTV) and organs at risk (OARs) is important for radiotherapy but is time-consuming. We trained and evaluated a U-ResNet model to provide fast and consistent auto-segmentation. Methods: We collected 160 patients’ CT scans with breast cancer who underwent breast-conserving surgery (BCS) and were treated with radiotherapy. CTV and OARs were delineated manually and were used for model training. The dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (95HD) were used to assess the performance of our model. CTV and OARs were randomly selected as ground truth (GT) masks, and artificial intelligence (AI) masks were generated by the proposed model. Two clinicians randomly compared CTV score differences of the contour. The consistency between two clinicians was tested. Time cost for auto-delineation was evaluated. Results: The mean DSC values of the proposed method were 0.94, 0.95, 0.94, 0.96, 0.96 and 0.93 for breast CTV, contralateral breast, heart, right lung, left lung and spinal cord, respectively. The mean 95HD values were 4.31mm, 3.59mm, 4.86mm, 3.18mm, 2.79mm and 4.37mm for the above structures, respectively. The average CTV scores for AI and GT were 2.89 versus 2.92 when evaluated by oncologist A (P=0.612), and 2.75 versus 2.83 by oncologist B (P=0.213), with no statistically significant differences. The consistency between two clinicians was poor (kappa=0.282). The time for auto-segmentation of CTV and OARs was 10.03 s. Conclusion: Our proposed model (U-ResNet) can improve the efficiency and accuracy of delineation compared with U-Net, performing equally well with the segmentation generated by oncologists.