No abstract

Background and Objective: Delineation of the clinical target volume (CTV) and organs at risk (OARs) is very important for radiotherapy but is time-consuming and prone to inter- and intra-observer variation. We trained and evaluated a U-Net-based model to provide fast and consistent auto-segmentation for breast cancer radiotherapy. Methods: We collected 160 patients’ computed tomography (CT) scans with early-stage breast cancer who underwent breast-conserving surgery (BCS) and were treated with radiotherapy in our center. CTV and OARs (contralateral breast, heart, lungs and spinal cord) were delineated manually by two experienced radiation oncologists. The data were used for model training and testing. The dice similarity coefficient (DSC) and 95th 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. The contours were randomly distributed to two clinicians to compare CTV score differences. The consistency between two clinicians was tested. We also evaluated time cost for auto-delineation. 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 4.31 mm, 3.59 mm, 4.86 mm, 3.18 mm, 2.79 mm and 4.37 mm for the above structures respectively. The average CTV scores for AI and GT were 2.92 versus 2.89 when evaluated by oncologist A (P=.612), and 2.75 versus 2.83 by oncologist B (P=.213), with no statistically significant differences. The consistency between two clinicians was poor (Kappa=0.282). The times for auto-segmentation of CTV and OARs were 3.88 s and 6.15 s. Conclusions: Our proposed model can improve the speed and accuracy of delineation compared with U-Net, while it performed equally well with the segmentation generated by oncologists.

Purpose Clinical target volumes (CTV) and organs at risk (OAR) could be auto-contoured to save workload. The goal of this study was to assess a convolutional neural network (CNN) for totally automatic and accurate CTV and OAR in prostate cancer, while also comparing anticipated treatment plans based on auto-contouring CTV to clinical plans. Methods From January 2013 to January 2019, 217 computed tomography (CT) scans of patients with locally advanced prostate cancer treated at our hospital were collected and analyzed. CTV and OAR were delineated with a deep learning based method, which named CUNet. The performance of this strategy was evaluated using the mean Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD), and subjective evaluation. Treatment plans were graded using predetermined evaluation criteria, and % errors for clinical doses to the planned target volume (PTV) and organs at risk(OARs) were calculated. Results The defined CTVs had mean DSC and 95HD values of 0.84 and 5.04 mm, respectively. For one patient's CT scans, the average delineation time was less than 15 seconds. When CTV outlines from CUNetwere blindly chosen and compared to GT, the overall positive rate in clinicians A and B was 53.15% vs 46.85%, and 54.05% vs 45.95%, respectively (P>0.05), demonstrating that our deep machine learning model performed as good as or better than human demarcation Furthermore, 8 testing patients were chosen at random to design the predicted plan based on the auto-courtoring CTV and OAR, demonstrating acceptable agreement with the clinical plan: average absolute dose differences of D2, D50, D98, Dmean for PTV are within 0.74%, and average absolute volume differences of V45, V50 for OARs are within 3.4%. Without statistical significance (p>0.05), the projected findings are comparable to clinical truth. Conclusion The experimental results show that the CTV and OARs defined by CUNet for prostate cancer were quite close to the ground reality.CUNet has the potential to cut radiation oncologists' contouring time in half. When compared to clinical plans, the differences between estimated doses to CTV and OAR based on auto-courtoring were small, with no statistical significance, indicating that treatment planning for prostate cancer based on auto-courtoring has potential.

Background With the advances of radiation technology, treatment of oligometastatic disease, with limited metastatic burden, have more chances to achieve long-term local control. Here we aim to evaluate the efficacy and safety of radiotherapy (RT) in oligometastatic ovarian cancer patients. Methods A retrospective analysis collecting 142 patients (189 lesions) with oligometastatic ovarian cancer were included in the study. All pateints received radiotherapy and the curative effect and response rate were evaluated by diagnostic imaging after 1–3 months of radiotherapy with RECIST. Endpoints were the rate of complete response (CR), chemotherapy-free interval (CFI), local control (LC) rate and overall survival (OS) rate. Toxicity was evaluated by the Radiation Therapy Oncology Group (RTOG). Logistic and Cox regression were used for the uni- and multivariate analysis of factors influencing survival outcomes. Results From 2013.1.1 to 2020.12.30, a total of 142 ovarian cancer patients (189 oligometastasis lesions) were included in the analysis. Prescribed doses to an average GTV of 3.10 cm were 1.8–8 Gy/fraction, median BED (28–115, a/b = 10 Gy), 5–28 fractions. For 179 evaluable lesions, the cases of CR, partial response (PR), stable disease (SD) and progressive disease (PD) after radiotherapy were 22,39,38 and 80 respectively. The disease control rate (DCR): CR + PR + SD was 55.31%, and the objective response rate (ORR): CR + PR was 34.08%. No patient developed grade 3 or higher side effect. The median CFI was 14 months (1–99 months), and the LC rate was 69.7%, 54.3% and 40.9% in 1 year, 2 years and 5 years respectively. GTV < 3 cm before treatment, platinum sensitivity, time from the last treatment ≥ 6 months, single lesion and BED(a/b = 10 Gy) ≥ 60 are the factors of good LC (p < 0.05). The total OS of 1 year, 2 years and 5 years were 67.1%, 52.6% and 30.3%, respectively. Single lesion (HR 0.598, 95%CI 0.405–0.884), DCR (HR 0.640, 95% CI 0.448–0.918) and ORR(HR 0.466, 95% CI 0.308–0.707) were the significant factors influencing 5-year OS. Conclusion For patients with oligometastatic ovarian cancer, radiotherapy has high LC, long chemotherapy-free interval, and survival benefits. Subgroup analysis shows that patients with single lesion and good local treatment results have higher overall survival rate, suggesting that active treatment is also beneficial for oligometastatic ovarian cancer patients.

Continuous sutures and interrupted sutures have been widely applied to skin closure after non‐obstetric surgery or traumatic wounds. Usually, continuous sutures were divided into transdermal or subcuticular sutures according to whether the stitches were placed through or below the epidermal layer. Interrupted sutures, on the other hand, involved penetration of the loose connective tissue beneath the skin layers, with stitches placed through the external skin layer. Complications including infection, dehiscence, and poor cosmetic appearance were not rare after suturing. Whether a suture method is a suitable option for rapid wound healing and long‐term cosmetic appearance remains controversial. To examine the potential benefits and harms of continuous skin sutures vs interrupted skin sutures in non‐obstetric surgery or traumatic wounds. Searching websites such as PubMed, the Cochrane Central Library, Web of Science and Embase, and http://clinicaltrials.gov were systematically searched up to 5 January 2022 and were assessed and guided by Preferred Reporting Items for Systematic Reviews and Meta‐analysis rules as well as guidelines. All relevant randomised controlled studies comparing continuous sutures with interrupted sutures of skin closure were analysed. The suture techniques and material used in each trial were recorded. The transdermal and subcuticular continuous sutures were separately compared with interrupted sutures in the subgroup analysis of dehiscence and cosmetic appearance because the visual appearance of these two continuous suturing techniques was significantly different. Ten studies including 1181 participants were analysed. Subcuticular continuous sutures had comparatively higher visual analogue scale (VAS) scores among patients and doctors than interrupted sutures (OR = 0.27, 95% Confidence Intervals [CI] = 0. 07‐0.47, P < .01). Similarly, priority was found regarding transdermal continuous sutures and interrupted sutures (OR = 0.40, 95% CI = 0.21‐0.60, P < .01). Five randomised controlled trials (RCTs) demonstrated relevant data about dehiscence events. The incidence of continuous suture was significantly lesser than that of interrupted suture (OR = 0.16, 95% CI = 0.07‐0.37, P < .01). There was no significant difference between the infection events rates of two suture methods (OR = 0.69, 95% CI = 0.40‐1.21, P = .62, I2 = 0%). This systematic review indicated the superiority of both transdermal and subcutaneous continuous sutures over interrupted sutures in skin closure in terms of wound healing and cosmetic appearance.