[an error occurred while processing this directive] | [an error occurred while processing this directive]
Study of three-dimensional dose distribution prediction in cervical cancer brachytherapy based on U-Net fully convolutional network
Xiang Yida1, Zhou Jianliang1, Bai Xue2, Wang Binbing2, Shan Guoping2
1School of Nuclear Science and Technology, University of South China, Hengyang 421000, China; 2Department of Radiation Physics, Zhejiang Cancer Hospital, Cancer Hospital of University of Chinese Academy of Sciences, Hangzhou 310022, China
AbstractObjective Topredict the three-dimensional dose distribution of regions of interest (ROI) with brachytherapy for cervical cancer based on U-Net fully convolutional network, and evaluate the accuracy of prediction model. Methods First, 100 cases of cervical cancer intracavity combined with interstitial implantation were selected as the entire research data set, and divided into the training set (n=72), validation set (n=8), and test set (n=20). Then the U-Net was used to construct two models based on whether the uterine tandem and the implantation needles were included as the distinguishing factors. Finally, dose distribution of 20 cases in the test set were predicted using the trained model, and comparative analysis was performed. The performance of the model was jointly evaluated byΔD90%,ΔD2cm3and the mean absolute deviation (MAD). Results Compared with the model without the uterine tandem and the implantation needles,theΔD2cm3of the rectum was increased by (16.83±1.82)cGy (P<0.05), andtheΔD90% or ΔD2cm3of the other ROI were not different significantly (all P>0.05). The MAD of the high-risk clinical target volume, rectum, sigmoid, small bowel, and bladder was increased by (11.96±3.78)cGy,(11.43±0.54)cGy,(24.08±1.65)cGy,(17.04±7.17)cGy and (9.52±4.35)cGy, respectively (all P<0.05). The MAD of the intermediate-risk clinical target volume was decreased by (120.85±29.78)cGy (P<0.05). The mean value of MAD for all ROI was decreased by (7.8±53)cGy (P<0.05), which was closer to the actual plan. Conclusions U-Net fully convolutional network can be used to predict three-dimensional dose distribution of patients with cervical cancer undergoing brachytherapy. Combining the uterine tube with the implantation needles as the input parameters yields more accurate predictions than a single use of the ROI structure as the input.
Xiang Yida,Zhou Jianliang,Bai Xue et al. Study of three-dimensional dose distribution prediction in cervical cancer brachytherapy based on U-Net fully convolutional network[J]. Chinese Journal of Radiation Oncology, 2022, 31(4): 359-364.
Xiang Yida,Zhou Jianliang,Bai Xue et al. Study of three-dimensional dose distribution prediction in cervical cancer brachytherapy based on U-Net fully convolutional network[J]. Chinese Journal of Radiation Oncology, 2022, 31(4): 359-364.
[1] Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2018, 68(6):394-424. DOI:10.3322/caac.21492. [2] Tanderup K, Eifel PJ, Yashar CM, et al. Curative radiation therapy for locally advanced cervical cancer:brachytherapy is not optional[J]. Int J Radiat Oncol Biol Phys, 2014, 88(3):537-539. DOI:10.1016/j.ijrobp.2013.11.011. [3] Han K, Milosevic M, Fyles A, et al. Trends in the utilization of brachytherapy in cervical cancer in the United States[J]. Int J Radiat Oncol Biol Phys, 2013, 87(1):111-119. DOI:10.1016/j.ijrobp.2013.05.033. [4] Chen X, Men K, Li Y, et al. A feasibility study on an automated method to generate patient-specific dose distributions for radiotherapy using deep learning[J]. Med Phys, 2019, 46(1):56-64. DOI:10.1002/mp.13262. [5] 王强,李光俊,宋莹,等. 宫颈癌VMAT计划中OAR的DVH预测价值[J]. 中华放射肿瘤学杂志,2016, 25(8):839-842. DOI:10.3760/cma.j.issn.1004-4221.2016.08.010. Wang Q, Li GJ, Song Y, et al. Predictive value dose-volume histograms of organs at risk in volumetic modulated are therapy plan for cervical cancer[J]. Chin J Radiat Oncol, 2016, 25(8):839-842. DOI:10.3760/cma.j.issn.1004-4221.2016.08.010. [6] 王雪桃,肖江洪,赵建玲,等. 基于RayStation计划系统的宫颈癌容积旋转调强自动计划设计[J]. 中华放射医学与防护杂志, 2018, 38(10):751-755. DOI:10.3760/cma.j.issn.0254-5098.2018.10.006. Wang XT, Xiao JH, Zhao JL, et al. Evaluation of fully automated volumetric modulated arc therapy planning of cervical cancer in RayStation treatment planning system[J]. Chin J Radiol Med Protect, 2018, 38(10):751-755. DOI:10.3760/cma.j.issn.0254-5098.2018.10.006. [7] Damato AL, Viswanathan AN, Cormack RA. Validation of mathematical models for the prediction of organs-at-risk dosimetric metrics in high-dose-rate gynecologic interstitial brachytherapy[J]. Med Phys, 2013, 40(10):101711-101718. DOI:10.1118/1.4819946. [8] Yusufaly TI, Kallis K, Simon A, et al. A knowledge-based organ dose prediction tool for brachytherapy treatment planning of patients with cervical cancer[J]. Brachytherapy, 2020, 19(5):624-634. DOI:10.1016/j.brachy.2020.04.008. [9] Schmid MP, Kirisits C, Nesvacil N, et al. Local recurrences in cervical cancer patients in the setting of image-guided brachytherapy:a comparison of spatial dose distribution within a matched-pair analysis[J]. Radiother Oncol, 2011, 100(3):468-472. DOI:10.1016/j.radonc.2011.08.014. [10] Nguyen D, Jia X, Sher D, et al. 3D radiotherapy dose prediction on head and neck cancer patients with a hierarchically densely connected U-net deep learning architecture[J]. Phys Med Biol, 2019, 64(6):065020. DOI:10.1088/1361-6560/ab039b. [11] 白雪,王升晔,王彬冰,等. 全卷积网络放疗三维剂量分布预测研究[J]. 中华放射肿瘤学杂志,2020, 29(8):666-670. DOI:10.3760/cma.j.cn113030-20191018-00427. Bai X, Wang SY, Wang BB, et al. Study of three-dimensional dose distribution prediction model in radiotherapy planning based on full convolution network[J]. Chin J Radiat Oncol, 2020, 29(8):666-670. DOI:10.3760/cma.j.cn113030-20191018-00427. [12] Ronneberger O, Fischer P, Brox T. U-net Convolutional networks for biomedical image segmentation[C]. Medical image computing and computer-assisted intervention-MICCAI 2015, 2015:234-241. DOI:10.1007/978-3-319-24574-4_28. [13] Appenzoller LM, Michalski JM, Thorstad WL, et al. Predicting dose-volume histograms for organs-at-risk in IMRT planning[J]. Med Phys, 2012, 39(12):7446-7461. DOI:10.1118/1.4761864. [14] 刘忠山,赵杨祉,郭杰,等. CT引导下局部晚期宫颈癌组织间插植近距离治疗剂量学分析[J]. 中华放射肿瘤学杂志,2017, 26(5):550-554. DOI:10.3760/cma.j.issn.1004-4221.2017.05.015. Liu ZS, Zhao YZ, Guo J, et al. CT-guided interstitial brachytherapy for locally advanced cervical cancer:introduction of the technique and report of dosimetry[J]. Chin J Radiat Oncol, 2017, 26(5):550-554. DOI:10.3760/cma.j.issn.1004-4221.2017.05.015. [15] 郑斯明,白玉海,刘晓东,等. CT引导下三管式腔内后装与腔内结合插植后装用于宫颈癌治疗的对比研究[J]. 现代肿瘤学, 2019, 27(22):4077-4080. DOI:10.3969/j.issn.1672-4992.2019.22.033. Zheng SM, Bai YH, Liu XD, et al. A comparative study of the CT-guided three tube intracavitary brachytherapy and intracavitary/interstitial brachytherapy for cervical cancer[J]. Modern Oncol, 2019, 27(22):4077-4080. DOI:10.3969/j.issn.1672-4992.2019.22.033. [16] 王先良,王培,李厨荣,等. 三维后装治疗中一种逆向剂量优化算法[J]. 中华放射肿瘤学杂志,2020, 29(8):676-681. DOI:10.3760/cma.j.cn113030-20180815-00413. Wang XL, Wang P, Li CR, et al. A inverse dose optimization algorithm for three-dimensional brachytherapy[J]. Chin J Radiat Oncol, 2020, 29(8):676-681. DOI:10.3760/cma.j.cn113030-20180815-00413. [17] Zhou ZW, Siddiquee MMR, Tajbakhsh N, et al. U-Net++:redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE Trans Med Imaging, 2020, 39(6):1856-1867. DOI:10.1109/TMI.2019.2959609. [18] Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network[C] Computer vision and pattern recognition. Honolulu:IEEE, 2017:6230-6239. DOI:10.1109/CVPR.2017.660.
2022, Vol. 31 
