全卷积网络放疗三维剂量分布预测研究

doi:10.3760/cma.j.cn113030-20191018-00427

摘要
图/表
参考文献(23)
相关文章 (3)
点击分布统计
下载分布统计

全文: PDF (0 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS) 背景资料

摘要目的研究基于全卷积网络的左侧乳腺癌放疗三维剂量分布预测方法,并对其预测精度进行评估。方法利用全卷积网络实现三维剂量分布预测。首先建立 60例左侧乳腺癌患者的容积调强弧形治疗(VMAT)计划库,从库中随机选取 10例作为测试集数据,其他 50例作为训练集数据;然后,构建U-Net模型,利用该网络在器官结构矩阵和剂量分布矩阵间建立相关模型;最后,利用模型预测测试集病例的剂量分布,并将预测结果与实际计划结果比较。结果 10例测试患者的PTV、患侧肺、心脏、双侧肺、脊髓的剂量平均绝对离差分别为(119.95±9.04)、(214.02±9.04)、(116.23±30.96)、(127.67±69.19)、(37.28±18.66) cGy。处方剂量80%、100%范围计划剂量和预测剂量的Dice相似性指数分别为 0.92±0.01和 0.92±0.01。处方剂量80%和10%范围内区域3mm/3%标准的γ通过率分别为 0.85±0.03、0.84±0.02。结论利用全卷积网络可实现左侧乳腺癌行VMAT患者的三维剂量分布预测。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	白雪
	王升晔
	王彬冰
	张婕
	邵凯南
	杨一威
	单国平
	陈明

关键词 ：全卷积网络, 剂量预测, 乳腺肿瘤/容积调强弧形疗法

Abstract：Objective To explore a three-dimensional dose distribution prediction method for the left breast cancer radiotherapy planning based on full convolution network (FCN), and to evaluate the accuracy of the prediction model. Methods FCN was utilized to achieve three-dimensional dose distribution prediction. First, a volumetric modulated arc therapy (VMAT) plan dataset with 60 cases of left breast cancer was built. Ten cases were randomly chosen from the dataset as the test set, and the remaining 50 cases were used as the training set. Then, a U-Net model was built with the organ structure matrix as inputs and dose distribution matrix as outputs. Finally, the model was adopted to predict the dose distribution of the cases in the test set, and the predicted 3D doses were compared with actual planned results. Results The mean absolute differences of PTV, ipsilateral lung, heart, whole lung and spinal cord for 10 cases were (119.95±9.04) cGy,(214.02±9.04) cGy,(116.23±30.96) cGy,(127.67±69.19) cGy, and (37.28±18.66) cGy, respectively. The Dice similarity coefficient (DSC) of the prediction dose and the planned dose in the 80% and 100% prescription dose range were 0.92±0.01 and 0.92±0.01. The γ rate of 3mm/3% in the area of 80% and 10% prescription dose range were 0.85±0.03 and 0.84±0.02. Conclusion FCN can be used to predict the three-dimensional dose distribution of left breast cancer patients undergoing VMAT.

Key words： Full convolution network Dose prediction Breast neoplasm/volumetric modulated arc therapy

收稿日期: 2019-10-18

基金资助:浙江省重点研发计划(2019C03003);浙江省医药卫生学科平台项目(2018ZD014);浙江省基础公益研究计划(LSY19H180002)

通讯作者: 王升晔,Email:wangsy@zjcc.org.cn

引用本文:

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.

Bai Xue,Wang Shengye,Wang Binbing et al. Study of three-dimensional dose distribution prediction model in radiotherapy planning based on full convolution network[J]. Chinese Journal of Radiation Oncology, 2020, 29(8): 666-670.

链接本文:

http://journal12.magtechjournal.com/Jweb_fszlx/CN/10.3760/cma.j.cn113030-20191018-00427 或 http://journal12.magtechjournal.com/Jweb_fszlx/CN/Y2020/V29/I8/666

[1] Bahm J, Montgomery L. Treatment planning protocols:a method to improve consistency in IMRT planning[J]. Med Dosim, 2011, 36(2):117-118. DOI:10.1016/j.meddos.2010.02.001.
[2] Nelms BE, Robinson G, Markham J, et al. Variation in external beam treatment plan quality:An inter-institutional study of planners and planning systems[J]. Pract Radiat Oncol, 2012, 2(4):296-305. DOI:10.1016/j.prro.2011.11.012.
[3] Nelms BE, Tome WA, Robinson G, et al. Variations in the contouring of organs at risk:test case from a patient with oropharyngeal cancer[J]. Int J Radiat Oncol Biol Phys, 2012, 82(1):368-378. DOI:10.1016/j.ijrobp.2010.10.019.
[4] Reddy NM, Nori D, Chang H, et al. Prostate and seminal vesicle volume based consideration of prostate cancer patients for treatment with 3D-conformal or intensity-modulated radiation therapy[J]. Med Phys, 2010, 37(7):3791-3801. DOI:10.1118/1.3451125.
[5] Moore KL, Brame RS, Low DA, et al. Experience-based quality control of clinical intensity-modulated radiotherapy planning[J]. Int J Radiat Oncol Biol Phys, 2011, 81(2):545-551. DOI:10.1016/j.ijrobp.2010.11.030.
[6] 石翔翔,唐涛,陈斌,等. 鼻咽癌调强放疗中腮腺平均吸收剂量预测模型研究[J]. 肿瘤防治研究,2017,44(4):253-256. DOI:10.3971/j.issn.1000-8578.2017.04.003.
Shi XX, Tang T, Chen B, et al. Prediction model of parotid mean dose in intensity modulated radiation therapy on nasopharyngeal carcinoma[J]. Cancer Res Prev Treat, 2017, 44(4):253-256. DOI:10.3971/j.issn.1000-8578.2017.04.003.
[7] Wu BB, Ricchetti F, Sanguineti G, et al. Patient geometry-driven information retrieval for IMRT treatment plan quality control[J]. Med Phys, 2009, 36(12):5497-5505. DOI:10.1118/1.3253464.
[8] Zhu X, Ge Y, Li T, et al. A planning quality evaluation tool for prostate adaptive IMRT based on machine learning[J]. Med Phys, 2011, 38(2):719-726. DOI:10.1118/1.3539749.
[9] 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.
[10] Yuan LL, Ge YR, Lee WR, et al. Quantitative analysis of the factors which affect the interpatient organ-at-risk dose sparing variation in IMRT plans[J]. Med Phys, 2012, 39(11):6868-6878. DOI:10.1118/1.4757927.
[11] Chao M, Wei J, Narayanasamy G, et al. Three-dimensional cluster formation and structure in heterogeneous dose distribution of intensity modulated radiation therapy[J]. Radiother Oncol, 2018, 127(2):197-205. DOI:10.1016/j.radonc.2018.03.011.
[12] Shiraishi S, Moore KL. Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy[J]. Med Phys, 2016, 43(1):378. DOI:10.1118/1.4938583.
[13] 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.
[14] 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.
[15] Ronneberger O, Fischer P, Brox T. U-Net:convolutional networks for biomedical image segmentation[C]. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 2015:234-41. DOI:10.1007/978-3-319-24574-4_28.
[16] Low DA, Harms WB, Mutic S, et al. A technique for the quantitative evaluation of dose distributions[J]. Med Phys, 1998, 25(5):656-661. DOI:10.1118/1.598248.
[17] Low DA, Dempsey JF. Evaluation of the gamma dose distribution comparison method[J]. Med Phys, 2003, 30(9):2455-2464. DOI:10.1118/1.1598711.
[18] 范嘉伟,王佳舟,胡伟刚. 基于核密度估计的自动计划研究[J]. 中华放射肿瘤学杂志, 2017, 26(6):661-666. DOI:10.3760/cma.j.issn.1004-4221.2017.06.012.
Fan JW, Wang JZ, Hu WG. A study of automatic treatment planning based on kernel density estimation[J]. Chin J Radiat Oncol, 2017, 26(6):661-666. DOI:10.3760/cma.j.issn.1004-4221.2017.06.012.
[19] McIntosh C, Purdie TG. Contextual atlas regression forests:multiple-atlas-based automated dose prediction in radiation therapy[J]. IEEE Trans Med Imaging, 2016, 35(4):1000-1012. DOI:10.1109/TMI.2015.2505188.
[20] Mcintosh C, Welch M, Mcniven A, et al. Fully automated treatment planning for head and neck radiotherapy using a voxel-based dose prediction and dose mimicking method[J]. Phys Med Biol, 2017, 62(15):5926-5944. DOI:10.1088/1361-6560/aa71f8.
[21] Badrinarayanan V, Kendall A, Cipolla R. SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(12):2481-2495. DOI:10.1109/TPAMI.2016.2644615.
[22] Lin G, Milan A, Shen C, et al. RefineNet:multi-path refinement networks for high-resolution semantic segmentation[C]//IEEE. Computer vision and pattern recognition. Honolulu:IEEE, 2017:5168-5177. DOI:10.1109/CVPR.2017.549.
[23] Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network[C]//IEEE. Computer vision and pattern recognition. Honolulu:IEEE, 2017:6230-6239. DOI:10.1109/CVPR.2017.660.