[1]王文成,周解平,张朋,等.基于深度学习方法的食管癌术后调强放疗三维剂量分布预测[J].中国医学物理学杂志,2022,39(2):133-138.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.001]
　WANG Wencheng,ZHOU Jieping,ZHANG Peng,et al.Deep learning-based prediction of three-dimensional dose distribution in postoperative intensity-modulated radiotherapy for esophageal cancer[J].Chinese Journal of Medical Physics,2022,39(2):133-138.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.001]
点击复制

基于深度学习方法的食管癌术后调强放疗三维剂量分布预测()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
39卷
期数:
2022年第2期
页码:
133-138
栏目:
医学放射物理
出版日期:
2022-02-26

文章信息/Info

Title:
Deep learning-based prediction of three-dimensional dose distribution in postoperative intensity-modulated radiotherapy for esophageal cancer
文章编号:
1005-202X（2022）02-0133-06
作者:
王文成1; 周解平2; 张朋2; 吴爱林2; 吴爱东1; 2
1.安徽医科大学生物医学工程学院， 安徽 合肥 230032； 2.中国科学技术大学附属第一医院放疗科， 安徽 合肥230001
Author(s):
WANG Wencheng1;  ZHOU Jieping2;  ZHANG Peng2;  WU Ailin2;  WU Aidong1;  2
1. School of Biomedical Engineering, Anhui Medical University, Hefei 230032, China 2. Department of Radiation Oncology, the First Affiliated Hospital of University of Science and Technology of China, Hefei 230001, China
关键词:
深度学习; 食管癌; 调强放疗; 剂量分布预测
Keywords:
Keywords: deep learning esophageal cancer intensity-modulated radiotherapy dose distribution prediction
分类号:
R735.1；R811.1
DOI:
DOI:10.3969/j.issn.1005-202X.2022.02.001
文献标志码:
A
摘要:
目的：构建一种深度学习网络模型预测食管癌调强放疗的三维剂量分布。方法：取100例中上段食管癌术后患者的调强放疗计划为研究对象，以患者计划的计算机断层扫描（CT）图像、靶区和危及器官的勾画图像以及适形射束信息作为输入数据，调强适形放射治疗（IMRT）的三维剂量分布作为输出数据，通过搭建的3D U-Res-Net混合网络进行训练并得到预测模型，利用该模型对测试集进行三维剂量预测。采用平均预测偏差[δ]、平均绝对误差（MAE）、戴斯相似性系数（DSC）和豪斯多夫距离（HD95）评价预测结果的精确性。结果：测试集的平均预测偏差为-0.23%~0.78%，MAE为1.67%~3.07%，两组计划等剂量面DSC均值大于0.91，尤其30 Gy以下的DSC达到0.95以上，平均HD95为0.51~0.73 cm。预测计划的剂量学参数均在临床允许的范围之内且相对剂量偏差小于2%，除靶区D2、脊髓Dmax、全肺V30差异有统计意义外（P<0.05），其余剂量学参数差别不大。结论：本研究构建的3D U-Res-Net深度学习网络模型可以实现对食管癌术后IMRT三维剂量分布的精确预测。
Abstract:
Abstract: Objective To develop a deep learning network model for predicting the three-dimensional (3D) dose distribution in postoperative intensity-modulated radiotherapy (IMRT) for esophageal cancer. Methods A total of 100 postoperative patients with upper and middle esophageal cancer treated by IMRT were enrolled in the study. The CT images, segmentations of target areas and organs-at-risk, and conformal beam configuration were taken as input data, and IMRT dose distribution was taken as output data. The established hybrid network 3D U-Res-Net was used for training and obtaining prediction model which was then used for the prediction of 3D dose distribution on the test set. The prediction accuracy was evaluated by the average prediction bias [δ], mean absolute error (MAE), Dice similarity coefficient (DSC) and Husdorff distance (HD95). Results For the test set, the average prediction bias ranged from -0.23% to 0.78%, and MAE varied from 1.67% to 3.07%. The average DSC was above 0.91 for all isodose surfaces, especially when the dose was less than 30 Gy (DSC was higher than 0.95), and the average HD95 was from 0.51 cm to 0.73 cm. The dosimetric parameters of the prediction plan were all within the clinically allowable range, and the relative dose deviation was less than 2%. There is no significant difference in dosimetric parameters except for D2 to target area, Dmax to spinal cord and V30 of whole lung (P<0.05). Conclusion The 3D dose distribution in the postoperative intensity-modulated radiotherapy (IMRT) for esophageal cancer can be accurately predicted by the established 3D U-Res-Net model.

相似文献/References:

[1]杨一威,商海焦,单国平,等.两种不同优化算法在胸部肿瘤调强放射治疗计划中的对比研究[J].中国医学物理学杂志,2015,32(02):276.[doi:10.3969/j.issn.1005-202X.2015.02.030]
[2]曾 彪,张九堂,席许平,等.单中心上下半野技术在胸中上段食管癌放射治疗中的剂量学分布[J].中国医学物理学杂志,2015,32(03):357.[doi:10.3969/j.issn.1005-202X.2015.03.012]
[3]陈恩乐,吴 魁,董 事,等.改变多叶准直器角度对调强放疗计划效率的影响[J].中国医学物理学杂志,2015,32(03):437.[doi:10.3969/j.issn.1005-202X.2015.03.030]
[4]宋 威,赵 迪,鹿 红,等.射野方向优化技术在胸中上段食管癌调强放疗中的应用[J].中国医学物理学杂志,2014,31(05):5109.[doi:10.3969/j.issn.1005-202X.2014.05.003]
[5]苏善宁,曾自力.中下段食管癌三维适形放疗不同照射方法对剂量分布的影响[J].中国医学物理学杂志,2014,31(06):5249.[doi:10.3969/j.issn.1005-202X.2014.06.006]
[6]陈杨生.食管癌放射治疗胸部组织校正与否对剂量学影响的研究[J].中国医学物理学杂志,2013,30(05):4360.[doi:10.3969/j.issn.1005-202X.2013.05.005]
[7]刘苓苓,费振乐,李兵兵,等.个性化选择食管癌放疗技术[J].中国医学物理学杂志,2016,33(3):243.[doi:1005-202X（2016）03-0243-05]
　[J].Chinese Journal of Medical Physics,2016,33(2):243.[doi:1005-202X（2016）03-0243-05]
[8]陶源,王佳飞,杜俊龙,等.基于卷积神经网络的细胞识别[J].中国医学物理学杂志,2017,34(1):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
　[J].Chinese Journal of Medical Physics,2017,34(2):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
[9]邵凯南,杜锋磊,李剑龙.RayArc在胸部旋转调强放射治疗计划设计中的应用[J].中国医学物理学杂志,2017,34(2):131.[doi:10.3969/j.issn.1005-202X.2017.02.005]
　Application of RayArc in volumetric modulated arc therapy planning of chest cancer[J].Chinese Journal of Medical Physics,2017,34(2):131.[doi:10.3969/j.issn.1005-202X.2017.02.005]
[10]王庆章,段天宇,刘建超,等.Monaco与Pinnacle治疗计划系统在食管癌放疗剂量验证上的比较[J].中国医学物理学杂志,2017,34(2):166.[doi:10.3969/j.issn.1005-202X.2017.02.011]
　Comparison of Monaco and Pinnacle treatment planning systems on the dosimetric verification of radiotherapy for esophageal cancer[J].Chinese Journal of Medical Physics,2017,34(2):166.[doi:10.3969/j.issn.1005-202X.2017.02.011]

备注/Memo

备注/Memo:
【收稿日期】2021-07-19 【基金项目】国家自然科学基金青年基金（11805198）；安徽省学术和技术带头人后备人选科研项目（2020H230） 【作者简介】王文成，在读硕士，研究方向：肿瘤放射物理，E-mail: 13155337320@163.com 【通信作者】吴爱东，博士，正高级工程师，研究方向：肿瘤放射物理，E-mail: flkaidongwu@163.com
更新日期/Last Update: 2022-03-06