[1]申璐瑶,魏强林,张俊俊,等.综合复杂性特征和剂量学评估指标提高剂量验证结果预测模型的性能[J].中国医学物理学杂志,2022,39(4):409-414.[doi:DOI:10.3969/j.issn.1005-202X.2022.04.003]
　SHEN Luyao,WEI Qianglin,ZHANG Junjun,et al.Comprehensive index combining plan complexity characteristics and dosimetric evaluation indicators to improve model performance for predicting the results of dose verification[J].Chinese Journal of Medical Physics,2022,39(4):409-414.[doi:DOI:10.3969/j.issn.1005-202X.2022.04.003]
点击复制

综合复杂性特征和剂量学评估指标提高剂量验证结果预测模型的性能()
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4期
页码:
409-414
栏目:
医学放射物理
出版日期:
2022-04-27

文章信息/Info

Title:
Comprehensive index combining plan complexity characteristics and dosimetric evaluation indicators to improve model performance for predicting the results of dose verification
文章编号:
1005-202X（2022）04-0409-06
作者:
申璐瑶1; 魏强林1; 张俊俊2; 宾石珍2; 刘义保1
1.东华理工大学核科学与工程学院， 江西 南昌 330013； 2.中南大学湘雅三医院肿瘤科， 湖南 长沙 410013
Author(s):
SHEN Luyao1;  WEI Qianglin1;  ZHANG Junjun2;  BIN Shizhen2;  LIU Yibao1
1. School of Nuclear Science and Engineering, East China University of Technology, Nanchang 330013, China 2. Department of Oncology, the Third Xiangya Hospital of Central South University, Changsha 410013, China
关键词:
机器学习; 剂量验证; 计划复杂性特征; 剂量学评估指标; 随机森林
Keywords:
Keywords: machine learning dose verification plan complexity characteristic dosimetric evaluation indicator random forest
分类号:
R318；R811.1
DOI:
DOI:10.3969/j.issn.1005-202X.2022.04.003
文献标志码:
A
摘要:
目的：构建随机森林模型预测调强计划剂量验证结果，研究综合复杂性特征和剂量学评估指标提高模型性能的可行性。方法：选取269例IMRT计划，共2 558个射野，采用电子射野影像系统进行剂量验证，γ通过率（2%/2 mm标准）阈值为95%，将剂量验证结果分为“通过”和“不通过”。提取计划的剂量学评估指标和射野的复杂性特征，分别构建剂量模型（基于剂量学评估指标）、计划模型（基于计划复杂性特征）和混合模型（综合剂量学评估指标和计划复杂性特征）。计算AUC值、特异性和敏感性评估模型性能。结果：剂量模型、计划模型和混合模型的AUC值分别为0.68、0.80和0.82，混合模型优于其他两个模型。混合模型的特异性和敏感性为0.70和0.79，均高于其他两个模型。剂量模型、计划模型和混合模型达到最佳性能所需的样本量分别为1 200、900和700。结论：剂量学评估指标与计划复杂性特征综合，可以提高模型的预测性能，同时在一定程度上弥补样本数量的不足，为预测剂量验证结果的机器学习模型性能的改善提供参考。
Abstract:
Abstract: Objective To develop a random forest model for predicting the results of intensity-modulated radiotherapy (IMRT) plan dose verification, and to study the feasibility of improving model performance by integrating plan complexity characteristics and dosimetric evaluation indicators. Methods Electronic portal imaging device was used for the dose verification of 269 IMRT plans with a total of 2 558 fields. The threshold of gamma passing rate (2%/2 mm criterion) was 95%, and there were only two possible outcomes in dose verification, namely pass and fail. The dosimetric evaluation indicators of plans and the complexity characteristics of the radiation fields were extracted for constructing the dose model (based on dosimetric evaluation indicators), planning model (based on plan complexity characteristics) and the hybrid model (comprehensively considering dosimetric evaluation indicators and plan complexity characteristics). The performances of the prediction models were evaluated by AUC, specificity and sensitivity. Results The AUC of the dose model, the planning model and the hybrid model were 0.68, 0.80 and 0.82, respectively, and the hybrid model had the highest AUC. The specificity and sensitivity of the hybrid model were 0.70 and 0.79, both higher than those of the other two models. The number of samples required for the optimal performance of the dose model the planning model and hybrid model were 1 200, 900 and 700, respectively. Conclusion Comprehensively considering dosimetric evaluation indicators and plan complexity characteristics can improve the prediction performance of the model, and at the same time make up for the lack of sample size to a certain extent, providing a reference for improvement of the performance of machine learning model for predicting the results of dose verification.

相似文献/References:

[1]张富利,王雅棣,许卫东,等.应用两种三维探测器阵列进行螺旋断层调强放疗计划剂量验证[J].中国医学物理学杂志,2015,32(02):218.[doi:10.3969/j.issn.1005-202X.2015.02.015]
[2]曾 彪,张九堂,席许平.单中心上下半野调强放射治疗的物理剂量验证[J].中国医学物理学杂志,2015,32(01):17.[doi:10.3969/j.issn.1005-202X.2015.01.005]
[3]任 强,王 玉,曹瑞芬,等.基于非晶硅电子射野影像装置的精确剂量刻度方法[J].中国医学物理学杂志,2015,32(01):38.[doi:10.3969/j.issn.1005-202X.2015.01.010]
[4]刘 浩,王 新,李公平,等.用二维电离室矩阵验证宫颈癌腔内放疗剂量分布[J].中国医学物理学杂志,2014,31(04):4988.[doi:10.3969/j.issn.1005-202X.2014.04.004]
[5]张富利,蒋华勇,王雅棣,等.应用一维、二维、三维探测器阵列进行螺旋断层调强放疗计划剂量验证[J].中国医学物理学杂志,2014,31(06):5230.[doi:10.3969/j.issn.1005-202X.2014.06.002]
[6]易金玲,金献测,周永强,等.鼻咽癌IMRT与VMAT治疗的计划与剂量验证比较研究[J].中国医学物理学杂志,2013,30(01):3859.[doi:10.3969/j.issn.1005-202X.2013.01.006]
[7]方明明,周希法,卢绪菁,等.使用Compass系统进行调强验证的一些探讨[J].中国医学物理学杂志,2013,30(01):3870.[doi:10.3969/j.issn.1005-202X.2013.01.008]
[8]陆佳扬,林珠,陈志坚,等.基于Delta4对Truebeam容积调强放疗(VMAT)计划的验证评估[J].中国医学物理学杂志,2013,30(03):4118.[doi:10.3969/j.issn.1005-202X.2013.03.008]
[9]谭丽娜,孙晓欢,马奎,等.三维剂量验证系统Delta4在容积旋转调强计划剂量验证中的应用[J].中国医学物理学杂志,2013,30(06):4497.[doi:10.3969/j.issn.1005-202X.2013.06.007]
[10]陈上河,王 石,吴朝霞,等.基于蒙特卡罗模拟的CyberKnife病人治疗计划剂量验证[J].中国医学物理学杂志,2015,32(04):451.[doi:10.3969/j.issn.1005-202X.2015.04.001]
　[J].Chinese Journal of Medical Physics,2015,32(4):451.[doi:10.3969/j.issn.1005-202X.2015.04.001]

备注/Memo

备注/Memo:
【收稿日期】2021-12-05 【基金项目】国家重点研发计划（2017YFF0106503）；湖南省自然科学基金青年基金（2020JJ5874） 【作者简介】申璐瑶，硕士研究生，研究方向：医学物理，E-mail: 1208494653@qq.com 【通信作者】刘义保，博士，教授，研究方向：核技术应用，E-mail: ybliu@ecut.edu.cn；宾石珍，硕士，主管技师，研究方向：放射治疗技术，E-mail: shizhenbin@csu.edu.cn
更新日期/Last Update: 2022-04-27