[1]梁冰花,孙建伟,陈宏林,等.多区域CT影像组学预测肺癌放射性肺炎[J].中国医学物理学杂志,2025,42(8):1011-1017.[doi:DOI:10.3969/j.issn.1005-202X.2025.08.005]
　LIANG Binghua,SUN Jianwei,CHEN Honglin,et al.CT-based multi-regional radiomics for predicting radiation pneumonitis in lung cancer patients[J].Chinese Journal of Medical Physics,2025,42(8):1011-1017.[doi:DOI:10.3969/j.issn.1005-202X.2025.08.005]
点击复制

多区域CT影像组学预测肺癌放射性肺炎()

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

卷:
42
期数:
2025年第8期
页码:
1011-1017
栏目:
医学影像物理
出版日期:
2025-08-30

文章信息/Info

Title:
CT-based multi-regional radiomics for predicting radiation pneumonitis in lung cancer patients
文章编号:
1005-202X（2025）08-1011-07
作者:
梁冰花1; 孙建伟2; 陈宏林3; 张涛3; 张恒1; 倪昕晔1
1.南京医科大学附属常州第二人民医院放疗科， 江苏 常州 213000； 2.无锡市锡山人民医院肿瘤科， 江苏 无锡 214000； 3.徐州市肿瘤医院放疗科， 江苏 徐州 221000
Author(s):
LIANG Binghua1;  SUN Jianwei2;  CHEN Honglin3;  ZHANG Tao3;  ZHANG Heng1;  NI Xinye1
1. Department of Radiotherapy, Changzhou Second Peoples Hospital, Nanjing Medical University, Changzhou 213000, China 2. Department of Oncology, Xishan Peoples Hospital, Wuxi 214000, China 3. Department of Radiotherapy, Xuzhou Cancer Hospital, Xuzhou 221000, China
关键词:
放射治疗; 影像组学; 肺癌; 放射性肺炎; 靶肺比; 预测模型
Keywords:
radiotherapy radiomics lung cancer radiation pneumonitis target-to-lung ratio prediction model
分类号:
R318；R818.7
DOI:
DOI:10.3969/j.issn.1005-202X.2025.08.005
文献标志码:
A
摘要:
目的：根据定位CT影像中的多区域影像组学分析，建立一个可靠的放射性肺炎（RP）预测模型。方法：回顾性分析徐州市肿瘤医院放疗科2021年1月~2023年6月接受放疗的185例患者资料。根据影像结合临床的诊断结果对患者是否发生RP进行分类。在定位CT图像中定义了3个感兴趣区域（ROI）：全肺（Lung）、去除计划靶区的肺组织（Lung-PTV）和PTV。分别提取3组ROI的影像组学特征，采用曼-惠特尼U检验、递归消除和Lasso等方法筛选特征，并使用支持向量机分类算法建立预测模型。采用受试者工作特征（ROC）曲线下面积（AUC）、准确性、特异性、敏感性、阳性预测值（PPV）和阴性预测值（NPV）这6个评价指标来验证模型的性能。结果：预测模型由7个影像组学特征组成，靶肺比临床模型、PTV模型、Lung模型和Lung-PTV模型在测试集的AUC值分别是0.535、0.801、0.672和0.706。PTV模型在训练集的AUC值为0.843，准确性为0.775；在测试集的AUC值为0.801，准确性为0.750。PTV模型的预测性能优于Lung模型、Lung-PTV模型和靶肺比临床模型。PTV+（Lung-PTV）联合模型在训练集和测试集的AUC值分别为0.867和0.806，高于PTV模型和Lung-PTV模型。结论：不同ROI内影像组学特征构建的预测模型对症状性RP的预测能力不同。使用PTV作为ROI的影像组学预测模型具有更好的预测性能。多区域影像组学联合模型能进一步提高对RP的预测能力。
Abstract:
Abstract: Objective To establish a reliable prediction model for radiation pneumonitis (RP) based on multi-regional radiomics analysis of localizable CT images. Methods A retrospective analysis was conducted on 185 patients who received radiotherapy from January 2021 to June 2023 in the Department of Radiotherapy, Xuzhou Cancer Hospital. Patients were classified as having RP or not based on imaging combined with clinical diagnosis. Three regions of interest (ROI) were defined in the localizable CT images: Lung, Lung-PTV and PTV, and their radiomics features were extracted. After feature screening using methods such as Mann-Whitney U test, recursive feature elimination, and Lasso, a prediction model was established using support vector machine classification algorithm. The model performance was validated using 6 evaluation metrics: the area under the receiver operating characteristic curve (AUC), accuracy, specificity, sensitivity, positive predictive value, and negative predictive value. Results The prediction model consisted of 7 radiomics features. The clinical model of target-to-lung ratio, PTV model, Lung model, and Lung-PTV model achieved AUC values of 0.535, 0.801, 0.672, and 0.706 in the test set, respectively. The AUC value and accuracy of PTV model reached 0.843 and 0.775 in the training set, while 0.801 and 0.750 in the test set. PTV model was superior to Lung model, Lung-PTV model, and clinical model in predictive performance. The AUC values of the combined PTV+ (Lung-PTV) model in the training and test sets were 0.867 and 0.806, respectively, higher than those of PTV model and Lung-PTV model. Conclusion The predictive ability of the prediction models constructed from radiomics features in different ROI for symptomatic RP varies. The radiomics prediction model using PTV as ROI exhibits superior predictive performance, and the combined multi-regional radiomics model can further improve the predictive ability for RP.

相似文献/References:

[1]武 杰,袁杭英,欧阳蓓蕾.内旋式放射治疗用面罩固定装置的设计[J].中国医学物理学杂志,2015,32(02):265.[doi:10.3969/j.issn.1005-202X.2015.02.027]
[2]司 森,吴鑫全,包尚联,等.基于GPU的蒙特卡洛放疗剂量模拟[J].中国医学物理学杂志,2015,32(01):1.[doi:10.3969/j.issn.1005-202X.2015.01.001]
[3]王 文,程梦云,杨 琪,等.基于MCNP源子程序的放射治疗剂量计算验证方法[J].中国医学物理学杂志,2015,32(01):13.[doi:10.3969/j.issn.1005-202X.2015.01.004]
[4]张一戈,邱小平,陈维军,等.基于图像引导技术对头颈部肿瘤临床摆位误差的剂量学影响[J].中国医学物理学杂志,2015,32(01):25.[doi:10.3969/j.issn.1005-202X.2015.01.007]
[5]孟慧鹏,孙小喆,王 昊,等.胸部偏后背肿瘤RapidArc采用仰卧位设计治疗计划的可行性分析[J].中国医学物理学杂志,2015,32(01):31.[doi:10.3969/j.issn.1005-202X.2015.01.008]
[6]庞皓文,孙小扬.基于快速自由形变的弹性配准算法在放疗CT中的应用[J].中国医学物理学杂志,2015,32(03):404.[doi:10.3969/j.issn.1005-202X.2015.03.023]
[7]贾卫娟,周一兵,谭维维,等.利用模拟机及挡铅托架进行放疗前的治疗模拟[J].中国医学物理学杂志,2014,31(01):4622.[doi:10.3969/j.issn.1005-202X.2014.01.007]
[8]白 雪,杜向慧,王升晔,等.半野技术结合非共面照射技术在乳腺癌胸锁联合照射中的应用[J].中国医学物理学杂志,2014,31(03):4849.[doi:10.3969/j.issn.1005-202X.2014.03.001]
[9]周 钢,田 野,陆雪官,等.乳腺癌保乳术后三种瘤床同期加量放疗技术的剂量学比较[J].中国医学物理学杂志,2014,31(03):4853.[doi:10.3969/j.issn.1005-202X.2014.03.002]
[10]李贤富,谢 力,郭飞,等.医科达Precise直线加速器快速应急处理方法探讨[J].中国医学物理学杂志,2014,31(04):4984.[doi:10.3969/j.issn.1005-202X.2014.04.003]
[11]张祥斌,戴谷宇,肖青,等.基于电子射野影像装置通量变化的影像组学特征进行眼突放射治疗摆位误差探测的初步研究[J].中国医学物理学杂志,2021,38(2):153.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.005]
　ZHANG Xiangbin,DAI Guyu,XIAO Qing,et al.Preliminary study of radiomics features of EPID image in detecting setup errors in eye lens radiotherapy[J].Chinese Journal of Medical Physics,2021,38(8):153.[doi:DOI:10.3969/j.issn.1005-202X.2021.02.005]

备注/Memo

备注/Memo:
【收稿日期】2025-01-21 【基金项目】国家自然科学基金（62371243）；江苏省医学重点学科建设单位[肿瘤治疗学(放疗)JSDW202237]；江苏省重点研发计划社会发展项目（BE2022720）；江苏省卫健委面上项目（M2020006）；江苏省自然科学基金（BK20231190）；常州市社会发展项目（CE20235063） 【作者简介】梁冰花，副主任技师，研究方向：放射物理，E-mail: 286079328@qq.com 【通信作者】倪昕晔，博士，研究员，研究方向：放射物理，E-mail: nxy2000@aliyun.com
更新日期/Last Update: 2025-09-13