| 王寻,卞婷婷,丁强,等.基于多维数据的机器学习方法预测非小细胞肺癌患者放射性肺炎的研究[J].中华放射医学与防护杂志,2025,45(8):774-781.Wang Xun,Bian Tingting,Ding Qiang,et al.Predicting radiation pneumonia in patients with non-small cell lung cancer using a machine learning method based on multidimensional data[J].Chin J Radiol Med Prot,2025,45(8):774-781 |
| 基于多维数据的机器学习方法预测非小细胞肺癌患者放射性肺炎的研究 |
| Predicting radiation pneumonia in patients with non-small cell lung cancer using a machine learning method based on multidimensional data |
| 投稿时间：2024-08-31 |
| DOI：10.3760/cma.j.cn112271-20240831-00330 |
| 中文关键词: 非小细胞肺癌 影像组学 剂量组学 放射性肺炎 |
| 英文关键词:Non-small cell lung cancer Radiomics Dosiomics Radiation pneumonitis |
| 基金项目:济宁市重点研发计划项目(2023YXNS052);山东省医药卫生科技项目(202203100691,202409030221);济宁医学院贺林院士新医学临床转化工作站科研基金(JYHL2022FZD01);山东省医学会临床科研资金齐鲁专项(YXH2022ZX02209) |
| 作者 | 单位 | E-mail | | 王寻 | 济宁医学院附属医院医学影像科, 济宁 272000 | | | 卞婷婷 | 济宁医学院附属医院医学影像科, 济宁 272000 | | | 丁强 | 菏泽医学专科学校附属医院肿瘤科, 菏泽 274009 | | | 葛双 | 济宁医学院附属医院肿瘤放疗科, 济宁 272000 | | | 张爱平 | 济宁肿瘤医院物理室, 济宁 272004 | | | 韩心舒 | 济宁医学院临床学院, 济宁 272000 | | | 陈月芹 | 济宁医学院附属医院医学影像科, 济宁 272000 | | | 叶书成 | 济宁医学院附属医院肿瘤放疗科, 济宁 272000 | | | 张谷青 | 济宁医学院附属医院医学影像科, 济宁 272000 | | | 马俊丽 | 济宁医学院附属医院肿瘤放疗科, 济宁 272000 | majl2015@yeah.net |
|
| 摘要点击次数: 346 |
| 全文下载次数: 196 |
| 中文摘要: |
| 目的 建立并验证基于定位CT和剂量学图像的影像组学、剂量组学结合临床参数的联合模型,预测非小细胞肺癌(NSCLC)患者放射性肺炎的发生。方法 回顾性收集济宁医学院附属医院2016年1月至2022年12月接受放射治疗的143例NSCLC患者临床资料,并按照7∶3随机分层分为训练组(100例)和内部验证组(43例)。另外收集来自济宁肿瘤医院2019年1月至2022年12月接受放射治疗的34例NSCLC患者临床资料作为外部验证组。训练组、内部验证组和外部验证组又根据放射性肺炎(RP)的严重程度进一步分为≥2级RP组和＜2级RP组,收集放疗剂量、定位CT及三维剂量图像。将全肺-PTV作为感兴趣区进行影像组学及剂量组学特征提取并进行特征降维,筛选出放射性肺炎关键特征,通过机器学习方法(MLP)建立临床模型(CM)、影像组学模型(RM)、剂量组学模型(DM)以及三者的联合模型(RDN)并绘制列线图,使用受试者工作特征(ROC)曲线下面积(AUC)和决策曲线(DCA)评估模型性能及临床适用性。结果 共提取1 834个影像组学特征及1 834个剂量组学特征,以是否发生≥2级RP为标签变量,在训练组中最终筛选出14个影像组学特征、15个剂量组学特征和3个临床特征用于构建预测模型(CM、RM、DM、RDN),并在内部验证组和外部验证组中验证模型性能与泛化能力。RDN在训练组、内部验证组及外部验证组中的AUC分别为0.915(95%CI: 0.852~0.978)、0.879(95%CI: 0.777~0.982)及0.838(95%CI: 0.701~0.975)。结合影像组学分值(R-score)、剂量组学分值(D-score)、肺平均剂量(MLD)、V20和V30绘制联合模型列线图,可实现个体化风险预测,有助于指导个体化放疗策略的制定。结论 基于定位CT和三维剂量图像,结合影像组学、剂量组学、临床特征建立的的联合模型有助于预测RP的发生。多维数据的结合生成了最优预测模型,可为临床医生提供指导。 |
| 英文摘要: |
| Objective To develop and validate a combined model integrating radiomics, dosiomics, and clinical parameters based on CT simulation and dosimetric images in order to predict the occurrence of radiation pneumonitis (RP) in patients with non-small cell lung cancer (NSCLC). Methods A retrospective study was conducted on the clinic data of 143 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022. Patients were randomly stratified into a training group (n = 100) and an internal validation group (n = 43) at a 7∶3 ratio. Moreover, clinic data were collected from 34 NSCLC patients who received radiotherapy at the Jining Cancer Hospital between January 2019 and December 2022 as an external validation group. All three groups (the training group, internal validation, and external validation groups) were further categorized into two groups based on the RP severity (i.e., RP ≥ grade 2 and RP < grade 2). Their radiotherapy dose, CT simulation, and 3D dose distribution images were collected. Then, the total lung minus planning target volume (TL-PTV) was defined as the region of interest (ROI) for radiomics and dosiomic feature extraction, followed by feature dimensionality reduction. Consequently, key features associated with RP were determined. Four predictive models were developed using machine learning approaches (especially multilayer perceptron, MLP): a clinical model (CM), a radiomics model (RM), a dosiomics model (DM), and a radiomics and dosiomics nomogram (RDN), with a nomogram subsequently constructed. Ultimately, the performance and clinical feasibility of these models were assessed using receiver operating characteristic (ROC), area under the curve (AUC), and decision curve analysis (DCA). Results A total of 1 834 radiomic features and 1 834 dosiomic features were extracted. Using the occurrence of RP ≥ grade 2 as the marker variable, 14 radiomic features, 15 dosiomic features, and three clinical features were selected from the training group to construct the prediction models (CM, RM, DM, and RDN). The performance and generalizability of these models were subsequently validated in both the internal validation and external validation groups. Specifically, the RDN exhibited AUCs of 0.915 (95% CI: 0.852-0.978), 0.879 (95% CI: 0.777-0.982), and 0.838 (95% CI: 0.701-0.975) in the three groups, respectively. A nomogram was established for RDN by integrating the radiomics score (R-score), dosiomics score (D-score), mean lung dose (MLD), V20, and V30. This nomogram allowed for individualized risk estimation of RP and facilitated personalized radiotherapy planning. Conclusions The RDN model that is developed based on CT simulation and 3D dose distribution images and integrates radiomics, dosiomics, and clinical features can effectively predict the RP risk of NSCLC patients. The integration of multidimensional data contributes to the formation of the optimal predictive model, offering guidance for clinicians. |
| HTML 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|