基于剂量组学模型预测鼻咽癌调强放疗后放射性颞叶损伤  

Dosiomics model for predicting radiation-induced temporal lobe injury in nasopharyngeal carcinoma after intensity-modulated radiotherapy

作　　者：刘君懿 李阳 王力 周佳伟 邱婷 高瀚 祝因苏 杨冠羽[3] 黄生富[1] 何侠[1] 吴俚蓉[1] Liu Junyi;Li Yang;Wang Li;Zhou Jiawei;Qiu Ting;Gao Han;Zhu Yinsu;Yang Guanyu;Huang Shengfu;He Xia;Wu Lirong(Department of Radiation Oncology,Jiangsu Cancer Hospital&Jiangsu Institute of Cancer Research&Affiliated Cancer Hospital of Nanjing Medical University,Nanjing 210009,China;Center of Radiology,Jiangsu Cancer Hospital&Jiangsu Institute of Cancer Research&Affiliated Cancer Hospital of Nanjing Medical University,Nanjing 210009,China;Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications(Southeast University),Ministry of Education,Nanjing 210096,China)

机构地区：[1]江苏省肿瘤医院/江苏省肿瘤防治研究所/南京医科大学附属肿瘤医院放疗科,南京210009 [2]江苏省肿瘤医院/江苏省肿瘤防治研究所/南京医科大学附属肿瘤医院影像中心,南京210009 [3]东南大学,新一代人工智能技术与交叉应用教育部重点实验室,南京210096

出　　处：《中华放射肿瘤学杂志》2025年第3期240-248,共9页Chinese Journal of Radiation Oncology

基　　金：江苏省第六期“333工程”优秀青年人才项目;江苏省卫健委预防医学面上项目(Ym2023109);南京市博士后课题优秀项目;江苏省肿瘤医院临床科技攀登计划-“求真”临床研究专项(ZL202207)。

摘　　要：目的探讨基于三维剂量分布的剂量组学模型在预测鼻咽癌患者调强放疗后放射性颞叶损伤(RTLI)中的性能并进行验证。方法回顾性分析2011年1月至2021年12月江苏省肿瘤医院收治的3578例鼻咽癌患者的资料。根据纳入和排除标准,纳入97例发生RTLI的鼻咽癌患者作为病例组,利用倾向性评分匹配法1∶1匹配97例未发生RTLI的鼻咽癌患者作为对照组。将患者按7∶3的比例采用简单随机法分为训练组(135例)和验证组(59例)。从患者三维剂量分布图中提取剂量组学特征,使用斯皮尔曼等级相关系数和最小绝对收缩和选择算子回归来筛选剂量组学特征。收集患者的临床特征,使用单因素及多因素分析筛选临床特征。随后,训练8个机器学习分类器分别构建剂量组学模型和临床模型。计算曲线下面积(AUC)、灵敏度、特异度等参数来比较剂量组学和临床特征的预测性能。多因素分析采用logistic回归方法评估,不同模型之间的ROC曲线采用DeLong检验进行比较。结果从三维剂量分布图中提取1130个剂量组学特征,经特征筛选后保留14个特征用于剂量组学模型建立,基于支持向量机(SVM)分类器的模型在验证组中取得了最高的AUC值,为0.977(95%CI为0.949~1.000),在训练组中的AUC值为1.000(95%CI为1.000~1.000)。通过对患者的临床特征进行单因素和多因素分析,最终选取2个临床特征用于临床模型建立,基于SVM分类器的模型在验证组中取得了最佳的AUC值(0.667,95%CI为0.523~0.810),其在训练组的AUC值为0.804(95%CI为0.730~0.878)。DeLong检验显示,剂量组学模型与临床模型的差异具有统计学意义(P<0.05)。结论基于三维剂量分布构建的剂量组学模型对于鼻咽癌患者调强放疗后RTLI的发生具有较高的预测能力,优于临床模型,为临床早期预测RTLI提供了新的思路。ObjectiveTo investigate and validate the performance of a dosiomics model that utilized 3D dose distribution to forecast radiation-induced temporal lobe injury(RTLI)in nasopharyngeal carcinoma(NPC)patients following intensity-modulated radiotherapy(IMRT).MethodsClinical data of 3578 patients diagnosed with NPC admitted to Jiangsu Cancer Hospital from January 2011 to December 2021 were retrospectively analyzed.According to the inclusion and exclusion criteria,97 NPC patients who developed RTLI were assigned into the case group.A 1:1 propensity score matching(PSM)method was used to match 97 NPC patients without RTLI as the control group.Patients were assigned into the training cohort(n=135)and the validation cohort(n=59)at a 7:3 ratio by simple random method.Dosiomics features were extracted from the patients'three-dimensional dose distribution maps.Spearman rho and the least absolute shrinkage and selection operator regression were used to select dosiomics features.Clinical features were collected and screened by univariate and multivariate analyses.Eight machine learning classifiers were then trained to build dosiomics models and clinical models,respectively.The area under the ROC curve(AUC),sensitivity,and specificity were calculated to compare the predictive performance of the dosiomics and clinical models.Multivariate analysis was conducted using logistic regression to assess the influencing factors,while comparisons of the ROC curves between two different models were performed using the DeLong test.ResultsA total of 1130 dosiomics features were extracted from the three-dimensional dose distribution maps,and 14 features were retained for model building after feature selection.The model based on the support vector machine(SVM)classifier achieved the highest AUC value of 0.977(95%CI:0.949-1.000)in the validation cohort,with an AUC of 1.000(95%CI:1.000-1.000)in the training cohort.By conducting univariate and multivariate analyses of the patients'clinical features,2 clinical features were retained to build the cl

关 键 词：鼻咽癌 剂量组学 调强放疗 机器学习 放射性颞叶损伤 预测模型 

分 类 号：R73[医药卫生—肿瘤]