探索个体化医疗中的技术问题:非小细胞肺癌生存预测的定量图像分析——容积CT数据密度校正的实用性
本研究对57例手术治疗的非小细胞肺癌患者的术前CT(平扫及增强)进行原发肿瘤大体体积、主动脉和气管空气的容积密度测量,并对肿瘤大体体积行密度校正(参考值为主动脉血和气管空气)。将临床病理与影像数据单独及联合与1年、3年、5年总生存进行相关分析,最佳预测值出现在临床病理联合影像参数时(AUC:1年0.72;3年0.82;5年0.78)。密度校正对影像定量特征预测总生存的性能影响方向不一,几乎所有预测指标均无统计学显著性。
要点
- 临床病理联合影像参数的预测性能最佳,AUC在1年、3年、5年分别为0.72、0.82、0.78。
- 密度校正对影像定量特征预测总生存的性能影响方向不一,仅灰度共生矩阵的cluster prominence预测1年总生存的负向性能有统计学显著性(P值0.05)。
- 归一化后部分灰度级大小区域特征(大区域低灰度强调)及联合模型的1年总生存预测有改善,而灰度共生矩阵参数(cluster prominence和shade)及一阶统计参数(range)分别对1年和5年总生存预测性能变差。
核心结论
- 对手术治疗的非小细胞肺癌患者,密度校正对容积CT影像定量特征预测总生存的性能影响方向不一,但几乎所有预测指标均无统计学显著性。
研究设计与样本
- 回顾性收集57例手术治疗的非小细胞肺癌患者的临床病理数据和术前CT扫描(包括增强前和增强后)。
- 对原发肿瘤大体体积、主动脉和气管空气行CT容积密度测量,并以主动脉血和气管空气为参考值对肿瘤大体体积行密度校正。
- 对每个数据集(结合对比剂给药和归一化)提取一阶统计和纹理特征,采用单因素/多因素逻辑回归和Akaike信息准则分析临床病理与影像数据与1年、3年、5年总生存的相关性。
- 预测性能通过ROC曲线和AUC值评估,并在非归一化/归一化数据集间采用DeLong检验比较。
诊断标准与关键数值
- 最佳预测值出现在临床病理联合影像参数时,AUC值:1年0.72;3年0.82;5年0.78。
- 归一化后,部分灰度级大小区域特征(大区域低灰度强调)及联合临床病理-影像模型对1年总生存的预测有改善;灰度共生矩阵参数(cluster prominence和shade)及一阶统计参数(range)分别对1年和5年总生存预测性能变差。
- cluster prominence预测1年总生存的负向性能是唯一有统计学显著性的结果(P值0.05)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
The aim of this study was to apply density correction method to the quantitative image analysis of non-small cell lung cancer (NSCLC) computed tomography (CT) images, determining its influence on overall survival (OS) prediction of surgically treated patients. Clinicopathological (CP) data and preoperative CT scans, pre- and post-contrast medium (CM) administration, of 57 surgically treated NSCLC patients, were retrospectively collected. After CT volumetric density measurement of primary gross tumour volume (GTV), aorta and tracheal air, density correction was conducted on GTV (reference values: aortic blood and tracheal air). For each resulting data set (combining CM administration and normalization), first-order statistical and textural features were extracted. CP and imaging data were correlated with patients 1-, 3- and 5-year OS, alone and combined (uni-/multivariate logistic regression and Akaike information criterion). Predictive performance was evaluated using the ROC curves and AUC values and compared among non-normalized/normalized data sets (DeLong test). The best predictive values were obtained when combining CP and imaging parameters (AUC values: 1 year 0.72; 3 years 0.82; 5 years 0.78). After normalization resulted an improvement in predicting 1-year OS for some of the grey level size zonebased features (large zone low grey level emphasis) and for the combined CP-imaging model, a worse performance for grey level co-occurrence matrix (cluster prominence and shade) and first-order statistical (range) parameters for 1- and 5-year OS, respectively. The negative performance of cluster prominence in predicting 1-year OS was the only statistically significant result (p value 0.05). Density corrections of volumetric CT data showed an opposite influence on the performance of imaging quantitative features in predicting OS of surgically treated NSCLC patients, even if no statistically significant for almost all predictors.
引用
- Farchione A, Larici AR, Masciocchi C, et al. Exploring technical issues in personalized medicine: NSCLC survival prediction by quantitative image analysis-usefulness of density correction of volumetric CT data. Radiol Med. 2020. PMID: 32125637. doi:10.1007/s11547-020-01157-3
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。