Department of Radiation Oncology, University of California Davis School of Medicine, Sacramento, CA 95817, United States of America. Medical Engineering and Technology Research Center; Imaging-X Joint Laboratory; Department of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Taian 271016, People's Republic of China. LS and YR contributed equally to the study.
Phys Med Biol. 2020 Jan 10;65(1):015009. doi: 10.1088/1361-6560/ab3247.
Cone-beam computed tomography (CBCT) images acquired during radiotherapy may allow early response assessment. Previous studies have reported inconsistent findings on an association of CBCT-measured tumor volume changes with clinical outcomes. The purpose of this pilot study was twofold: (1) to characterize changes in CBCT-based radiomics features during treatment; and (2) to quantify the potential association of CBCT-based delta-radiomics features with overall survival in locally advanced lung cancer. We retrospectively identified 23 patients and calculated 658 radiomics features from each of 11 CBCT images per patient. Feature selection was performed based on repeatability, robustness against contouring uncertainties, and non-redundancy. We calculated the coefficient of determination (R ) for the relationship between the actual feature value at the end of treatment and predicted value based on linear models fitted using features between the first and kth fractions. We also quantified the predictive ability for survival with two methods by: (1) comparing delta-radiomics features (defined as the mean change between the first and kth fractions) between two groups of patients divided by a cutoff survival time of 18 months using the t-test or Wilcoxon rank-sum test; and (2) quantifying univariate discrimination of two groups divided by the median of delta-radiomics feature. All selected seven radiomics features during treatment (as early as the 10th fraction) were predictive of those at the end of treatment (R > 0.64). Three delta-radiomics features demonstrated significant differences (q < 0.05, as early as the 10th fraction) between the two groups of patients divided by the cutoff survival time. Two of those three features were also predictive of survival according to the log-rank statistics. We provided the first demonstration of a potential association of CBCT-based delta-radiomics features early during treatment with overall survival in locally advanced lung cancer. Our preliminary findings should be validated for a larger cohort of patients.
锥形束计算机断层扫描（CBCT）图像在放射治疗期间可能允许早期评估反应。先前的研究报告称，CBCT 测量的肿瘤体积变化与临床结果之间的关联存在不一致的发现。本研究的目的有两个：（1）描述治疗过程中基于 CBCT 的放射组学特征的变化；（2）量化基于 CBCT 的δ-放射组学特征与局部晚期肺癌总生存率的潜在关联。我们回顾性地确定了 23 名患者，并为每位患者的 11 次 CBCT 图像中的每幅图像计算了 658 个放射组学特征。基于重复性、对抗勾画不确定性的稳健性和非冗余性，进行特征选择。我们根据线性模型，使用第 1 次和第 k 次分割之间的特征，计算治疗结束时实际特征值与预测值之间的决定系数（R）。我们还使用两种方法量化了对生存的预测能力：（1）通过 t 检验或 Wilcoxon 秩和检验比较两组患者之间的δ-放射组学特征（定义为第 1 次和第 k 次分割之间的平均值变化），以生存时间 18 个月为截止值；（2）通过将两组分为两组的中位数，量化两组之间的单变量区分δ-放射组学特征。在治疗过程中选择的 7 个放射组学特征（最早在第 10 次分割时）都可以预测治疗结束时的特征（R > 0.64）。根据截止生存时间，两组患者之间的三个δ-放射组学特征显示出显著差异（q < 0.05，最早在第 10 次分割时）。其中两个特征根据对数秩统计也可预测生存情况。我们首次证明了基于 CBCT 的δ-放射组学特征在局部晚期肺癌治疗早期与总生存率之间存在潜在关联。我们的初步发现应在更大的患者队列中得到验证。
Zotero 插件