Applied Radiation Therapy Trinity, Discipline of Radiation Therapy, Trinity St James' Cancer Institute, Trinity College Dublin, Dublin, Ireland.
Applied Radiation Therapy Trinity, Discipline of Radiation Therapy, Trinity St James' Cancer Institute, Trinity College Dublin, Dublin, Ireland.
Phys Med. 2021 Feb;82:240-248. doi: 10.1016/j.ejmp.2021.01.084. Epub 2021 Mar 4.
This study aimed to quantify the variability in the values of radiomic features extracted from a right parotid gland (RPG) delineated by a series of independent observers.
This was a secondary analysis of anonymous data from a delineation workshop. Inter-observer variability of the RPG from 40 participants was quantified using DICE similarity coefficient (DSC) and Hausdorff distance (HD). An additional contour was generated using Varian SmartSegmentation. Radiomic features extracted include four shape features, six histogram features, and 32 texture features. The absolute mean paired percentage difference (PPD) in feature values from the expert and participants were ranked . Feature robustness was classified using pre- determined thresholds.
63% of participants achieved a DSC > 0.7, the auto- segmentation DSC was 0.76. The average HD for the participants was 16.16 mm ± 0.66 mm, and 15.16 mm for the auto-segmentation. 48% (n = 20) and 33% (n = 14) of features were deemed to be robust with a mean absolute PPD < 5%, for the auto-segmentation and manual delineations respectively; the majority of which were from the grey-run length matrix family. 7% (n = 3) of features from the auto- segmentation and 10% (n = 4) from the manual contours were deemed to be unstable with a mean absolute PPD > 50%. The value of the most robust feature was not related to DSC and HD.
Inter-observer delineation variability affects the value of the radiomic features extracted from the RPG. This study identifies the radiomic features least sensitive to these uncertainties. Further investigation of the clinical relevance of these features in prediction of xerostomia is warranted.
本研究旨在量化由一系列独立观察者勾画的右腮腺（RPG）的放射组学特征值的变异性。
这是一个匿名勾画工作坊数据的二次分析。通过 DICE 相似性系数（DSC）和 Hausdorff 距离（HD）来量化 40 名参与者的 RPG 间的观察者间变异性。使用 Varian SmartSegmentation 生成另外一条轮廓。提取的放射组学特征包括四个形状特征、六个直方图特征和 32 个纹理特征。从专家和参与者处提取的特征值的绝对平均配对百分比差异（PPD）进行排名。使用预先确定的阈值对特征稳健性进行分类。
63%的参与者达到了 DSC>0.7，自动分割的 DSC 为 0.76。参与者的平均 HD 为 16.16mm±0.66mm，自动分割的为 15.16mm。48%（n=20）和 33%（n=14）的特征分别被认为是稳健的，其平均绝对 PPD<5%，用于自动分割和手动勾画；其中大部分来自灰度游程长度矩阵家族。7%（n=3）的自动分割特征和 10%（n=4）的手动勾画特征被认为是不稳定的，其平均绝对 PPD>50%。最稳健特征的值与 DSC 和 HD 无关。
观察者间勾画的变异性会影响从 RPG 提取的放射组学特征的值。本研究确定了对这些不确定性最不敏感的放射组学特征。进一步研究这些特征在预测口干症中的临床相关性是有必要的。
