Department of Radiology, Fondation Ophtalmologique Adolphe de Rothschild, Paris, France.
Université Paris Descartes Sorbonne Paris Cité, INSERM UMR-S970, Cardiovascular Research Center-PARCC, Paris, France.
PLoS One. 2019 Mar 7;14(3):e0213459. doi: 10.1371/journal.pone.0213459. eCollection 2019.
To assess the influence of gray-level discretization on inter- and intra-observer reproducibility of texture radiomics features on clinical MR images.
We studied two independent MRI datasets of 74 lacrymal gland tumors and 30 breast lesions from two different centers. Two pairs of readers performed three two-dimensional delineations for each dataset. Texture features were extracted using two radiomics softwares (Pyradiomics and an in-house software). Reproducible features were selected using a combination of intra-class correlation coefficient (ICC) and concordance and coherence coefficient (CCC) with 0.8 and 0.9 as thresholds, respectively. We tested six absolute and eight relative gray-level discretization methods and analyzed the distribution and highest number of reproducible features obtained for each discretization. We also analyzed the number of reproducible features extracted from computer simulated delineations representative of inter-observer variability.
The gray-level discretization method had a direct impact on texture feature reproducibility, independent of observers, software or method of delineation (simulated vs. human). The absolute discretization consistently provided statistically significantly more reproducible features than the relative discretization. Varying the bin number of relative discretization led to statistically significantly more variable results than varying the bin size of absolute discretization.
When considering inter-observer reproducible results of MRI texture radiomics features, an absolute discretization should be favored to allow the extraction of the highest number of potential candidates for new imaging biomarkers. Whichever the chosen method, it should be systematically documented to allow replicability of results.
评估灰度离散化对临床磁共振成像上纹理放射组学特征的观察者间和观察者内可重复性的影响。
我们研究了两个来自两个不同中心的 74 例泪腺肿瘤和 30 例乳腺病变的独立 MRI 数据集。每例数据集由两对读者进行三次二维勾画。使用两种放射组学软件（Pyradiomics 和内部软件）提取纹理特征。使用组内相关系数（ICC）和一致性和相干性系数（CCC）的组合，分别选择 0.8 和 0.9 作为阈值，选择可重复的特征。我们测试了六种绝对灰度离散化方法和八种相对灰度离散化方法，并分析了每种离散化方法得到的可重复特征的分布和最高数量。我们还分析了从代表观察者间变异性的计算机模拟勾画中提取的可重复特征的数量。
灰度离散化方法直接影响纹理特征的可重复性，与观察者、软件或勾画方法（模拟与人工）无关。绝对离散化始终比相对离散化提供更多具有统计学意义的可重复特征。相对离散化的分箱数变化导致的结果比绝对离散化的分箱大小变化更具统计学意义的差异。
在考虑 MRI 纹理放射组学特征的观察者间可重复性结果时，应优先考虑绝对离散化，以允许提取潜在成像生物标志物的最高数量的候选者。无论选择哪种方法，都应系统地记录下来，以确保结果的可重复性。
