Gray-level discretization impacts reproducible MRI radiomics texture features

ObjectivesTo assess the influence of gray-level discretization on inter- and intra-observer reproducibility of texture radiomics features on clinical MR images.Materials and methodsWe 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.ResultsThe 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.ConclusionsWhen 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.

研究目的：本研究旨在探究灰度离散化对临床磁共振（MR）图像放射组学纹理特征的观察者间与观察者内可重复性的影响。
材料与方法：本研究纳入来自两个不同医学中心的独立磁共振成像数据集共2套，分别包含74例泪腺肿瘤患者与30例乳腺病变患者。由2组阅片者分别对每套数据集完成3次二维病灶轮廓勾画。采用两款放射组学软件（Pyradiomics及一款院内自研软件）提取纹理特征。以组内相关系数（intra-class correlation coefficient, ICC）与一致性相关系数（concordance and coherence coefficient, CCC）分别以0.8和0.9作为阈值，联合筛选可重复特征。本研究共测试6种绝对灰度离散化方法与8种相对灰度离散化方法，并分析每种离散化方案对应的可重复特征分布及最大可重复特征数。此外，本研究还对模拟观察者间差异的计算机辅助勾画所提取的可重复特征数量进行了分析。
结果：灰度离散化方法对放射组学纹理特征的可重复性具有直接影响，且该影响不受阅片者组别、所用软件类型或勾画方式（计算机模拟勾画 vs 人工勾画）的干扰。绝对灰度离散化方法始终可获得较相对灰度离散化方法显著更多的可重复特征，且差异具有统计学意义。调整相对离散化的灰度箱数量所引发的结果变异性，较调整绝对离散化的灰度箱宽度更为显著，且差异具有统计学意义。
结论：若需获取磁共振图像放射组学纹理特征的观察者间可重复性结果，应优先选用绝对灰度离散化方法，以获取最多数量的新型影像生物标志物潜在候选特征。无论选用何种离散化方案，均应进行系统性记录，以保障研究结果的可重复性。