Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany.
Department of Molecular Bioinformatics, Institute of Computer Science, Johann Wolfgang Goethe-University, Robert-Mayer-Str. 11-15, 60325, Frankfurt am Main, Germany.
BMC Med Imaging. 2021 Aug 12;21(1):123. doi: 10.1186/s12880-021-00654-9.
To assess the potential of radiomic features to quantify components of blood in intraaortic vessels to non-invasively predict moderate-to-severe anemia in non-contrast enhanced CT scans.
One hundred patients (median age, 69 years; range, 19-94 years) who received CT scans of the thoracolumbar spine and blood-testing for hemoglobin and hematocrit levels ± 24 h between 08/2018 and 11/2019 were retrospectively included. Intraaortic blood was segmented using a spherical volume of interest of 1 cm diameter with consecutive radiomic analysis applying PyRadiomics software. Feature selection was performed applying analysis of correlation and collinearity. The final feature set was obtained to differentiate moderate-to-severe anemia. Random forest machine learning was applied and predictive performance was assessed. A decision-tree was obtained to propose a cut-off value of CT Hounsfield units (HU).
High correlation with hemoglobin and hematocrit levels was shown for first-order radiomic features (p < 0.001 to p = 0.032). The top 3 features showed high correlation to hemoglobin values (p) and minimal collinearity (r) to the top ranked feature Median (p < 0.001), Energy (p = 0.002, r = 0.387), Minimum (p = 0.032, r = 0.437). Median (p < 0.001) and Minimum (p = 0.003) differed in moderate-to-severe anemia compared to non-anemic state. Median yielded superiority to the combination of Median and Minimum (p(AUC) = 0.015, p(precision) = 0.017, p(accuracy) = 0.612) in the predictive performance employing random forest analysis. A Median HU value ≤ 36.5 indicated moderate-to-severe anemia (accuracy = 0.90, precision = 0.80).
First-order radiomic features correlate with hemoglobin levels and may be feasible for the prediction of moderate-to-severe anemia. High dimensional radiomic features did not aid augmenting the data in our exemplary use case of intraluminal blood component assessment. Trial registration Retrospectively registered.
评估基于放射组学特征定量主动脉内血液成分的能力，以无创预测非增强 CT 扫描中的中重度贫血。
回顾性纳入 2018 年 8 月至 2019 年 11 月期间接受胸腰椎 CT 扫描和血红蛋白及血细胞比容水平检测（在 24 小时内）的 100 例患者（中位年龄 69 岁；范围 19-94 岁）。采用 1cm 直径的球形感兴趣区对主动脉内血液进行分割，连续进行放射组学分析，应用 PyRadiomics 软件。采用相关性和共线性分析进行特征选择。获得最终特征集以区分中重度贫血。应用随机森林机器学习进行预测性能评估。获得决策树，提出 CT 亨氏单位（HU）的截断值。
与血红蛋白和血细胞比容水平呈高度相关性的是一阶放射组学特征（p<0.001 至 p=0.032）。前 3 个特征与血红蛋白值高度相关（p），与排名最高的特征中位数（p<0.001）的共线性最小（r）。能量（p=0.002，r=0.387），最小值（p=0.032，r=0.437）。与非贫血状态相比，中重度贫血患者的中位数（p<0.001）和最小值（p=0.003）不同。在采用随机森林分析的预测性能中，中位数优于中位数和最小值的组合（p（AUC）=0.015，p（precision）=0.017，p（accuracy）=0.612）。中位数 HU 值≤36.5 提示中重度贫血（准确率=0.90，精度=0.80）。
一阶放射组学特征与血红蛋白水平相关，可能可用于预测中重度贫血。在我们对管腔内血液成分评估的示例使用案例中，高维放射组学特征无助于增强数据。
回顾性注册。
