PDF(Pubmed)
Abstract：
OBJECTIVE: Lung carcinoids and atypical hamartomas may be difficult to differentiate but require different treatment. The aim was to differentiate these tumors using contrast-enhanced CT semantic and radiomics criteria.
METHODS: Between November 2009 and June 2020, consecutives patient operated for hamartomas or carcinoids with contrast-enhanced chest-CT were retrospectively reviewed. Semantic criteria were recorded and radiomics features were extracted from 3D segmentations using Pyradiomics. Reproducible and non-redundant radiomics features were used to training a random forest algorithm with cross-validation. A validation-set from another institution was used to evaluate of the radiomics signature, the 3D \'median\' attenuation feature (3D-median) alone and the mean value from 2D-ROIs.
RESULTS: Seventy-three patients (median 58 years [43‒70]) were analyzed (16 hamartomas; 57 carcinoids). The radiomics signature predicted hamartomas vs carcinoids on the external dataset (22 hamartomas; 32 carcinoids) with an AUC = 0.76. The 3D-median was the most important in the model. Density thresholds < 10 HU to predict hamartoma and > 60 HU to predict carcinoids were chosen for their high specificity > 0.90. On the external dataset, sensitivity and specificity of the 3D-median and 2D-ROIs were, respectively, 0.23, 1.00 and 0.13, 1.00 < 10 HU; 0.63, 0.95 and 0.69, 0.91 > 60 HU. The 3D-median was more reproducible than 2D-ROIs (ICC = 0.97 95% CI [0.95‒0.99]; bias: 3 ± 7 HU limits of agreement (LoA) [- 10‒16] vs. ICC = 0.90 95% CI [0.85‒0.94]; bias: - 0.7 ± 21 HU LoA [- 4‒40], respectively).
CONCLUSIONS: A radiomics signature can distinguish hamartomas from carcinoids with an AUC = 0.76. Median density < 10 HU and > 60 HU on 3D or 2D-ROIs may be useful in clinical practice to diagnose these tumors with confidence, but 3D is more reproducible.
UNASSIGNED: Radiomic features help to identify the most discriminating imaging signs using random forest. \'Median\' attenuation value (Hounsfield units), extracted from 3D-segmentations on contrast-enhanced chest-CTs, could distinguish carcinoids from atypical hamartomas (AUC = 0.85), was reproducible (ICC = 0.97), and generalized to an external dataset.
CONCLUSIONS: • 3D-\'Median\' was the best feature to differentiate carcinoids from atypical hamartomas (AUC = 0.85). • 3D-\'Median\' feature is reproducible (ICC = 0.97) and was generalized to an external dataset. • Radiomics signature from 3D-segmentations differentiated carcinoids from atypical hamartomas with an AUC = 0.76. • 2D-ROI value reached similar performance to 3D-\'median\' but was less reproducible (ICC = 0.90).
METHODS: Between November 2009 and June 2020, consecutives patient operated for hamartomas or carcinoids with contrast-enhanced chest-CT were retrospectively reviewed. Semantic criteria were recorded and radiomics features were extracted from 3D segmentations using Pyradiomics. Reproducible and non-redundant radiomics features were used to training a random forest algorithm with cross-validation. A validation-set from another institution was used to evaluate of the radiomics signature, the 3D \'median\' attenuation feature (3D-median) alone and the mean value from 2D-ROIs.
RESULTS: Seventy-three patients (median 58 years [43‒70]) were analyzed (16 hamartomas; 57 carcinoids). The radiomics signature predicted hamartomas vs carcinoids on the external dataset (22 hamartomas; 32 carcinoids) with an AUC = 0.76. The 3D-median was the most important in the model. Density thresholds < 10 HU to predict hamartoma and > 60 HU to predict carcinoids were chosen for their high specificity > 0.90. On the external dataset, sensitivity and specificity of the 3D-median and 2D-ROIs were, respectively, 0.23, 1.00 and 0.13, 1.00 < 10 HU; 0.63, 0.95 and 0.69, 0.91 > 60 HU. The 3D-median was more reproducible than 2D-ROIs (ICC = 0.97 95% CI [0.95‒0.99]; bias: 3 ± 7 HU limits of agreement (LoA) [- 10‒16] vs. ICC = 0.90 95% CI [0.85‒0.94]; bias: - 0.7 ± 21 HU LoA [- 4‒40], respectively).
CONCLUSIONS: A radiomics signature can distinguish hamartomas from carcinoids with an AUC = 0.76. Median density < 10 HU and > 60 HU on 3D or 2D-ROIs may be useful in clinical practice to diagnose these tumors with confidence, but 3D is more reproducible.
UNASSIGNED: Radiomic features help to identify the most discriminating imaging signs using random forest. \'Median\' attenuation value (Hounsfield units), extracted from 3D-segmentations on contrast-enhanced chest-CTs, could distinguish carcinoids from atypical hamartomas (AUC = 0.85), was reproducible (ICC = 0.97), and generalized to an external dataset.
CONCLUSIONS: • 3D-\'Median\' was the best feature to differentiate carcinoids from atypical hamartomas (AUC = 0.85). • 3D-\'Median\' feature is reproducible (ICC = 0.97) and was generalized to an external dataset. • Radiomics signature from 3D-segmentations differentiated carcinoids from atypical hamartomas with an AUC = 0.76. • 2D-ROI value reached similar performance to 3D-\'median\' but was less reproducible (ICC = 0.90).
摘要：
目的：肺类癌和不典型错构瘤可能难以区分，但需要不同的治疗方法。目的是使用对比增强的CT语义和放射组学标准来区分这些肿瘤。
方法：在2009年11月至2020年6月期间，对连续接受错构瘤或类癌手术的患者进行了胸部CT对比增强检查。记录语义标准，并使用Pyradiomics从3D分割中提取影像组学特征。使用可重复和非冗余的影像组学特征来训练具有交叉验证的随机森林算法。来自另一个机构的验证集用于评估放射组学签名，单独的3D“中位数”衰减特征(3D-中位数)和2D-ROI的平均值。
结果：分析了73例患者（中位58岁[43-70]）（16例错构瘤；57例类癌）。影像组学特征预测外部数据集上的错构瘤与类癌(22个错构瘤;32个类癌),AUC=0.76。3D中位数是模型中最重要的。选择密度阈值<10HU来预测错构瘤和>60HU来预测类癌,因为它们的高特异性>0.90。在外部数据集上，3D中位数和2D-ROI的敏感性和特异性分别为，分别,0.23、1.00和0.13、1.00<10HU；0.63、0.95和0.69、0.91>60HU。3D中位数比2D-ROIs更具可重复性（ICC=0.9795％CI[0.95–0.99]；偏倚：3±7HU一致极限（LoA）[-10–16]与ICC=0.9095%CI[0.85-0.94]；偏差：-0.7±21HULoA[-4-40]，分别)。
结论：影像组学特征可以区分错构瘤和类癌，AUC=0.76。3D或2D-ROIs的中位密度<10HU和>60HU可能在临床实践中对诊断这些肿瘤有信心。但3D更具可重复性。
■放射组学特征有助于使用随机森林识别最具鉴别力的影像学征象。中值衰减值(Hounsfield单位),从对比增强胸部CT的3D分割中提取，可以区分类癌和非典型错构瘤（AUC=0.85），具有可重复性(ICC=0.97)，并推广到外部数据集。
结论：•3D-“median”是鉴别类癌与非典型错构瘤的最佳特征（AUC=0.85）。•3D-“中间值”特征是可再现的(ICC=0.97)并且被推广到外部数据集。•来自3D分割的影像组学特征区分类癌与非典型错构瘤,AUC=0.76。•2D-ROI值达到与3D-“中位数”相似的性能，但重现性较差（ICC=0.90）。
方法：在2009年11月至2020年6月期间，对连续接受错构瘤或类癌手术的患者进行了胸部CT对比增强检查。记录语义标准，并使用Pyradiomics从3D分割中提取影像组学特征。使用可重复和非冗余的影像组学特征来训练具有交叉验证的随机森林算法。来自另一个机构的验证集用于评估放射组学签名，单独的3D“中位数”衰减特征(3D-中位数)和2D-ROI的平均值。
结果：分析了73例患者（中位58岁[43-70]）（16例错构瘤；57例类癌）。影像组学特征预测外部数据集上的错构瘤与类癌(22个错构瘤;32个类癌),AUC=0.76。3D中位数是模型中最重要的。选择密度阈值<10HU来预测错构瘤和>60HU来预测类癌,因为它们的高特异性>0.90。在外部数据集上，3D中位数和2D-ROI的敏感性和特异性分别为，分别,0.23、1.00和0.13、1.00<10HU；0.63、0.95和0.69、0.91>60HU。3D中位数比2D-ROIs更具可重复性（ICC=0.9795％CI[0.95–0.99]；偏倚：3±7HU一致极限（LoA）[-10–16]与ICC=0.9095%CI[0.85-0.94]；偏差：-0.7±21HULoA[-4-40]，分别)。
结论：影像组学特征可以区分错构瘤和类癌，AUC=0.76。3D或2D-ROIs的中位密度<10HU和>60HU可能在临床实践中对诊断这些肿瘤有信心。但3D更具可重复性。
■放射组学特征有助于使用随机森林识别最具鉴别力的影像学征象。中值衰减值(Hounsfield单位),从对比增强胸部CT的3D分割中提取，可以区分类癌和非典型错构瘤（AUC=0.85），具有可重复性(ICC=0.97)，并推广到外部数据集。
结论：•3D-“median”是鉴别类癌与非典型错构瘤的最佳特征（AUC=0.85）。•3D-“中间值”特征是可再现的(ICC=0.97)并且被推广到外部数据集。•来自3D分割的影像组学特征区分类癌与非典型错构瘤,AUC=0.76。•2D-ROI值达到与3D-“中位数”相似的性能，但重现性较差（ICC=0.90）。
