肺类癌和非典型错构瘤在鉴别上可能存在困难，但需要不同的治疗方法。本研究旨在利用增强CT语义和放射组学标准来区分这些肿瘤。回顾性审查2009年11月至2020年6月间行手术治疗非典型错构瘤或类癌的患者在增强胸部CT上的影像资料。记录语义标准，使用Pyradiomics从三维分割中提取放射组学特征。使用可重复且非冗余的放射组学特征利用交叉验证训练随机森林算法。另一家机构的验证集用于评估放射组学标记、3D中值衰减特征（3D-median）以及2D-ROI的均值。共分析了73名患者（中位年龄58岁【43-70】），其中16例为错构瘤，57例为类癌。放射组学标记对外部数据集（22例错构瘤，32例类癌）预测的AUC为0.76。在模型中，3D中值衰减特征最重要。选择密度阈值<10 HU用于预测错构瘤和>60 HU用于预测类癌，以获得高特异性>0.90。在外部数据集中，3D中值和2D-ROI的敏感性和特异性分别为0.23、1.00和0.13、1.00 (<10 HU)；0.63、0.95和0.69、0.91 (>60 HU)。与2D-ROI相比，3D中值的可重复性更高（ICC=0.97，95% CI【0.95-0.99】，偏倚：3±7 HU一致性界限【-10--16】而ICC=0.90，95% CI【0.85-0.94】，偏倚：-0.7±21 HU一致性界限【-4--40】）。放射组学标记可以通过AUC=0.76区分错构瘤和类癌。基于增强胸部CT的3D分割提取的中位密度<10 HU和>60 HU的值可能对于自信诊断这些肿瘤在临床实践中有用，但是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性的影像征象。从增强胸部CT的3D分割中提取的"中位"衰减值（Hounsfield单位）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），并适用于外部数据集。• 3D-"中位"特征是区分类癌和非典型错构瘤最好的特征（AUC=0.85）。• 3D-"中位"特征具有可重复性（ICC=0.97），并适用于外部数据集。• 从3D分割中提取的放射组学标记可以通过AUC=0.76区分类癌和非典型错构瘤。• 2D-ROI的值与3D-"中位"相当，但可重复性较差（ICC=0.90）。© 2023. 欧洲放射学会（ESR）。

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.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.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).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.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.• 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).© 2023. European Society of Radiology (ESR).