需要改进小（≤15mm）肺结节分层的方法。我们的目标是开发一种放射组学模型来辅助肺癌诊断。使用2007年1月至2018年12月的健康记录对患者进行回顾性识别。外部测试集来自国家LIBRA研究和前瞻性肺癌筛查计划。使用 TexLab2.0 从多区域 CT 分割中提取放射组学特征。 LASSO 回归生成 5 特征小结节放射组学预测向量 (SN-RPV)。 K 均值聚类用于根据 SN-RPV 将患者分为风险组。模型性能与 6 名胸部放射科医生进行了比较。 SN-RPV 和放射科医生风险组结合起来生成“安全网”和“早期诊断”决策支持工具。总共包括 810 名患者，990 个结节。训练、测试和外部测试数据集的恶性肿瘤预测 AUC 分别为 0.85 (95% CI: 0.82-0.87)、0.78 (95% CI: 0.70-0.85) 和 0.78 (95% CI: 0.59-0.92)。与表现最接近平均值的放射科医生相比，测试集准确度为 73%（95% CI：65-81%），潜在漏诊 [8/12] 或延迟 [6/9] 癌症的发病率提高了 66.67%六位读者。SN-RPV 可能会在早期癌症诊断方面提供净效益。© 2023。作者，获得 Springer Nature Limited 的独家许可。

Methods to improve stratification of small (≤15 mm) lung nodules are needed. We aimed to develop a radiomics model to assist lung cancer diagnosis.Patients were retrospectively identified using health records from January 2007 to December 2018. The external test set was obtained from the national LIBRA study and a prospective Lung Cancer Screening programme. Radiomics features were extracted from multi-region CT segmentations using TexLab2.0. LASSO regression generated the 5-feature small nodule radiomics-predictive-vector (SN-RPV). K-means clustering was used to split patients into risk groups according to SN-RPV. Model performance was compared to 6 thoracic radiologists. SN-RPV and radiologist risk groups were combined to generate "Safety-Net" and "Early Diagnosis" decision-support tools.In total, 810 patients with 990 nodules were included. The AUC for malignancy prediction was 0.85 (95% CI: 0.82-0.87), 0.78 (95% CI: 0.70-0.85) and 0.78 (95% CI: 0.59-0.92) for the training, test and external test datasets, respectively. The test set accuracy was 73% (95% CI: 65-81%) and resulted in 66.67% improvements in potentially missed [8/12] or delayed [6/9] cancers, compared to the radiologist with performance closest to the mean of six readers.SN-RPV may provide net-benefit in terms of earlier cancer diagnosis.© 2023. The Author(s), under exclusive licence to Springer Nature Limited.