亚肺叶切除与早期肺腺癌的不良预后密切相关，因为肿瘤存在气腔扩散（STAS）。因此，术前预测 STAS 对于手术计划非常重要。本研究旨在开发一种针对肿瘤小于 3 cm、实变肿瘤比 (C/T) 小于 0.5 的肺腺癌的 STAS 深度学习 (STAS-DL) 预测模型。该研究回顾性入组了 581 名患者2015年至2019年间来自两个机构的STAS-DL模型的开发是为了通过固体成分门控（SCG）提取固体成分的特征来预测STAS。 STAS-DL 模型在测试集中进行了外部验证评估，并与没有 SCG 的深度学习模型 (STAS-DLwoSCG)、基于放射组学的模型、C/T 比和五名胸外科医生进行了比较。使用决策曲线分析的曲线下面积 (AUC)、准确性和标准化净效益来评估模型的性能。该研究评估了训练组中的 458 名患者（研究所 1）和测试组中的 123 名患者（研究所 2）放。与测试集中的其他方法相比，所提出的 STAS-DL 表现最佳，AUC 为 0.82，准确率为 74%，优于 STAS-DLwoSCG，准确率为 70%，并且优于医生AUC 为 0.68。此外，与其他方法相比，STAS-DL 实现了最高的标准化净效益。所提出的 STAS-DL 模型对于 STAS 的术前预测具有巨大潜力，并且可以支持早期毛玻璃为主的手术计划决策肺腺癌。© 2023。外科肿瘤学会。

Sublobar resection is strongly associated with poor prognosis in early-stage lung adenocarcinoma, with the presence of tumor spread through air spaces (STAS). Thus, preoperative prediction of STAS is important for surgical planning. This study aimed to develop a STAS deep-learning (STAS-DL) prediction model in lung adenocarcinoma with tumor smaller than 3 cm and a consolidation-to-tumor (C/T) ratio less than 0.5.The study retrospectively enrolled of 581 patients from two institutions between 2015 and 2019. The STAS-DL model was developed to extract the feature of solid components through solid components gated (SCG) for predicting STAS. The STAS-DL model was assessed with external validation in the testing sets and compared with the deep-learning model without SCG (STAS-DLwoSCG), the radiomics-based model, the C/T ratio, and five thoracic surgeons. The performance of the models was evaluated using area under the curve (AUC), accuracy and standardized net benefit of the decision curve analysis.The study evaluated 458 patients (institute 1) in the training set and 123 patients (institute 2) in the testing set. The proposed STAS-DL yielded the best performance compared with the other methods in the testing set, with an AUC of 0.82 and an accuracy of 74%, outperformed the STAS-DLwoSCG with an accuracy of 70%, and was superior to the physicians with an AUC of 0.68. Moreover, STAS-DL achieved the highest standardized net benefit compared with the other methods.The proposed STAS-DL model has great potential for the preoperative prediction of STAS and may support decision-making for surgical planning in early-stage, ground glass-predominant lung adenocarcinoma.© 2023. Society of Surgical Oncology.