Xu Pengliang, Yu Huanming, Xing Wenjian, Zhang Shiyu, Hu Haihua, Li Wenhui, Jia Dan, Zhi Shengxu, Peng Xiuhua
Department of Thoracic Surgery, The First People's Hospital of Huzhou, Huzhou, China.
Department of Radiology, Linghu Hospital, Second Medical Group of Nanxun District, Huzhou, China.
Front Oncol. 2025 May 8;15:1572720. doi: 10.3389/fonc.2025.1572720. eCollection 2025.
The goal of this paper is to compare the effectiveness of three deep learning models (2D, 3D, and 2.5D), three radiomics models(INTRA, Peri2mm, and Fusion2mm), and a combined model in predicting the spread through air spaces (STAS) in non-small cell lung cancer (NSCLC) to identify the optimal model for clinical surgery planning.
We included 480 patients who underwent surgery at four centers between January 2019 and August 2024, dividing them into a training cohort, an internal test cohort, and an external validation cohort. We extracted deep learning features using the ResNet50 algorithm. Least absolute shrinkage selection operator(Lasso) and spearman rank correlation were utilized to choose features. Extreme Gradient Boosting (XGboost) was used to execute deep learning and radiomics. Then, a combination model was developed, integrating both sources of data.
The combined model showed outstanding performance, with an area under the receiver operating characteristic curve (AUC) of 0.927 (95% CI 0.870 - 0.984) in the test set and 0.867 (95% CI 0.819 - 0.915) in the validation set. This model significantly distinguished between high-risk and low-risk patients and demonstrated significant advantages in clinical application.
The combined model is adequate for preoperative prediction of STAS in patients with stage T1 NSCLC, outperforming the other six models in predicting STAS risk.
本文旨在比较三种深度学习模型（二维、三维和2.5维）、三种影像组学模型（肿瘤内部、肿瘤边缘2mm、融合2mm）以及一种联合模型在预测非小细胞肺癌（NSCLC）气腔播散（STAS）方面的有效性，以确定临床手术规划的最佳模型。
我们纳入了2019年1月至2024年8月期间在四个中心接受手术的480例患者，将他们分为训练队列、内部测试队列和外部验证队列。我们使用ResNet50算法提取深度学习特征。利用最小绝对收缩选择算子（Lasso）和斯皮尔曼等级相关性来选择特征。采用极端梯度提升（XGboost）进行深度学习和影像组学分析。然后，开发了一个联合模型，整合了两种数据来源。
联合模型表现出色，在测试集中受试者工作特征曲线下面积（AUC）为0.927（95%CI 0.870 - 0.984），在验证集中为0.867（95%CI 0.819 - 0.915）。该模型显著区分了高风险和低风险患者，并在临床应用中显示出显著优势。
联合模型适用于T1期NSCLC患者术前STAS预测，在预测STAS风险方面优于其他六种模型。
