Background: Radiomics can provide quantitative descriptors of tumor phenotype, but translation is often limited by feature instability across scanners and protocols. We aimed to develop and internally validate a protocol-specific CT-radiomics model using preoperative imaging to predict 5-year recurrence in patients with stage I lung adenocarcinoma after complete surgical resection. Methods: The retrospective study included 270 patients with completely resected stage I lung adenocarcinoma from January 2010–December 2021, among whom 23 (8.5%) experienced recurrence within five years. Radiomic features were extracted from routine preoperative CT scans. After preprocessing to remove highly constant and highly correlated features, the Synthetic Minority Over-sampling Technique addressed class imbalance in the training set. Recursive Feature Elimination identified the most predictive radiomic features. An XGBoost classifier was trained using optimized hyperparameters identified through RandomizedSearchCV with cross-validation. Model performance was evaluated using the ROC curve and predictive metrics. Results: Five radiomic features differed significantly between recurrence groups (p= 0.007 to <0.001): Shape Sphericity, first-order 90Percentile, GLCM Autocorrelation, GLCM Cluster Shade, and GLDM Large Dependence Low Gray Level Emphasis. The radiomics model showed excellent discriminatory ability with AUC values of 0.99 (95% CI: 0.98–1.00), 0.97 (95% CI: 0.91–1.00), and 0.96 (95% CI: 0.85–1.00) on the training, validation, and test sets, respectively. On the test set, the model achieved sensitivity of 100% (95% CI: 51–100%), specificity of 94% (95% CI: 81–98%), PPV of 67% (95% CI: 30–90%), NPV of 100% (95% CI: 90–100%), and overall accuracy of 95% (95% CI: 83–99%). Conclusions: Under protocol-homogeneous imaging conditions, CT radiomics accurately predicted recurrence in patients with completely resected stage I lung adenocarcinoma. External multi-vendor validation is needed before broader deployment.
背景：放射组学可量化描述肿瘤表型特征，但其应用常因扫描设备和成像协议导致的特征不稳定性而受限。本研究旨在开发并内部验证一种基于术前CT影像的协议特异性放射组学模型，用于预测Ⅰ期肺腺癌患者完全手术切除后的5年复发风险。方法：这项回顾性研究纳入2010年1月至2021年12月期间接受完全手术切除的270例Ⅰ期肺腺癌患者，其中23例（8.5%）在五年内出现复发。从常规术前CT影像中提取放射组学特征。经过预处理剔除高恒定性和高相关性特征后，采用合成少数类过采样技术处理训练集中的类别不平衡问题。通过递归特征消除法筛选最具预测价值的放射组学特征。使用经随机搜索交叉验证优化的超参数训练XGBoost分类器，并采用ROC曲线及预测指标评估模型性能。结果：五个放射组学特征在复发组间存在显著差异（p值范围0.007至<0.001）：形状球形度、一阶90百分位数、灰度共生矩阵自相关、灰度共生矩阵集群阴影、灰度依赖矩阵大依赖低灰度强调。该放射组学模型在训练集、验证集和测试集上均表现出优异的判别能力，AUC值分别为0.99（95% CI：0.98–1.00）、0.97（95% CI：0.91–1.00）和0.96（95% CI：0.85–1.00）。测试集中模型灵敏度为100%（95% CI：51–100%），特异度94%（95% CI：81–98%），阳性预测值67%（95% CI：30–90%），阴性预测值100%（95% CI：90–100%），总体准确率达95%（95% CI：83–99%）。结论：在协议标准化的成像条件下，CT放射组学能准确预测完全切除术后Ⅰ期肺腺癌患者的复发风险，未来需通过多中心多设备的外部验证以推进临床应用。
肿瘤(癌症)患者之家