用多中心CT影像+模型融合，提升肺癌生存预测准确率
Consensus in the Parliament of AI: Harmonized Multi-Region CT-Radiomics and Foundation-Model Signatures for Multicentre NSCLC Risk Stratification
- 用ComBat等方法统一多中心扫描差异，融合肺、肿瘤等多个区域特征
- 整合深度特征与临床数据后，5年生存预测t-AUC达0.92，灵敏度96.8%
- 适合做多中心癌症预后建模的研究者和临床决策支持系统开发者
本研究评估了图像标准化与多区域特征融合对非小细胞肺癌（NSCLC）患者生存预测的影响。基于来自五个中心的876名患者的胸部CT影像，提取了肺、肿瘤、纵隔淋巴结、冠状动脉及冠状动脉钙化（CAC）评分的手工特征与预训练深度特征，并结合临床数据构建生存模型。采用ComBat、重建核归一化（RKN）及RKN-ComBat进行特征校正，分别在感兴趣区域（ROI）层面建模并采用集成策略。使用正则化Cox模型估计总生存率，通过一致性指数（C-index）、5年时间依赖AUC（t-AUC）和风险比评估性能。SHAP值分析特征贡献，共识分析在固定时间点对预测概率进行分类。结果表明，TNM分期具有预测价值（C-index = 0.67；风险比 = 2.70；t-AUC = 0.85）。结合ComBat校正的临床与肿瘤纹理放射组学模型表现优异（C-index = 0.76；t-AUC = 0.88）。50个体素立方体的基金会模型（FM）深度特征也具预测能力（C-index = 0.76；t-AUC = 0.89）。综合肿瘤、肺、纵隔淋巴结、CAC及FM特征的集成模型达到C-index 0.71、t-AUC 0.79。共识分析识别出高置信度患者子集，该模型5年t-AUC达0.92，敏感性96.8%，特异性70.0%。结论：图像标准化与多区域特征融合显著提升多中心NSCLC生存预测能力，支持个体化风险分层。
原文摘要 · Abstract (English)
Purpose: This study evaluates the impact of harmonization and multi-region feature integration on survival prediction in non-small cell lung cancer (NSCLC) patients. We assess the prognostic utility of handcrafted radiomics and pretrained deep features from thoracic CT images, integrating them with clinical data using a multicentre dataset. Methods: Survival models were built using handcrafted radiomic and deep features from lung, tumor, mediastinal nodes, coronary arteries, and coronary artery calcium (CAC) scores from 876 patients across five centres. CT features were harmonized using ComBat, reconstruction kernel normalization (RKN), and RKN-ComBat. Models were constructed at the region of interest (ROI) level and through ensemble strategies. Regularized Cox models estimated overall survival, with performance assessed via the concordance index (C-index), 5-year time-dependent area under the curve (t-AUC), and hazard ratios. SHAP values interpreted feature contributions, while consensus analysis categorized predicted survival probabilities at fixed time points. Results: TNM staging showed prognostic value (C-index = 0.67; hazard ratio = 2.70; t-AUC = 0.85). The clinical and tumor texture radiomics model with ComBat yielded high performance (C-index = 0.76; t-AUC = 0.88). FM deep features from 50 voxel cubes also showed predictive value (C-index = 0.76; t-AUC = 0.89). An ensemble model combining tumor, lung, mediastinal node, CAC, and FM features achieved a C-index of 0.71 and t-AUC of 0.79. Consensus analysis identified a high-confidence patient subset, resulting in a model with a 5-year t-AUC of 0.92, sensitivity of 96.8%, and specificity of 70.0%. Conclusion: Harmonization and multi-region feature integration enhance survival prediction in NSCLC patients using CT imaging, supporting individualized risk stratification in multicentre settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。