文献速递胸部CT

多模态Transformer整合CT与病理用于I期非小细胞肺癌术后风险分层

Multimodal Transformer Integrating CT and Pathology for Postoperative Risk Stratification in Stage I Non-Small Cell Lung Cancer.
PubMed 文献 · Radiol Imaging Cancer · 2026-01-01

本研究开发并评估了一种可解释的多模态深度学习模型DLRTransformer,整合CT的2.5维深度学习特征、影像组学、临床变量及病理报告文本嵌入,用于I期NSCLC术后无病生存预测。多中心回顾性纳入1073例患者,外部验证C指数0.77-0.78,优于指南风险分层(0.60-0.65),且模型风险评分与辅助治疗获益存在交互作用。

要点

  • DLRTransformer外部验证C指数0.77-0.78,优于指南分层0.60-0.65。
  • 高风险患者辅助治疗改善无病生存(HR 0.30),低风险患者未见获益。
  • 风险评分与肿瘤微环境表型相关,高评分者新生细胞丰富、三级淋巴结构减少。

核心结论

  • DLRTransformer较指南风险分层改善了I期NSCLC术后风险分层,并识别出可从辅助治疗中获益的患者。

研究设计与样本

  • 多中心回顾性研究,纳入5个中心1073例I期NSCLC患者(平均年龄60.8岁±9.8,550例男性)。
  • 模型整合CT多视图2.5维深度学习特征、影像组学、临床变量及大语言模型提取的病理报告预后嵌入,经中心Transformer架构融合预测无病生存。
  • 在独立外部数据集上评估模型性能,并与指南基于的风险分层比较,同时分析风险评分与肿瘤微环境特征的关联。

关键影像表现/征象

  • 原文未报告具体影像征象,模型输入为CT多视图2.5维深度学习特征及影像组学特征。
  • 模型风险评分与肿瘤微环境表型相关:新生细胞丰富度增加和三级淋巴结构减少。

诊断标准与关键数值

  • 外部数据集C指数0.77-0.78,优于指南风险分层的0.60-0.65。
  • 治疗与风险交互作用HR 0.14(95%CI 0.06, 0.32;P < .01)。
  • 倾向性评分匹配亚组中,高风险患者辅助治疗改善无病生存(HR 0.30;95%CI 0.11, 0.84;P = .02)。
  • 低风险患者辅助治疗无显著获益(HR 1.70;95%CI 0.97, 2.99;P = .06)。

临床应用与阅片要点

  • 该模型可作为I期NSCLC术后风险分层辅助工具,帮助识别可能从辅助治疗获益的高风险患者。
  • 模型整合CT深度学习与影像组学特征,提示日常阅片时可关注与肿瘤微环境相关的影像表型,但原文未给出具体可视征象。

局限性

  • 回顾性研究设计。
  • 原文未报告其他局限。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Purpose To develop and evaluate an interpretable, multimodal deep learning model to improve postoperative risk stratification and predict adjuvant therapy benefit in stage I non-small cell lung cancer (NSCLC). Materials and Methods In this multicenter retrospective study of patients with stage I NSCLC, a multimodal model called the Deep Learning-Radiomic-Text Transformer (DLRTransformer) was developed by integrating multiview 2.5-dimensional deep learning features from CT scans, radiomics, clinical variables, and prognostic embeddings extracted from pathology reports using a large language model. A central transformer architecture fuses these features to predict disease-free survival. Model performance was evaluated on independent external datasets and compared with guideline-based risk stratification. Associations between model-derived risk scores and tumor microenvironment features were analyzed to assess biologic interpretability. Results A total of 1073 patients (mean age ± SD, 60.8 years ± 9.8; 550 male) were enrolled from five centers. On external datasets, DLRTransformer demonstrated robust prognostic performance (concordance index, 0.77-0.78), outperforming the guideline-based risk stratification (concordance index, 0.60-0.65). Risk scores were associated with tumor microenvironment phenotypes, including increased neoplastic cellularity and reduced tertiary lymphoid structures. A treatment-by-risk interaction was observed (interaction hazard ratio [HR], 0.14; 95% CI: 0.06, 0.32; P < .01). In propensity score-matched subcohorts, adjuvant therapy improved disease-free survival in high-risk patients (HR, 0.30; 95% CI: 0.11, 0.84; P = .02) but not in low-risk patients (HR, 1.70; 95% CI: 0.97, 2.99; P = .06). Conclusion The DLRTransformer improved postoperative risk stratification compared with guideline-based risk stratification and identified patients with stage I NSCLC who benefited from adjuvant therapy.

来源:Radiol Imaging Cancer,查看原文。版权归原作者所有。

引用

  1. Wang L, Zong Y, Li X, et al. Multimodal Transformer Integrating CT and Pathology for Postoperative Risk Stratification in Stage I Non-Small Cell Lung Cancer. Radiol Imaging Cancer. 2026. PMID: 42886039. doi:10.1148/rycan.250617

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。