文献速递胸部CT

深度学习影像组学特征通过反映肿瘤异质性和微环境预测肺腺癌患者的总生存期

Deep Learning Radiomic Signature Predicts the Overall Survival of Patients with Lung Adenocarcinoma by Reflecting the Tumor Heterogeneity and Microenvironment.
PubMed 文献 · Acad Radiol · 2025-10-09

该研究基于三个机构2019年1月至2024年1月的306例肺腺癌患者数据,利用ResNet50构建CT图像深度学习影像组学特征(DLRS),并用公共数据库外部验证。测试队列中DLRS预测1、3、5年OS的AUC分别为0.912、0.851、0.841,优于传统影像组学评分和临床模型;不同评分组间肿瘤异质性和微环境存在显著差异。

要点

  • DLRS预测肺腺癌1、3、5年OS的AUC分别为0.912、0.851、0.841,优于传统影像组学评分和临床模型。
  • 按DLRS分层的高、低评分组间生存时间存在显著差异。
  • 不同评分组间肿瘤异质性和微环境显著不同,并有不同基因表达模式。

核心结论

  • DLRS可通过反映肿瘤异质性和微环境有效预测肺腺癌患者预后。

研究设计与样本

  • 研究纳入三个机构2019年1月至2024年1月的306例符合条件的肺腺癌患者,使用ResNet50开发基于图像的深度学习影像组学特征(DLRS),并用pyradiomics包计算传统影像组学评分、构建临床模型,另从公共数据库The Cancer Imaging Archive获取外部队列进一步验证。

诊断标准与关键数值

  • 测试队列中DLRS预测1年、3年、5年OS的AUC(95%CI)分别为0.912(0.881-0.952)、0.851(0.824-0.901)、0.841(0.807-0.878)。

局限性

  • 原文未报告局限性

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

RATIONALE AND OBJECTIVES: The need for prediction of overall survival (OS) in patients with lung adenocarcinoma (LUAD) has been increasingly recognized. We aimed to generate a computed tomography-derived radiomic signature for predicting prognosis in LUAD patients, and then explored the relationship between radiomic features and tumor heterogeneity and microenvironment.

MATERIALS AND METHODS: Data of 306 eligible LUAD patients from three institutions were obtained between January 2019 and January 2024. The mainstream Residual Network 50 (ResNet50) was used to develop an image-based deep learning radiomic signature (DLRS). We developed a clinical model and calculated the conventional radiomics score using pyradiomics package. An external cohort from a public database called The Cancer Imaging Archive was obtained for further validation. We performed the time-dependent receiver operator characteristic curve to assess the performance of the models. We divided the whole dataset into high and low-score groups with the help of the DLRS. The differences in tumor heterogeneity and microenvironment between different score groups were investigated using the sequencing data from the corresponding LUAD cohort from the Cancer Genome Atlas.

RESULTS: In the test cohort, the DLRS outperformed the conventional radiomics score and clinical model, with the area under the curves (95%CI) for 1, 3, and 5-year OS of 0.912 (0.881-0.952), 0.851 (0.824-0.901), and 0.841 (0.807-0.878), respectively. Significant differences in survival time were observed between different groups stratified by this signature. It showed great discrimination, calibration, and clinical utility (all p<0.05). Distinct gene expression patterns were identified. The tumor heterogeneity and microenvironment significantly varied between different score groups.

CONCLUSION: The DLRS could effectively predict the prognosis of LUAD patients by reflecting the tumor heterogeneity and microenvironment.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Dai C, Huang B, Yu Z, et al. Deep Learning Radiomic Signature Predicts the Overall Survival of Patients with Lung Adenocarcinoma by Reflecting the Tumor Heterogeneity and Microenvironment. Acad Radiol. 2025. PMID: 41073175. doi:10.1016/j.acra.2025.09.033

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。