METHODS: We conducted a retrospective study involving 508 NSCLC patients from three institutions, incorporating CT images and clinicopathologic data. Two radiomic scores and a deep network feature were constructed on three data sources in the 3D tumor region. Using these features, we developed and validated the \'Deep-RadScore,\' a deep learning radiomics model to predict prognostic factors, gene mutations, and immune molecule expression levels.
RESULTS: The Deep-RadScore exhibits strong discrimination for tumor molecular features. In the independent test cohort, it achieved impressive AUCs: 0.889 for lymphovascular invasion, 0.903 for pleural invasion, 0.894 for T staging; 0.884 for EGFR and ALK, 0.896 for KRAS and PIK3CA, 0.889 for TP53, 0.895 for ROS1; and 0.893 for PD-1/PD-L1. Fusing features yielded optimal predictive power, surpassing any single imaging feature. Correlation and interpretability analyses confirmed the effectiveness of customized deep network features in capturing additional imaging phenotypes beyond known radiomic features.
CONCLUSIONS: This proof-of-concept framework demonstrates that new biomarkers across imaging features and molecular phenotypes can be provided by fusing radiomic features and deep network features from multiple data sources. This holds the potential to offer valuable insights for radiological phenotyping in characterizing diverse tumor molecular alterations, thereby advancing the pursuit of non-invasive personalized treatment for NSCLC patients.
方法:我们进行了一项回顾性研究,包括来自三个机构的508名NSCLC患者,结合CT图像和临床病理数据。在3D肿瘤区域的三个数据源上构建了两个放射学评分和一个深度网络特征。使用这些功能,我们开发并验证了Deep-RadScore,一种用于预测预后因素的深度学习影像组学模型,基因突变,和免疫分子表达水平。
结果:Deep-RadScore对肿瘤分子特征表现出强烈的辨别能力。在独立测试队列中,它实现了令人印象深刻的AUC:0.889的淋巴管浸润,胸膜侵犯0.903,T分期为0.894;EGFR和ALK为0.884,KRAS和PIK3CA为0.896,TP53为0.889,ROS1为0.895;PD-1/PD-L1为0.893。融合功能产生了最佳预测能力,超越任何单一的成像功能。相关性和可解释性分析证实了定制的深度网络特征在捕获超出已知放射学特征的其他成像表型方面的有效性。
结论:这个概念验证框架表明,通过融合来自多个数据源的放射学特征和深度网络特征,可以提供跨成像特征和分子表型的新生物标志物。这具有为表征不同肿瘤分子改变的放射学表型提供有价值的见解的潜力。从而推进对NSCLC患者的非侵入性个性化治疗的追求。