Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer.
发表日期： 2017.03.31 来源：Cancer Research. 2017 Jul 15;77(14):3922-3930.
Emmanuel Rios Velazquez1, Chintan Parmar1, Ying Liu2,3 , Thibaud P. Coroller1, Gisele Cruz4, Olya Stringfield2, Zhaoxiang Ye3, Mike Makrigiorgos1, Fiona Fennessy4 , Raymond H. Mak1, Robert Gillies2, John Quackenbush5,6,7 and Hugo J.W.L. Aerts8,4,5.
1. Department of Radiation Oncology Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts.
2. Departments of Cancer Imaging and Metabolism, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida.
3.Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China.
4. Department of Radiology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts.
5. Department of Biostatistics & Computational Biology, Dana-Farber Cancer Institute, Boston, Massachusetts.
6. Department of Cancer Biology, Dana-Farber Cancer Institute, Boston, Massachusetts.
7. Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts.
8. Department of Radiation Oncology Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts.
肿瘤的特征在于体细胞突变，其驱动生物过程最终反映在肿瘤表型中。关于放射摄影术表型，现有的理解与特定突变的存在通常不相关，人工智能（AI）方法可以通过使用预定义的工程算法或自动深度学习方法的过程（也称为影像组学）自动量化表型特征。 在这里，我们证明了通过对763位肺腺癌患者的独立数据集进行体细胞突变测试和计算机断层扫描（CT）图像分析的的综合分析，成像表型如何与体细胞突变相关联。我们开发了能够区分探究组（n = 353）中的肿瘤基因型的影像组学特征，并在独立的验证组（n = 352）中进行了验证。所有的影像组学标记显著优于常规放射影像学预测因子（肿瘤体积和最大直径）。我们发现与放射摄影术异质性相关的影像组学标记，成功地区分EGFR +和EGFR-病例（AUC = 0.69）。 将该特征与EGFR状态临床模型（AUC = 0.70）相结合，显著提高了预测精度（AUC = 0.75）。最佳表现特征能够区分EGFR +和KRAS +肿瘤（AUC = 0.80），并且当与临床模型（AUC = 0.81）组合时，其性能大大提高（AUC = 0.86）。 KRAS + / KRAS-影像组学标记也表现出显著差异，尽管性能比较低（AUC = 0.63），并且没有提高KRAS状态的临床预测指标的准确性。 我们的研究结果表明，通过影像组学可以预测体细胞突变驱动的特异的放射照相表型。这项工作因其非侵入性，反复和低成本地应用的特点，对于在临床中使用基于成像的生物标志物具有重要的影响。
Tumors are characterized by somatic mutations that drive biological processes ultimately reflected in tumor phenotype. With regard to radiographic phenotypes, generally unconnected through present understanding to the presence of specific mutations, artificial intelligence methods can automatically quantify phenotypic characters by using predefined, engineered algorithms or automatic deep-learning methods, a process also known as radiomics. Here we demonstrate how imaging phenotypes can be connected to somatic mutations through an integrated analysis of independent datasets of 763 lung adenocarcinoma patients with somatic mutation testing and engineered CT image analytics. We developed radiomic signatures capable of distinguishing between tumor genotypes in a discovery cohort (n = 353) and verified them in an independent validation cohort (n = 352). All radiomic signatures significantly outperformed conventional radiographic predictors (tumor volume and maximum diameter). We found a radiomic signature related to radiographic heterogeneity that successfully discriminated between EGFR+ and EGFR- cases (AUC = 0.69). Combining this signature with a clinical model of EGFR status (AUC = 0.70) significantly improved prediction accuracy (AUC = 0.75). The highest performing signature was capable of distinguishing between EGFR+ and KRAS+ tumors (AUC = 0.80) and, when combined with a clinical model (AUC = 0.81), substantially improved its performance (AUC = 0.86). A KRAS+/KRAS- radiomic signature also showed significant albeit lower performance (AUC = 0.63) and did not improve the accuracy of a clinical predictor of KRAS status. Our results argue that somatic mutations drive distinct radiographic phenotypes that can be predicted by radiomics. This work has implications for the use of imaging-based biomarkers in the clinic, as applied noninvasively, repeatedly, and at low cost.