Guo Wentian, Li Hui, Zhu Yitan, Lan Li, Yang Shengjie, Drukker Karen, Morris Elizabeth, Burnside Elizabeth, Whitman Gary, Giger Maryellen L, Ji Yuan
University of Chicago, Department of Public Health Sciences, 5841 South Maryland Avenue MC2000, Chicago, Illinois 60637, United States; Fudan University, School of Public Health, 130 Dongan Road, Shanghai 200032, China.
University of Chicago , Department of Radiology, 5841 South Maryland Avenue, Chicago, Illinois 60637, United States.
J Med Imaging (Bellingham). 2015 Oct;2(4):041007. doi: 10.1117/1.JMI.2.4.041007. Epub 2015 Sep 23.
Genomic and radiomic imaging profiles of invasive breast carcinomas from The Cancer Genome Atlas and The Cancer Imaging Archive were integrated and a comprehensive analysis was conducted to predict clinical outcomes using the radiogenomic features. Variable selection via LASSO and logistic regression were used to select the most-predictive radiogenomic features for the clinical phenotypes, including pathological stage, lymph node metastasis, and status of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). Cross-validation with receiver operating characteristic (ROC) analysis was performed and the area under the ROC curve (AUC) was employed as the prediction metric. Higher AUCs were obtained in the prediction of pathological stage, ER, and PR status than for lymph node metastasis and HER2 status. Overall, the prediction performances by genomics alone, radiomics alone, and combined radiogenomics features showed statistically significant correlations with clinical outcomes; however, improvement on the prediction performance by combining genomics and radiomics data was not found to be statistically significant, most likely due to the small sample size of 91 cancer cases with 38 radiomic features and 144 genomic features.
整合了来自癌症基因组图谱（The Cancer Genome Atlas）和癌症影像存档（The Cancer Imaging Archive）的浸润性乳腺癌的基因组和放射组学成像特征，并进行了全面分析，以利用放射基因组学特征预测临床结果。通过套索（LASSO）和逻辑回归进行变量选择，以选择针对临床表型（包括病理分期、淋巴结转移以及雌激素受体（ER）、孕激素受体（PR）和人表皮生长因子受体2（HER2）状态）的最具预测性的放射基因组学特征。进行了基于受试者工作特征（ROC）分析的交叉验证，并将ROC曲线下面积（AUC）用作预测指标。在病理分期、ER和PR状态的预测中获得的AUC高于淋巴结转移和HER2状态的预测。总体而言，单独的基因组学、单独的放射组学以及组合的放射基因组学特征的预测性能与临床结果显示出统计学上的显著相关性；然而，未发现通过组合基因组学和放射组学数据来提高预测性能具有统计学意义，这很可能是由于样本量较小，仅有91例癌症病例，具有38个放射组学特征和144个基因组特征。
