AUTHOR=Liu Qin , Li Jie , Xu Lin , Wang Jiasi , Zeng Zhaoping , Fu Jiangping , Huang Xuan , Chu Yanpeng , Wang Jing , Zhang Hong-Yu , Zeng Fanxin 

TITLE=Individualized Prediction of Colorectal Cancer Metastasis Using a Radiogenomics Approach

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.620945

DOI=10.3389/fonc.2021.620945

ISSN=2234-943X

ABSTRACT=Objectives: To evaluate whether incorporating the radiomics, genomics, and clinical features allow prediction of metastasis in colorectal cancer (CRC) and to develop a preoperative nomogram for predicting metastasis. 
Methods: We retrospectively analyzed radiomics features of computed tomography (CT) images in 134 patients (62 in the primary cohort, 28 in the validation cohort and 44 in the independent-test cohort) clinicopathologically diagnosed with CRC at Dazhou Central Hospital from February 2018 to October 2019. All patients were collected tumor tissues for RNA sequencing and obtained Clinical data from medical records. A total of 854 radiomic features were extracted from enhanced venous-phase CT of CRC. Least absolute shrinkage and selection operator (LASSO) regression analysis was utilized for data dimension reduction, feature screen, and radiomics signature development. Multivariable logistic regression analysis was performed to build a multi-scale predicting model incorporating the radiomics, genomics, and clinical features. The receiver operating characteristic (ROC), calibration curve, and decision curve were conducted to evaluate the performance of the nomogram.
Results: The radiomics signature based on 16 selected radiomics features showed good performance in metastasis assessment in both primary [area under curve (AUC)=0.945, 95% confidence interval (CI): 0.892-0.998] and validation cohorts (AUC=0.754, 95% CI: 0.570-0.938). The multi-scale nomogram model contained radiomics features signatures, 4 genes expression related to cell cycle pathway, and CA19-9 level. The multi-scale model showed good discrimination performance in the primary cohort (AUC = 0.981, 95% CI: 0.953-1.000), the validation cohort (AUC = 0.822, 95% CI: 0.635-1.000) and the independent-test cohort (AUC = 0.752, 95% CI: 0.608-0.896) and good calibration. Decision curve analysis confirmed the clinical application value of the multi-scale model.
Conclusion: This study presented a multi-scale model that incorporated the radiological eigenvalues, genomics features, and CA19-9, which could be conveniently utilized to facilitate the individualized preoperatively assessing metastasis in CRC patients.