AUTHOR=Gao Ruizhi , Qin Hui , Lin Peng , Ma Chenjun , Li Chengyang , Wen Rong , Huang Jing , Wan Da , Wen Dongyue , Liang Yiqiong , Huang Jiang , Li Xin , Wang Xinrong , Chen Gang , He Yun , Yang Hong 

TITLE=Development and Validation of a Radiomic Nomogram for Predicting the Prognosis of Kidney Renal Clear Cell Carcinoma

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.613668

DOI=10.3389/fonc.2021.613668

ISSN=2234-943X

ABSTRACT=Purpose: The present study aims to comprehensively investigate the prognostic value of a radiomics nomogram that integrates contrast-enhanced computed tomography (CECT) radiomics signature and clinical-pathological parameters in kidney renal clear cell carcinoma (KIRC).
Methods: A total of 136 and 78 KIRC patients from training and validation cohort were included in the retrospective study.  The intraclass coefficient of correlation (ICC) was used to assessed reproducibility of radiomics features. Univariate Cox analysis and least absolute shrinkage and selection operator (LASSO) as well as multivariate Cox analysis were utilized to construct radiomics signature and clinical signature in the training cohort and to validate in the validation cohort. A prognostic nomogram was established containing radiomics signature and clinicopathological parameters by using multivariate Cox analysis. The predictive ability of the nomogram (relative operating characteristic curve [ROC], concordance index [C-index], Hosmer-Lemeshow test, and calibration curve) was evaluated in the training and the validation cohort. Patients were split into high- and low-risk groups, and the Kaplan-Meier (KM) method was conducted to identify the forecasting ability of the established models. In addition, genes related with a radiomics risk score were determined by weighted correlation network analysis (WGCNA) and were used to conduct functional analysis.
Results: A total of 2,944 radiomics features were acquired from the tumor volumes of interest (VOI). The radiomics signature, including ten selected features, and the clinical signature, including three selected clinical variables, showed good performance in the training and validation cohort (area under the curve [AUC], 0.897 and 0.712 for the radiomics signature; 0.827 and 0.822 for the clinical signature, respectively). The radiomics prognostic nomogram showed favorable performance and calibration in the training cohort (AUC, 0.896, C-index, 0.846), which was verified in the validation cohort (AUC, 0.768). KM curves indicated that the progression-free interval (PFI) time was dramatically shorter in the high-risk group than in the low-risk group. The functional analysis indicated that radiomics signatures were significantly associated with T cell activation.
Conclusions: The nomogram combined with CECT radiomics and clinicopathological signatures exhibits excellent power in predicting the PFI of KIRC patients, which may aid in clinical management and prognostic evaluation of cancer patients.