Radiomic profiling of clear cell renal cell carcinoma reveals subtypes with distinct prognoses and molecular pathways

Background: To identify radiomic subtypes of clear cell renal cell carcinoma (ccRCC) patients with distinct clinical significance and molecular characteristics reflective of the heterogeneity of ccRCC. Methods: Quantitative radiomic features of ccRCC were extracted from preoperative CT images of 160 ccRCC patients. Unsupervised consensus cluster analysis was performed to identify robust radiomic subtypes based on these features. The Kaplan-Meier method and chi-square test were used to assess the different clinicopathological characteristics and gene mutations among the radiomic subtypes. Subtype-specific marker genes were identified, and gene set enrichment analyses were performed to reveal the specific molecular characteristics of each subtype. Moreover, a gene expression-based classifier of radiomic subtypes was developed using the random forest algorithm and tested in another independent cohort ( n = 101). Results: Radiomic profiling revealed three ccRCC subtypes with distinct clinicopathological features and prognoses. VHL, MUC16, FBN2 , and FLG were found to have different mutation frequencies in these radiomic subtypes. In addition, transcriptome analysis revealed that the dysregulation of cell cycle-related pathways may be responsible for the distinct clinical significance of the obtained subtypes. The prognostic value of the radiomic subtypes was further validated in another independent cohort (log-rank P = 0.015). Conclusion: In the present multi-scale radiogenomic analysis of ccRCC, radiomics played a central role. Radiomic subtypes could help discern genomic alterations and non-invasively stratify ccRCC patients.

Automated summary

In this study, radiomic subtypes of ccRCC patients were identified using quantitative radiomic features extracted from preoperative CT images. These subtypes showed distinct clinicopathological features, gene mutations, and molecular characteristics. A gene expression-based classifier of radiomic subtypes was developed and validated, showing the potential of radiomics in discerning genomic alterations and stratifying ccRCC patients non-invasively.