Radiomics-based tumor heterogeneity augments clinicopathological models for predicting recurrence in high-risk clear cell renal cell carcinoma after nephrectomy

Zhan Feng ¹, Piao Yang ², Yaoyao Wu ²

⁰The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. gerxyuan@zju.edu.cn.

Abdominal Radiology (new York) +

|

July 11, 2025

View abstract on PubMed

Summary

CT radiomics improves recurrence prediction for high-risk clear cell renal cell carcinoma (ccRCC) after surgery. Integrating radiomics with clinical factors enhances risk stratification for better treatment decisions.

Area Of Science

Oncology
Radiology
Medical Imaging

Background

Clear cell renal cell carcinoma (ccRCC) is the most common subtype of kidney cancer.
Accurate prediction of recurrence risk is crucial for high-risk ccRCC patients post-nephrectomy.
Current clinicopathological models have limitations in precise risk stratification.

Purpose Of The Study

To assess the association between CT radiomics-based tumor heterogeneity and recurrence-free survival (RFS) in high-risk ccRCC.
To evaluate if integrating CT radiomics with clinicopathological models improves recurrence risk prediction.
To inform adjuvant treatment decisions for ccRCC patients.

Main Methods

Retrospective analysis of 194 high-risk ccRCC patients undergoing nephrectomy.
Development of a radiomics model using random survival forest on pre-operative CT images.
Evaluation of radiomics, Leibovich score, and combined models using survival analysis and time-dependent ROC curves.

Main Results

The radiomics model showed superior predictive performance over the Leibovich score in the test set.
Higher time-dependent AUCs and better calibration were observed for the radiomics model.
The combined model offered the highest net benefit for predicting 2- to 3-year recurrence risk.

Conclusions

CT radiomics offers incremental prognostic value for high-risk ccRCC, surpassing conventional models.
This imaging-based approach enables more precise recurrence risk stratification.
Potential to optimize surveillance and adjuvant therapy trial design in precision oncology.

Keywords:

Clear cell renal cell carcinoma Prognosis Radiomics