CT-Based Radiomics in the Characterization of Solid Renal Tumors: A Systematic Review.

Area of Science:

• Medical Imaging
• Oncology
• Radiology

Background:

• Renal cell carcinoma (RCC) presents histological heterogeneity, challenging differentiation from benign renal tumors like fat-poor angiomyolipoma (fpAML) and renal oncocytoma (RO) using conventional CT.
• This diagnostic challenge can lead to overtreatment due to surgical intervention for benign conditions.

Purpose of the Study:

• To systematically review the diagnostic performance of CT-based radiomics in characterizing solid renal tumors.
• To evaluate radiomics' effectiveness in differentiating benign tumors from RCC, clear cell RCC (ccRCC) from non-ccRCC, fpAML from RCC, and RO from RCC.

Main Methods:

• A systematic literature search was performed in PubMed/MEDLINE, Cochrane, and Scopus databases for studies published between 2012 and 2025.
• The review focused on studies evaluating CT-based radiomics for characterizing solid renal tumors, specifically in differentiating key subtypes and benign from malignant lesions.

Main Results:

• The review assessed 47 studies involving 11,999 patients, demonstrating high diagnostic performance for CT-based radiomics across all evaluated categories.
• Median Area Under the Curve (AUC) values ranged from 0.830 for benign vs. malignant differentiation to 0.912 for fpAML vs. RCC.
• Combined radiomic features with clinical parameters in nomograms consistently achieved the highest predictive accuracy.

Conclusions:

• CT-based radiomics offers a promising non-invasive and objective tool for renal tumor characterization, potentially minimizing unnecessary surgeries and facilitating personalized treatment strategies.
• Widespread clinical implementation is hindered by the need for standardized protocols, automated segmentation tools, and prospective, multicenter validation studies.