Improving the diagnostic accuracy of small renal masses: Integration of radiomics and clear cell likelihood scores in multiparametric MRI

Abstract

Objectives

Accurate diagnosis of small renal masses is crucial for treatment planning. Combining radiomics analysis with the Clear Cell Likelihood Score (ccLS) in multiparametric MRI can effectively assess malignancy risk. This study aimed to evaluate the contribution of MRI-based radiomics analysis to the diagnostic performance of the ccLS in differentiating clear cell renal carcinoma (ccRCC).

Materials and methods

This retrospective study included patients with cT1a renal masses who underwent preoperative MRI and nephrectomy. Radiomic features were extracted from multiparametric MRI images, including T2-weighted imaging and contrast-enhanced T1-weighted imaging sequences. Qualitative assessment was performed using the ccLS version 2.0, based on multiparametric MRI findings. The diagnostic efficacies of the ccLS, radiomic analysis, and the combination of the two methods in differentiating ccRCCs were analyzed.

Results

A total of 72 small renal masses (43 ccRCC and 29 non-ccRCC) from 68 patients were evaluated. Using ccLS alone, lesions classified as ccLS ≥ 4 were identified as ccRCCs with a sensitivity of 83.3% and specificity of 73.3%. Radiomic analysis revealed significant differences between ccRCC and non-ccRCC lesions, with AUC values ranging from 0.48 to 0.87 across different features. The combined use of radiomic features and ccLS improved the differentiation of ccRCCs, achieving a sensitivity of 90.7%, specificity of 78.4%, and an AUC of 0.88. In lesions classified as ccLS 3 (equivocal), radiomic analysis alone distinguished ccRCCs with 100% sensitivity and 62.5% specificity.

Conclusions

This study’s findings demonstrated that radiomics analysis successfully differentiated lesions with a ccLS 3 and that the use of radiomic analysis in combination with ccLS successfully differentiated ccRCC and non-ccRCC lesions.