Machine learning-based multiparametric CT radiomics for predicting microvascular invasion before nephrectomy in clear cell renal cell carcinoma.

Purpose: This study aimed to investigate the value of integrating computed tomography (CT)-based tumor radiomics features with clinical parameters for preoperative prediction of microvascular invasion (MVI) in clear cell renal cell carcinoma (ccRCC).

Methods: We retrospectively analyzed data from a single-center cohort of ccRCC patients. Radiomics features were extracted from preoperative multiphasic CT scans (unenhanced, corticomedullary, and nephrographic phases). Following dimensionality reduction and feature selection, eight machine learning algorithms were evaluated to identify the optimal radiomics model. Independent clinical predictors were determined through univariate and multivariate analyses. A nomogram integrating the radiomics signature (rad-score) with significant clinical parameters was subsequently developed. Model performance was assessed using the area under the curve (AUC), decision curve analysis (DCA), and calibration curve analysis (CAC).

Results: Of 143 initially enrolled patients, 110 met inclusion criteria after screening, with 5502 radiomics features extracted. The support vector classifier (SVM) model demonstrated the highest discriminative ability, achieving mean AUCs of 0.976 (training cohort) and 0.892 (test cohort), significantly outperforming the clinical model (training AUC = 0.935, test AUC = 0.933). The nomogram showed superior diagnostic performance, with AUCs of 0.958 (test). DCA and CAC confirmed its clinical utility and robustness.

Conclusions: Multiparametric CT radiomics models enable non-invasive prediction of MVI status in ccRCC, with the SVM-based algorithm showing optimal performance. The integrated nomogram provides excellent and consistent diagnostic accuracy, offering a valuable preoperative tool for clinical decision-making.