Generation of automated nephrometry scores through direct prediction of each component.

Authors

Abstract

To evaluate whether a deep learning model could automate R.E.N.A.L. nephrometry score generation and predict clinically significant outcomes. A ResNet-50 neural network was trained on 599 patients from the 2023 KiTS Challenge dataset to predict numeric R.E.N.A.L. score components (excluding the anterior/posterior designation) using preoperative CT images and expert-derived segmentation masks. Five-fold cross-validation produced automated scores, which were compared with consensus human scores from six raters. Associations with clinical outcomes were assessed using logistic regression and receiver operating characteristic analysis. External validation was performed in 1,806 patients from an independent health system, with human scores available for 193 cases. Automated scores showed strong correlation with human consensus (Spearman's ρ = 0.77), outperforming individual raters (ρ = 0.42, p < 0.01). Automated scores demonstrated higher predictive accuracy for partial versus radical nephrectomy (AUC 0.87 vs. 0.80, p = 0.0012), malignancy (AUC 0.72 vs. 0.62, p = 0.0002), and pathologic stage ≥pT3 (AUC 0.81 vs. 0.72, p = 0.0003). In the external cohort, automated scores correlated with human scoring and predicted radical versus partial nephrectomy (AUC 0.78), higher stage disease (AUC 0.72), high-grade pathology (AUC 0.64), and open surgery (AUC 0.59). Limitations include reliance on CT imaging and cohort-specific factors. Deep learning-based nephrometry scores are reproducible, correlate with human scoring, and can predict multiple clinical outcomes across institutional cohorts. This approach reduces subjectivity, streamlines assessment, and supports integration into radiology workflows to improve kidney cancer care.

Tags

Topics