Prediction of Benign and Malignant Small Renal Masses Using CT-Derived Extracellular Volume Fraction: An Interpretable Machine Learning Model.
Authors
Affiliations (2)
Affiliations (2)
- Department of Radiology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, Zhejiang Province, China (Y.G., Q.F., Y.L., D.Y., L.C., G.B.); Key Laboratory of Structural Malformations in Children of Zhejiang Province, Wenzhou, Zhejiang Province, China (Y.G., Q.F., Y.L., D.Y., L.C., G.B.).
- Department of Radiology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, Zhejiang Province, China (Y.G., Q.F., Y.L., D.Y., L.C., G.B.); Key Laboratory of Structural Malformations in Children of Zhejiang Province, Wenzhou, Zhejiang Province, China (Y.G., Q.F., Y.L., D.Y., L.C., G.B.). Electronic address: [email protected].
Abstract
We developed a machine learning model comprising morphological characteristics, enhancement dynamics, and extracellular volume (ECV) fractions for distinguishing malignant and benign small renal masses (SRMs), supporting personalised management. This retrospective analysis involved 230 patients who underwent SRM resection with preoperative imaging, including 185 internal and 45 external cases. The internal cohort was split into training (n=136) and validation (n=49) sets. Histopathological evaluation categorised the lesions as renal cell carcinomas (n=183) or benign masses (n=47). Eleven multiphasic contrast-enhanced computed tomography (CT) parameters, including the ECV fraction, were manually measured, along with clinical and laboratory data. Feature selection involved univariate analysis and least absolute shrinkage and selection operator regularisation. Feature selection informed various machine learning classifiers, and performance was evaluated using receiver operating characteristic curves and classification tests. The optimal model was interpreted using SHapley Additive exPlanations (SHAP). The analysis included 183 carcinoma and 47 benign SRM cases. Feature selection identified seven discriminative parameters, including the ECV fraction, which informed multiple machine learning models. The Extreme Gradient Boosting model incorporating ECV exhibited optimal performance in distinguishing malignant and benign SRMs, achieving area under the curve values of 0.993 (internal training set), 0.986 (internal validation set), and 0.951 (external test set). SHAP analysis confirmed ECV as the top contributor to SRM characterisation. The integration of multiphase contrast-enhanced CT-derived ECV fraction with conventional contrast-enhanced CT parameters demonstrated diagnostic efficacy in differentiating malignant and benign SRMs.