A CT-based radiomics nomogram for differentiation of benign and malignant small renal masses (≤4 cm).

RATIONALE AND OBJECTIVES

Based on radiomics signature and clinical data, to develop and verify a radiomics nomogram for preoperative distinguish between benign and malignant of small renal masses (SRM).

MATERIALS AND METHODS

One hundred and fifty-six patients with malignant (n = 92) and benign (n = 64) SRM were divided into the following three categories: category A, typical angiomyolipoma (AML) with visible fat; category B, benign SRM without visible fat, including fat-poor angiomyolipoma (fp-AML), and other rare benign renal tumors; category C, malignant renal tumors. At the same time, one hundred and fifty-six patients included in the study were divided into the training set (n = 108) and test set (n = 48). Respectively from corticomedullary phase (CP), nephrogram phase (NP) and excretory phase (EP) CT images to extract the radiomics features, and the optimal features were screened to establish the logistic regression model and decision tree model, and computed the radiomics score (Rad-score). Demographics and CT findings were evaluated and statistically significant factors were selected to construct a clinical factors model. The radiomics nomogram was established by merging Rad-score and selected clinical factors. The Akaike information criterion (AIC) values and the area under the curve (AUC) were used to compare model discriminant performance, and decision curve analysis (DCA) was used to assess clinical usefulness.

RESULTS

Seven, fifteen, nineteen, and seventeen distinguishing features were obtained in the CP, NP, EP, and three-phase joint, respectively, and the logistic regression and decision tree models were built based on this features. In the training set, the logistic regression model works better than the decision tree model for distinguishing categories A and B from category C, with the AUC of CP, NP, EP and three-phase joint were 0.868, 0.906, 0.937 and 0.975, respectively. The radiomics nomogram constructed based on the three-phase joint Rad-score and selected clinical factor performed well on the training set (AUC, 0.988; 95% CI, 0.974-1.000) for differentiation of categories A and B from category C. In the test set, the AUC of clinical factors model, radiomics signature and radiomics nomogram for discriminating categories A and B from category C were 0.814, 0.954 and 0.968, respectively; for the identification of category A from category C, the AUC of the three models were 0.789, 0.979, 0.985, respectively; for discriminating category B from category C, the AUC of the three models were 0.853, 0.915, 0.946, respectively. The radiomics nomogram had better discriminative than the clinical factors model in both training and test sets (P < 0.05). The radiomics nomogram (AIC = 40.222) with the lowest AIC value was considered the best model compared with that of the clinical factors model (AIC = 106.814) and the radiomics signature (AIC = 44.224). The DCA showed that the radiomics nomogram have better clinical utility than the clinical factors model and radiomics signature.

CONCLUSIONS

The logistic regression model has better discriminative performance than the decision tree model, and the radiomics nomogram based on Rad-score of three-phase joint and clinical factors has a good predictive effect in differentiating benign from malignant of SRM, which may help clinicians develop accurate and individualized treatment strategies.