Search

To evaluate the efficiency of CT-based peritumoral radiomics signatures of clear cell renal cell carcinoma (ccRCC) for malignancy grading in preoperative prediction. 203 patients with pathologically confirmed as ccRCC were retrospectively enrolled in this study. All patients were categorized into training set (n = 122) and validation set (n = 81). For each patient, two types of volumes of interest (VOI) were masked on CT images. One type of VOIs was defined as the tumor mass volume (TMV), which was masked by radiologists delineating the outline of all contiguous slices of the entire tumor, while the other type defined as the peritumoral tumor volume (PTV), which was automatically created by an image morphological method. 1760 radiomics features were calculated from each VOI, and then the discriminative radiomics features were selected by Pearson correlation analysis for reproducibility and redundancy. These selected features were investigated their validity for building radiomics signatures by mRMR feature ranking method. Finally, the top ranked features, which were used as radiomics signatures, were input into a classifier for malignancy grading. The prediction performance was evaluated by receiver operating characteristic (ROC) curve in an independent validation cohort. The radiomics signatures of PTV showed a better performance on malignancy grade prediction of ccRCC with AUC of 0.807 (95% CI 0.800–0.834) in train data and 0.848 (95% CI 0.760–0.936) in validation data, while the radiomics signatures of TMV with AUC of 0.773 (95% CI 0.744–0.802) in train data and 0.810 (95% CI 0.706–0.914) in validation data. The CT-based peritumoral radiomics signature is a potential way to be used as a noninvasive tool to preoperatively predict the malignancy grades of ccRCC.

Accurate preoperative differential diagnosis of fat-poor angiomyolipoma (fp-AML) and clear cell renal cell carcinoma (ccRCC) is essential for proper treatment planning. In this paper, we develop an effective radiomics model for reliable noninvasive discrimination of fp-AML from ccRCC, which incorporates a sophisticated feature selection procedure and a sparse radial basis function neural network (sRBFNN). Specifically, 774 three-dimensional radiomics features are first extracted from contrast-enhanced computed tomography (CECT) images. Pearson’s correlation matrices and Welch’s t-test are used to remove the insignificant features, then sequential forward floating selection method is utilized to select the discriminative features. Finally, the sRBFNN is employed for classification. The radiomics model is examined by leave-one-out cross validation and yields the best performance of 90.00%, 66.67%, 100.0%, and 0.9173 in terms of prediction accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curves, respectively. Furthermore, the reliability of the predictions is verified by evaluating the probabilistic outputs of the sRBFNN. The experimental results demonstrate that the developed radiomics model has great potential in the noninvasive discrimination of fp-AML from ccRCC.