A preliminary radiomics model for predicting perirenal fat invasion on renal cell carcinoma with contrast-enhanced CT images

Objective: The aim is to develop a radiomics model based on contrast-enhanced CT scans for preoperative prediction of perirenal fat invasion (PFI) in patients with renal cell carcinoma (RCC).

Methods: The CT data of 131 patients with pathology-confirmed PFI status (64 positives) were retrospectively collected and randomly assigned to the training and test datasets. The kidneys and the masses were annotated by semi-automatic segmentation. Eight types of regions of interest (ROI) were chosen for the training of the radiomics models. The areas under the curves (AUCs) from the receiver operating characteristic (ROC) curve analysis were used to analyze the diagnostic performance. Eight types of models with different ROIs have been developed. The models with the highest AUC in the test dataset were used for construction of the corresponding final model, and comparison with radiologists' diagnosis.

Results: The AUCs of the models for each ROI was 0.783-0.926, and there was no statistically significant difference between them (P > 0.05). Model 4 was using the ROI of the outer half-ring which extended along the edge of the mass at the outer edge of the kidney into the perirenal fat space with a thickness of 3 mm. It yielded the highest AUC (0.926) and its diagnostic accuracy was higher than the radiologists' diagnosis.

Conclusion: We have developed and validated a radiomics model for prediction of PFI on RCC with contrast-enhanced CT scans. The model proved to be more accurate than the radiologists' diagnosis.