Non-Invasive Fuhrman Grading of Clear Cell Renal Cell Carcinoma Using Computed Tomography Radiomics Features and Machine Learning

TLDR: In this article, three image preprocessing techniques (Laplacian of Gaussian, wavelet filter, and discretization of the intensity values) were applied on tumor volumes to identify optimal classification methods for CT radiomics-based preoperative prediction of clear cells renal cell carcinoma (ccRCC) grade.

Abstract: Purpose: To identify optimal classification methods for computed tomography (CT) radiomics-based preoperative prediction of clear cells renal cell carcinoma (ccRCC) grade. Methods and material: Seventy one ccRCC patients were included in the study. Three image preprocessing techniques (Laplacian of Gaussian, wavelet filter, and discretization of the intensity values) were applied on tumor volumes. In total, 2530 radiomics features (tumor shape and size, intensity statistics, and texture) were extracted from each segmented tumor volume. Univariate analysis was performed to assess the association of each feature with the histological condition. In the case of multivariate analysis, the following was implemented: three feature selection including the least absolute shrinkage and selection operator (LASSO), students t-test and minimum Redundancy Maximum Relevance (mRMR) algorithms. These selected features were then used to construct three classification models (SVM, random forest, and logistic regression) to discriminate the high from low-grade ccRCC at nephrectomy. Lastly, multivariate model performance was evaluated on the bootstrapped validation cohort using the area under receiver operating characteristic curve (AUC). Results: Univariate analysis demonstrated that among different image sets, 128 bin discretized images have statistically significant different (q-value < 0.05) texture parameters with a mean of AUC 0.74 (q-value < 0.05). The three ML-based classifier shows proficient discrimination of the high from low-grade ccRCC. The AUC was 0.78 in logistic regression, 0.62 in random forest, and 0.83 in SVM model, respectively. Conclusion: Radiomics features can be a useful and promising non-invasive method for preoperative evaluation of ccRCC Fuhrman grades. Key words: RCC, Radiomics, Machine Learning, Computed Tomography