Abstract:
RCC is the most prevalent renal malignancy and ccRCC is the most common subtype of RCC. It is reported that the prognosis has a strong association with VHL alteration. It is also reported that PBRM1 gene, second most common alteration in ccRCC, has a critical role in ccRCC progression and great potential to identify ccRCC. Moreover, available treatment opportunities are mostly related to stage information. The treatment options are limited in stage 3 and 4. Studies of ccRCC indicate that there is a correlation between cancer CT imaging features and gene expression (radiogenomics). We hypothesized that from quantitative 2D CT images via one slice with the biggest tumor, both VHL and PBRM1 mutations and stages can be predicted with accuracy using ML algorithms. TCGA-KIRC data were collected and tumors were segmented by an expert radiologist. Classification was done by using CL and ANN on MATLAB. Our results showed that Fine Gaussian SVM model is able to predict VHL and NON-VHL data with 68.6%, k-NN with Random Subspace model is able to predict PBRM1 and NON-PBRM1 with 84.9% ,and ANN predicted stages with 91.90% accuracies. From this study, it appears that ML-based quantitative 2D CT analysis using one slice for each patient is a feasible and potential method for predicting the status of VHL and PBRM1 mutations and stages for ccRCC patients.|Keywords : Renal Cell Carcinoma (RCC) , Clear cell Renal Cell Carcinoma (ccRCC), Von Hippel Lindau (VHL), Polybromo-1 (PBRM1), Computed Tomography (CT), Machine Learning (ML), Artificial Neural Network (ANN), Classification Learner (CL).
