AutoML Radiomics-Based Classification of Patients with Renal Cell Carcinoma Using Non-Contrast Enhanced Magnetic Resonance Imaging

Motivation: Kidney cancer is often diagnosed as either clear cell renal carcinoma (ccRCC) or non-clear cell renal carcinoma (non-ccRCC) to determine treatment recommendations. Additionally, many patients with kidney cancer cannot receive contrast medium due to renal function disorders. Goal(s): for the distinction of ccRCC from other types of RCC without contrast medium administrationApproach: A model using automated machine learning (AutoML) based on radiomics features Results: Our results indicate that the best model from the AutoML process demonstrated a mean sensitivity of 0.819 and a mean specificity of 0.729 in distinguishing between ccRCC and non-ccRCC. Impact: To demonstrated that the TPOP-radiomics-based classification model can effectively discriminate between ccRCC and non-ccRCC using MRI without the need for contrast medium.