EVALUATION OF RADIOMICS AND MACHINE LEARNING IN IDENTIFICATION OF AGGRESSIVE TUMOR FEATURES IN RENAL CELL CARCINOMA (RCC)

Abstract

The purpose of this study was to evaluate the use of CT radiomics features and machine learning analysis to identify aggressive tumor features, including high nuclear grade (NG) and sarcomatoid (sarc) features, in large Renal Cell Carcinomas (RCCs). CT-based, volumetric radiomics analysis was performed on non-contrast (NC) and portalvenous (PV) phase multidetector computed tomography (MDCT) images of large (>7 cm) untreated RCCs in 141 patients (46W/95M, mean age 60 years). Machine learning analysis was applied to the extracted radiomics data to evaluate for association with high NG (grade 3-4), with multichannel analysis for NG performed in a subset of patients (n=80). A similar analysis was performed in a sarcomatoid rich cohort (n=43, 31M/12F, meanage63.7yrs) using sizematchednon-sarcomatoid controls (n=49) for identification of sarcomatoid change. The XG Boost Model performed best on the tested data. After manual and machine feature extraction, models consisted of 3, 7, 5, 10 radiomics features for NC sarc, PV sarc, NC NG and PV NG respectively. The area under the receiver operating characteristic curve (AUC) for these models was 0.59, 0.65, 0.69 and 0.58 respectively. The multichannel NG model extracted 6 radiomic features using the features election strategy and showed an AUC of 0.67. We found statistically significant but weak associations between aggressive tumor features (high nuclear grade, sarcomatoid features) in large RCC using 3D radiomics and machine learning analysis.