Abstract
Autosomal dominant polycystic kidney disease (ADPKD) is a prevalent hereditary disorder characterized by the development and growth of fluid-filled cysts, resulting in a decline in kidney function. Beyond total kidney and cyst volume quantification, non-cystic tissue characterization by multi-parametric MRI (mp-MRI) and radiomics holds promise. We conducted a radiomic analysis based on reproducible and informative features extracted from non-cystic tissue on mp-MRI in ADPKD patients. T2-weighted (T2-w), T1-weighted MRI (T1-w), and IntraVoxel Incoherent Motion (IVIM) maps from Diffusion Weighted Imaging (DWI) were considered. The reliability of radiomic features was evaluated using five different segmentation methods. The impact of segmentation variability on radiomic reproducibility was assessed through Intraclass Correlation Coefficients (ICC), and a preliminary correlation analysis with relevant clinical parameters, such as age and eGFR, was also performed. The results from 14 patients indicate that radiomic features derived from IVIM maps exhibit greater reliability compared to features from T1-w and T2-w for characterizing non-cystic tissue in ADPKD patients, also showing a moderate correlation with age and eGFR. Additionally, lower-order features, including those computed from histograms and co-occurrence matrices, demonstrate higher reproducibility than other texture features.