Robustness Analysis of DCE-MRI-Derived Radiomic Features in Breast Masses: Assessing Quantization Levels and Segmentation Agreement

Machine learning models based on radiomic features allow us to obtain biomarkers capable of modeling the disease and able to support the clinical routine. Recent studies showed that it is fundamental that the computed features are robust and reproducible. Although several initiatives to standardize the definition and extraction process of biomarkers are ongoing, there is lack of comprehensive guidelines. Therefore, no standardized procedures are available for ROI selection, feature extraction and processing, with the risk of undermining the effective use of radiomic models in clinical routine. In this study, we aim to assess the impact that the different segmentation methods and the quantization level (defined by means of the number of bins used in the features extraction phase) may have on the robustness of the radiomic features. In particular, the robustness of texture features extracted by PyRadiomics, and belonging to five categories---GLCM, GLRLM, GLSZM, GLDM, NGTDM---was evaluated using the Intra-class Correlation Coefficient (ICC) and mean differences between segmentation raters. In addition to the robustness each single feature, an overall index for each feature category was quantified. The analysis shows that the level of quantization (i.e., `bincount' parameter) plays a key role in defining robust features: in fact, in our study focused on a Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) dataset of 111 breast masses, sets with cardinality varying between 34 and 43 robust features, were obtained with `binCount' values equal to 256 and 32, respectively. Moreover, both manual segmentation methods demonstrated good reliability and agreement, instead automated segmentation achieved lower ICC values. Considering the dependence on the quantization level, taking into account only the \emph{intersection subset} among all the values of `binCount' could be the best selection strategy. Among radiomic feature categories, GLCM, GLRLM, and GLDM showed the best overall robustness as the segmentation method varies.