Radiological images contain much information that exceeds what can be visually perceived. In this context, radiomics enables the extraction of detailed features and biomarkers from images using automated algorithms, to serve as decision-support tools in the clinical management of various pathologies [1,2]. Despite being an active field of research for years, radiomics remains in the investigative stage, with the ultimate objective of integrating this discipline into clinical practice. This aligns with the effort in medicine to advance personalized healthcare [3].

One of the main limitations of radiomics is its variability, which can be attributed to multiple factors, including the scanning process, the segmentation of the volume of interest, and the calculation methods used for radiomic features, among others. Specifically, in the image acquisition phase of computed tomography (CT), imaging parameters have a significant impact on the variability of radiomic features [4,5].

Several studies have assessed the robustness of radiomic features across different types of CT scanners [6,7]. However, limited research has focused on the use of polychromatic tube CT (pCT). With the increasing adoption of dual-energy computed tomography (DECT) for the diagnosis of various pathologies, a reevaluation of the behavior of radiomic features is necessary.

The objective of this study is to propose a methodology for evaluating the robustness of radiomic features in terms of repeatability and reproducibility using fast kV-switching CT (fsCT). In this context, one of the first steps in assessing the robustness of radiomic features is to examine their reproducibility and repeatability in phantom imaging. Initially, this study will focus on repeatability by acquiring consecutive images under identical conditions. Subsequently, reproducibility will be evaluated by comparing images obtained using different acquisition protocols, various reconstruction techniques, and different reconstruction algorithms.