Radiomics has gained momentum as a non-invasive prediction tool to assess MRI based tumor data in neuro-oncology. However, there’s little understating about the robustness and reproducibility of these features in normative population which is an important first step before translating to pathology. This work investigates and demonstrates the reproducibility of radiomic features on T2-FLAIR images and variation within hemispheres and lobes and its gender and age-related effect. Overall, our findings suggest that care must be taken while interpreting these features for pathological inference.
This abstract and the presentation materials are available to members only; a login is required.