Computer-extracted (radiomic) features can provide a wealth of quantitative information that is useful for quantitative characterization of disease. However, routine image acquisition parameters can vary substantially across patients with the potential to confound or degrade results obtained by analysis of radiomic features. The extent to which the variation in routine image acquisition parameters can affect radiomic features in vivo is not well known. In this work, we evaluate the influence of varied contrast weighting (TR, TE), varied resolution, and the use of parallel imaging on intensity and textural radiomic features in T2-weighted images.
This abstract and the presentation materials are available to members only; a login is required.