Introduction: The aim of this study was to determine whether radiomic features measured at baseline in Magnetic Resonance images (MRI) of acoustic neuromas (AN) can predict Gamma Knife (GK) treatment outcome.Methods: The study was conducted on pre- and post-GK MRI-T2 scans of 32 patients with AN who underwent stereotactic radiosurgery (SRS) for 12 Gy dose. Radiomic features extracted include Intensity, Fractals, Laplacian of Gaussian and textural Co-Occurrence, Run-length (RL), Size Zone, and Neighborhood Gray-Tone Difference matrices (NGTDM) features. Subjects were classified as treatment failures (TF) if tumor volume increased > 10%. Pre- and post-SRS audiology reports were utilized in hearing evaluation.Results: Fifteen subjects (47%) qualified as TFs. In univariate receiver operating characteristic (ROC) analysis, two radiomicfeatures, complexity in NGTDM and run percentage in RL, displayed areas under curves of > 0.65.Conclusion: This initial radiomic study establishes features that illustrates the prognostic ability of the SRS treatment in acousticneuroma. Hearing preservation was achieved in a majority of acoustic neuroma patients treated in Gamma Knife.
Radiomic assessment of the progression of acoustic neuroma after gamma knife stereotactic radiosurgery
