Radiomics-based Prediction of Re-hemorrhage in Cerebral Cavernous Malformation after Gamma Knife Radiosurgery

We conducted a retrospective study of long-term follow-ups in patients with cerebral cavernous malformation (CCM) treated by Gamma Knife radiosurgery (GKRS). CCM is one of the common cerebral vascular diseases. Hemorrhage is a common and dangerous symptom of CCMs, and re-hemorrhage may still occur in 30% of patients after the treatment of GKRS. We aim to identify the reliable imaging biomarkers using radiomics of magnetic resonance images (MRI) to predict the re-hemorrhage after GKRS.Clinical Relevance— This study reported the longitudinal changes of MRI radiomic features in CCM after GKRS. Combining machine-learning approach with the longitudinal radiomic features can predict the re-hemorrhage of CCM after GKRS to guide the clinical management.