Multiparametric MRI Model Accurately Predicts Post-Thrombectomy Parenchymal Hematoma

A multiparametric MRI model (ADC, rCBF, rCBV, rK2) predicted parenchymal hematoma after thrombectomy with AUC 0.88 and 77% accuracy in a retrospective, single-center study of 100 patients.

• Retrospective cohort of 100 patients with large-vessel occlusion stroke undergoing endovascular thrombectomy; 32 developed parenchymal hematoma.
• The model used 5th percentile ADC, rCBF, rCBV, and 95th percentile rK2, achieving AUC 0.88 ± 0.07 (mean ± SD).
• No external validation was performed; single-center design limits generalizability.

RadPigeon summaries are original and for information only. They are not clinical advice.