Two-way comparison of brain perfusion image processing software for patients with acute ischemic strokes in real-world.

Abstract

Perfusion imaging generates multimaps of ischemic tissues and is a proven decision-making tool in patients with acute ischemic stroke. However, the reliability of perfusion post-processing outcomes has been debated, given disparate results of various software applications, especially for patients with small ischemic core volume. This study was undertaken to compare ischemic volume estimates determined by imSTROKE (a software with new imaging protocol) and RAPID computer applications, respectively. A total of 611 patients qualified for study, each having met inclusion and exclusion criteria of the Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands (MR CLEAN trial). Subjects were examined by computed tomography perfusion (CTP) imaging (n = 349) or perfusion-weighted (PWI) and diffusion-weighted (DWI) imaging (n = 262). Ischemic volumes estimated by imSTROKE and RAPID applications were then compared. We used Bland-Altman analysis and intraclass correlation coefficients (ICCs) to ascertain agreement between applications. Accuracies of estimated core infarct and penumbra volumes were tested at specific thresholds (core: 25 mL, 50 mL, and 70 mL; penumbra: 45 mL, 90 mL, and 125 mL). Median core infarct volumes by imSTROKE and RAPID were 29.18 mL and 29.53 mL, respectively (ICC = 0.9880, 95% confidence interval [CI]: 0.9860-0.9898). Median penumbra volumes by imSTROKE and RAPID were 68.20 mL and 68.55 mL, respectively (ICC = 0.9885, 95% CI: 0.9865-0.9902). In estimating core infarct and penumbra volumes, imSTROKE and RAPID applications showed high-level agreement. For patients with small ischemic core volume, compared with RAPID, imSTROKE may have better sensitivity.