Multiparametric AI-based perfusion analysis outperforms Tmax thresholding for critically hypoperfused tissue estimation in acute ischemic stroke undergoing admission MRI

ObjectivePerfusion imaging is used to estimate critically hypoperfused tissue in acute ischemic stroke (AIS), commonly using threshold-based methods.This study compared an artificial intelligence (AI)-driven multiparametric approach with conventional thresholding for estimating ischemic core and hypoperfused tissue volumes. Materials and MethodsWe analyzed 186 AIS patients from the HIBISCUS-STROKE cohort (NCT03149705) who underwent MRI before mechanical thrombectomy.A deep-learning AI model, incorporating multiparametric imaging features, was compared to standard thresholding methods.The ischemic core was defined by an ADC62010mm/s threshold, and critically hypoperfused tissue was defined by Tmax6s.Successful thrombectomy was determined by a modified thrombolysis in cerebral infarction score 2B.For recanalized patients, AI and ADC-based core volumes were compared with the final infarct volume from day 6 T2-FLAIR MRI.For non-recanalized patients, the hypoperfused tissue estimates were compared with the final infarct volume. ResultsThe AI-derived ischemic core volume strongly correlated with ADC-based estimates (=0.82,P<0.0001) with no significant volume differences (P=0.38).In recanalized patients, both methods correlated similarly with final infarct volume (0.67;P<0.0001), with comparable median underestimations and biases on Bland-Altman analysis.AI-estimated hypoperfused tissue volumes were significantly lower than those obtained via Tmax thresholding (medians: 44.4 mL vs. 79.6 mL; P=0.007), with a more favorable bias in non-recanalized patients. ConclusionThe AI-driven multiparametric approach refined the estimation of critically hypoperfused tissue compared to conventional Tmax thresholding while maintaining comparable performance for assessing the ischemic core.