Abstract P343: Relationship of Infarct Volume to Inflammation and Prognostic Significance in Patients With Acute Ischemic Stroke

Abstract

Background and Purpose: The diffusion weighted imaging (DWI) lesion volumes in acute ischemic stroke (AIS) can be automatically measured using deep learning-based segmentation algorithms. We aim to explore the prognostic significance of artificial intelligence-predicted infarct volume, and the association of markers of acute inflammation with the infarct volume. Methods: 12,598 AIS/TIA patients were included in this analysis. Intarct volume was automatically measured using a U-Net model for acute ischemic stroke lesion segmentation on DWI. Participants were divided into 5 subgroups according to infarct volume. Spearman’s correlations were employed to study the association between infarct volume and markers of acute inflammation. Multivariable logistic regression and Cox proportional hazards model were performed to explore the relationship between infarct volume and the incidence of poor functional outcome (modified Rankin scale score 3-6), stroke recurrence or combined vascular events at 3 months. Results: The U-Net model prediction correlated and agreed well with manual annotation ground truth for infarct volume (r=0.96; P<0.001). There were positive correlations between the infarct volume and markers of acute inflammation (neutrophil [r=0.175; P<0.001], hs-CRP [r=0.180; P<0.001], and IL-6 [r=0.225; P<0.001]). Compared with those without DWI lesions, patients with the largest infarct volume (4th Quartile) were nearly five times more likely to have poor functional outcome (mRS 3-6) (adjusted odds ratio, 4.70; 95% confidence intervals [CI], 3.29-6.72; P for trend<0.001) after adjustment for confounding factors and markers of acute inflammation. The infarct volume category was significantly associated with stroke recurrence (adjusted hazard ratios [HRs], 1.0, 1.43[0.95,2.17], 2.22[1.49,3.29], 2.06[1.40,3.05], 2.26[1.52,3.36]; P for trend<0.001) and combined vascular events(adjusted HRs, 1.0, 1.38[0.92,2.09], 2.25[1.53,3.32], 2.03[1.38,2.98], 2.28[1.54,3.36]; P for trend<0.001). Conclusions: Infarct volume measured automatically by deep learning-based tool was a strong predictor of poor functional outcome as well as stroke recurrence, with the potential for widespread adoption in both research and clinical settings.