Abstract WMP23: Automated Regional Density Measurements on Baseline Non-Contrast CT Predict Final Infarction in Acute Ischemic Stroke Patients

Abstract

Introduction: Early ischemic changes on non-contrast CT (NCCT) can be visually assessed using the Alberta Stroke Program Early CT Score (ASPECTS). We sought to determine if automated regional density quantification provides additional information on the development of final infarction. Methods: We selected 121 patients with middle cerebral artery stroke due to large vessel occlusion out of a consecutive cohort. Densities in ASPECTS regions were quantified as average Hounsfield Unit (HU) values using automated segmentation (Fig. 1). Relative HU (rHU) values were calculated dividing absolute regional densities of ischemic by non-ischemic hemispheres. Final infarction was quantified semi-automatically as total volume and was defined visually per ASPECTS region in a dichotomized fashion. A composite rHU score incorporating values from all ASPECTS regions weighted by regional relevance was calculated. ROC analysis was performed to calculate AUC values. Linear regression analysis was used for multivariable adjustment. Results: Median visual ASPECTS on NCCT was 8 (IQR: 6-9). Automated density measurements were feasible in all 121 patients within one minute of post-processing time. rHU values yielded significant regional classification of final infarction in ROC analyses for all ASPECTS regions except M3 and M6. Best classifications were achieved for lentiform nucleus (AUC=0.810, p<0.001), caudate nucleus (AUC=0.777, p<0.001), and insula (AUC=0.764, p<0.001). The composite rHU score was independently associated with final infarction volume (β=-0.353, p<0.001), outperforming visual ASPECTS assessment (β=-0.190, p=0.062) in multivariable regression analysis. Conclusions: Automated NCCT density changes identify ASPECTS regions that develop final infarction in stroke patients. The composite rHU score outperformed visual ASPECTS interpretation in the prediction of final infarction volumes and may serve as an observer-independent imaging biomarker.