Automated ASPECTS in Acute Ischemic Stroke: A Comparative Analysis with CT Perfusion

Background: Automated ASPECTS has the potential to reduce interobserver variability in the determination of early ischemic changes. The aim was to assess the performance of an automated ASPECTS software against a neuroradiologist's assessment in a comparative analysis with concurrent CTP-based CBV ASPECTS.

Materials and Methods: Patients with anterior circulation stroke who had baseline NCCT and CTP and underwent successful mechanical thrombectomy were included. NCCT-ASPECTS was assessed by 2 neuroradiologists (consensus for discrepancies), CTP-CBV ASPECTS by a different neuroradiologist, and automated ASPECTS by Brainomix software. ASPECTS was dichotomized (≥6 or <6) and analyzed by time from onset (>6 or ≤6 hours).

Results: 58 patients were included. Interobserver agreement for NCCT ASPECTS was moderate (k = 0.48), improving to 0.64 for dichotomized data. Automated ASPECTS showed excellent agreement with consensus reads (k = 0.84) and CTP-CBV ASPECTS (k = 0.84). ICCs were 0.84 (raw) and 0.94 (dichotomized). There was significant negative correlation with final infarct volume for all three groups (strongest for automated, r = −0.66).

Conclusions: ASPECTS derived from automated software performs equally as well as consensus reads of expert neuroradiologists and concurrent CTP-CBV ASPECTS, and can be used to standardize ASPECTS reporting and minimize interpretation variability.