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

Area of Science:

• Neurology
• Radiology
• Medical Imaging Analysis

Background:

• Automated ASPECTS (Alberta Stroke Program Early CT Score) has the potential to reduce interobserver variability in identifying early ischemic changes.
• Assessing early ischemic changes is crucial for stroke management and treatment decisions.

Purpose of the Study:

• To evaluate the performance of an automated ASPECTS software.
• To compare automated ASPECTS with neuroradiologist assessments and CTP-CBV ASPECTS.

Main Methods:

• 58 anterior circulation stroke patients with NCCT and CTP were included.
• ASPECTS were assessed by two neuroradiologists (NCCT), one neuroradiologist (CTP-CBV), and automated software.
• Data were dichotomized and analyzed for agreement and correlation with infarct volume.

Main Results:

• Automated ASPECTS showed excellent agreement with consensus reads (κ=0.84) and CTP-CBV ASPECTS (κ=0.84).
• High intraclass correlation coefficients were observed for both raw (0.84) and dichotomized (0.94) scores.
• Automated scores correlated significantly with final infarct volume (r=-0.66).

Conclusions:

• Automated ASPECTS software performs comparably to expert consensus and CTP-CBV ASPECTS.
• Automated ASPECTS can standardize reporting and minimize interpretation variability in stroke imaging.
• This technology holds promise for improving the consistency of early ischemic change assessment.