Characterizing the effects of noncontrast head CT reconstruction kernel and slice thickness parameters on the performance of an automated AI algorithm in the evaluation of ischemic stroke
Journal of Medical Imaging, 2026
Abstract
Introduction: This study investigates how CT scan parameters affect AI algorithm performance in stroke detection.
Methods: Researchers analyzed the impact of noncontrast head CT reconstruction kernel and slice thickness on automated AI algorithm evaluation of ischemic stroke.
Results: The study found that both reconstruction kernel and slice thickness parameters significantly influence the performance of AI algorithms in ischemic stroke assessment.
Conclusion: Standardization of CT imaging protocols is crucial for consistent AI algorithm performance in stroke evaluation. Read full study
