Motivation: Conventional brain MRI protocols require longer scan times, leading to patient discomfort and motion artifacts, which is especially problematic for aging populations with neurodegenerative or cerebrovascular diseases. Goal(s): This study aimed to reduce scan time using AI-assisted compressed sensing (ACS) while maintaining diagnostic accuracy and image quality equivalent to conventional parallel imaging. Approach: Seventy patients underwent both ACS and conventional brain MRI. Radiologists evaluated image quality (artifacts, boundary sharpness, lesion visibility) and diagnostic performance for conditions like white matter hyperintensities and infarcts. Results: ACS reduced scan time by 29.2%, improved image quality, and maintained diagnostic accuracy with strong inter-observer agreement. Impact: ACS dramatically reduces brain MRI scan time while maintaining diagnostic accuracy. This offers a practical, time-efficient alternative for routine neuroimaging, particularly in elderly populations and resource-limited settings, enhancing patient comfort and clinical workflow without sacrificing diagnostic quality.
Gu et al. (2025) studied this question.