Automated brain MRI protocol adaptation based on imaging findings using AI: diagnostic performance and agreement with neuroradiologists.
Authors
Affiliations (5)
Affiliations (5)
- Department of Radiology, Copenhagen University Hospital Rigshospitalet, Copenhagen, Denmark.
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.
- Imaging Institute, Cleveland Clinic, Cleveland, OH, USA.
- Cerebriu A/S, Copenhagen, Denmark.
- Department of Neurology, Copenhagen University Hospital Rigshospitalet, Copenhagen, Denmark.
Abstract
BackgroundSelecting optimal brain magnetic resonance imaging (MRI) protocols is a manual, error-prone process, often complicated by incomplete clinical information. Automated AI-based analysis of initial imaging sequences offers a potential strategy for dynamic protocol adaptation while the patient is still in the scanner.PurposeTo evaluate the diagnostic performance and agreement with neuroradiologists of an AI tool designed to automatically adapt brain MRI protocols based on the detection of critical findings (brain infarcts, acute hemorrhages, and mass lesions) using three initial imaging sequences.Material and MethodsWe retrospectively collected consecutive cohorts of brain MRI scans from two tertiary medical centers. The cohorts were consecutively enriched with positive findings of brain infarcts, hemorrhages, and mass lesions. An AI tool and neuroradiologists independently assessed three sequences (diffusion-weighted imaging, T2-FLAIR, SWI/T2*-GRE) for critical findings and recommended protocol adaptations from seven options. Diagnostic performance was compared against reference findings based on radiological reports and de novo imaging review.ResultsA total of 752 patients were included (325 men; mean age=61 years). The AI tool's pooled sensitivity for detecting infarcts, hemorrhages, and mass lesions was 92% (95% CI=86-96), 75% (95% CI=64-84), and 71% (95% CI=61-79), with pooled specificity of 93% (95% CI=90-95), 86% (95% CI=83-88), and 90% (95% CI=87-92), respectively. Agreement on protocol adaptation between the AI and neuroradiologists was moderate (κ=0.47), though concordance was high (84%-87%) for scans requiring no further adaptations.ConclusionThe AI tool demonstrated reasonable pathology detection, relevant protocol recommendations, and potential to ensure appropriate imaging protocols in high-volume, low-risk scan scenarios, but expert oversight is required.