Ultrafast MRI using deep learning echoplanar imaging for a comprehensive assessment of acute ischemic stroke
- 16 March 2023
- journal article
- research article
- Published by Springer Nature in European Radiology
- Vol. 33 (5) , 3715-3725
Abstract
Objectives Acute ischemic stroke (AIS) is an emergency requiring both fast and informative MR sequences. We aimed to assess the performance of an artificial intelligence-enhanced ultrafast (UF) protocol, compared to the reference protocol, in the AIS management. Methods We included patients admitted in the emergency department for suspected AIS. Each patient underwent a 3-T MR protocol, including reference acquisitions of T2-FLAIR, DWI, and SWI (duration: 7 min 54 s) and their accelerated multishot EPI counterparts for T2-FLAIR and T2*, complemented by a single-shot EPI DWI (duration: 1 min 54 s). Two blinded neuroradiologists reviewed each dataset, assessing DWI (detection, location, number of acute lesions), FLAIR (vascular hyperintensities, visibility of acute lesions), and SWI/T2* (hemorrhagic transformation, thrombus). We compared the agreement between the diagnoses obtained with both protocols using kappa coefficients. Results A total of 173 patients were included consecutively, of whom 80 with an AIS in DWI. We found an almost perfect agreement between the UF and reference protocols regarding the detection, distribution, number of AIS in DWI (κ = 0.98, 0.98, and 0.87 respectively), the presence of vascular hyperintensities, and the presence of a parenchymal hyperintensity in the AIS region in FLAIR (κ = 0.93 and 0.89 respectively). Agreement was substantial in T2*/SWI for thrombus detection, and fair for hemorrhagic transformation detection (κ = 0.64 and 0.38 respectively). Differential diagnoses were similarly detected by both protocols (κ = 1). Conclusions Our AI-enhanced ultrafast MRI protocol allowed an effective detection and characterization of both AIS and differential diagnoses in less than 2 min. Key Points • The AI-enhanced ultrafast MRI protocol allowed an effective detection of acute stroke. • Characterization of stroke features with the UF protocol was equivalent to the reference sequences. • Differential diagnoses were detected similarly by the UF and reference protocols.Keywords
This publication has 21 references indexed in Scilit:
- The global burden of stroke: persistent and disablingThe Lancet Neurology, 2019
- MRI-Guided Thrombolysis for Stroke with Unknown Time of OnsetNew England Journal of Medicine, 2018
- FLAIR vascular hyperintensities predict early ischemic recurrence in TIANeurology, 2018
- A 1‐minute full brain MR exam using a multicontrast EPI sequenceMagnetic Resonance in Medicine, 2017
- Speed in Clinical Magnetic ResonanceInvestigative Radiology, 2017
- Stroke ThrombolysisStroke, 2014
- Magnetic resonance imaging and computed tomography in emergency assessment of patients with suspected acute stroke: a prospective comparisonThe Lancet, 2007
- Reliability in detection of hemorrhage in acute stroke by a new three‐dimensional gradient recalled echo susceptibility‐weighted imaging technique compared to computed tomography: A retrospective studyJournal of Magnetic Resonance Imaging, 2004
- CT and Diffusion-Weighted MR Imaging in Randomized OrderStroke, 2002
- Correction for vascular artifacts in cerebral blood flow values measured by using arterial spin tagging techniquesMagnetic Resonance in Medicine, 1997