Redefining Hemodynamic Imaging in Stroke: Perfusion Parameter Map Generation from TOF-MRA using Artificial Intelligence

BackgroundPerfusion assessment in cerebrovascular disease is essential for evaluating cerebral hemodynamics and guides many current treatment decisions. Dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) is of great utility to generate perfusion parameter maps, but its reliance on a contrast agent with associated health risks and technical challenges limit its usability. We hypothesized that native Time-of-flight magnetic resonance angiography (TOF-MRA) can be used to generate perfusion parameter maps with an artificial intelligence (AI) method, called generative adversarial network (GAN), offering a contrast-free alternative to DSC-MRI. MethodsWe propose an adapted 3D pix2pix GAN that generates common perfusion maps from TOF-MRA images (CBF, CBV, MTT, Tmax). The models are trained on two datasets consisting of 272 patients with acute stroke and steno-occlusive disease. The performance was evaluated by the structural similarity index measure (SSIM), for the acute dataset we calculated the Dice coefficient for lesions with a time-to-maximum (Tmax) >6s. FindingsOur GAN model showed high visual overlap and high performance for all perfusion maps on both the acute stroke dataset (mean SSIM 0.88-092) and data including steno-occlusive disease patients (mean SSIM 0.83-0.98). For lesions of Tmax>6, the median Dice coefficient was 0.49. InterpretationOur study shows that our AI model can accurately generate perfusion parameter maps from TOF-MRA images, paving the way for clinical utility. We present a non-invasive alternative to contrast agent-based imaging for the assessment of cerebral hemodynamics in patients with cerebrovascular disease. Leveraging TOF-MRA data for the generation of perfusion maps represents a groundbreaking approach in cerebrovascular disease imaging. This method could greatly impact the stratification of patients with cerebrovascular diseases by providing an alternative to contrast agent-based perfusion assessment. FundingThis work has received funding from the European Commission (Horizon2020 grant: PRECISE4Q No. 777107, coordinator: DF) and the German Federal Ministry of Education and Research (Go-Bio grant: PREDICTioN2020 No. 031B0154 lead: DF).