Generating Synthetic MR Perfusion Maps from DWI and FLAIR in Acute Ischemic Stroke using Deep Learning

Background: Magnetic resonance imaging (MRI) is critical for acute stroke triage, but time-consuming, and often requires contrast injection for perfusion imaging. This study aimed to synthesize T-map perfusion maps from routinely available, non-contrast DWI and FLAIR sequences by means of deep generative models. We hypothesized that relevant perfusion information could be inferred from these modalities that would streamline imaging and reduce reliance on dynamic susceptibility contrast perfusion. Methods: Acute MRI data from 355 patients with anterior circulation stroke, including dynamic susceptibility contrast perfusion, were retrospectively collected from two European centers. Six versions of a denoising diffusion probabilistic model (DDPM) and a GAN architecture were trained to generate synthetic T-max perfusion maps from DWI and FLAIR imaging and infarct core mask as input. Performance was assessed by comparing synthetic and ground truth T-max perfusion maps using image similarity metrics. Regions with T-max >6s were compared using Dice coefficients, and mismatch volume distributions were analyzed. An ablation study quantified the contribution of each input. Results: The best performance was achieved by a DDPM with a 2.5D architecture using DWI, FLAIR, infarct core mask, and a specified loss function. It produced synthetic perfusion T-max maps with high similarity to ground truth in an inference time of under 110 seconds. The model showed strong spatial overlap for clinically relevant T-max >6s regions in internal validation (average Dice = 0.82, SD = 0.08), and external validation average (Dice 0.59, SD = 0.13), respectively. Synthetic maps also closely matched ground-truth mismatch distributions, capturing key perfusion patterns. The infarct core mask played a critical role in model performance, alongside DWI and FLAIR inputs. Conclusions: We propose a robust, non-invasive, and scalable framework to generate synthetic T-max perfusion maps from standard non-contrast MRI. This approach has the potential to expand access to perfusion data in acute stroke, shorten imaging protocols, and accelerate treatment decisions by eliminating the need for contrast-enhanced acquisition.