Perfusion parameter map generation from TOF-MRA in stroke using generative adversarial networks

• Published in: NeuroImage (Orlando, Fla.) Vol. 298; p. 120770
• Main Authors: Lohrke, Felix, Madai, Vince Istvan, Kossen, Tabea, Aydin, Orhun Utku, Behland, Jonas, Hilbert, Adam, Mutke, Matthias Anthony, Bendszus, Martin, Sobesky, Jan, Frey, Dietmar
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01-09-2024; Elsevier Limited; Elsevier
• Subjects: Angiography; Artificial intelligence; Blood; Cerebrovascular diseases; Contrast agents; Datasets; Dynamic susceptibility contrast MR; Generative adversarial networks; Health risk assessment; Health risks; Hemodynamics; Ischemia; Magnetic resonance imaging; Medical imaging; Patients; Perfusion; Perfusion weighted imaging; Software; Stroke; TOF-MRA; Tomography; Vascular diseases; TOF-MRA; Generative adversarial networks; Stroke; Perfusion weighted imaging; Dynamic susceptibility contrast MR; generative adversarial networks; dynamic susceptibility contrast MR; perfusion weighted imaging; stroke
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2024.120770

•We developed an artificial intelligence model that generates 5 perfusion parameter maps from time-of-flight magnetic resonance angiography using image-to-image translation.•The generated perfusion parameter maps showed high visual similarity and moderate quantitative overlap with the real perfusion maps and areas of hypoperfusion.•This approach could offer an alternative to contrast agent-based imaging.•Before clinical use of this method for patient stratification and assessment of cerebral hemodynamics in cerebrovascular disease patients, validation is warranted.
To generate perfusion parameter maps from Time-of-flight magnetic resonance angiography (TOF-MRA) images using artificial intelligence to provide an alternative to traditional perfusion imaging techniques.
This retrospective study included a total of 272 patients with cerebrovascular diseases; 200 with acute stroke (from 2010 to 2018), and 72 with steno-occlusive disease (from 2011 to 2014). For each patient the TOF MRA image and the corresponding Dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) were retrieved from the datasets. The authors propose an adapted generative adversarial network (GAN) architecture, 3D pix2pix GAN, that generates common perfusion maps (CBF, CBV, MTT, TTP, Tmax) from TOF-MRA images. The performance was evaluated by the structural similarity index measure (SSIM). For a subset of 20 patients from the acute stroke dataset, the Dice coefficient was calculated to measure the overlap between the generated and real hypoperfused lesions with a time-to-maximum (Tmax) > 6 s.
The GAN model exhibited high visual overlap and performance for all perfusion maps in both datasets: acute stroke (mean SSIM 0.88–0.92, mean PSNR 28.48–30.89, mean MAE 0.02–0.04 and mean NRMSE 0.14–0.37) and steno-occlusive disease patients (mean SSIM 0.83–0.98, mean PSNR 23.62–38.21, mean MAE 0.01–0.05 and mean NRMSE 0.03–0.15). For the overlap analysis for lesions with Tmax>6 s, the median Dice coefficient was 0.49.
Our AI model can successfully generate perfusion parameter maps from TOF-MRA images, paving the way for a non-invasive alternative for assessing cerebral hemodynamics in cerebrovascular disease patients. This method could impact the stratification of patients with cerebrovascular diseases. Our results warrant more extensive refinement and validation of the method.