Feasibility study of Attention-Guided Pix2Pix GAN for the synthesizing of enhanced cerebral vascular images in 7 Tesla MRI

Motivation: The application of 7T contrast-enhanced (CE) MRI in cerebral vascular imaging offers superior spatial resolution, enabling enhanced visualization of intricate brain plaques. Nonetheless, the administration of contrast agents imposes a certain economic and health burden on patients. Goal(s): To develop the Attention-Guided Pix2Pix GAN method for synthesizing 7T CE-T1WI images from 7T pre-contrast T1WI, aiming at evaluating cerebral vascular plaque. Approach: The performance of synthetic 7T CE-T1WI image was compared to real 7T CE-T1WI image. Results: Attention-Guided Pix2Pix GAN successfully synthesizes high-quality 7T CE-T1WI images from 7T pre-contrast T1WI data, which was comparable to real 7T CE-T1WI image. Impact: The model we proposed can generate high-quality 7T magnetic resonance cerebrovascular enhancement images, which makes it possible to diagnose cerebral vessels without the use of contrast agents.