Super-resolution and denoising of 4D-Flow MRI using physics-Informed deep neural nets

Mojtaba F Fathi1, Isaac Perez-Raya1, Ahmadreza Baghaie2

  • 1Dept. of Mechanical Engineering, University of Wisconsin-Milwaukee, Milwaukee, WI, USA.

Summary

A new deep learning method enhances 4D-Flow MRI scans, improving spatial and temporal resolution for better blood flow visualization. This data-driven approach overcomes limitations in current imaging techniques for clinical applications.