Image processing technique for improved MRI image fidelity
A novel technique to improve MRI image fidelity via the combination of a denoising and deep learning-based reconstruction step.
Applications
- Functional and structural imaging
Technology Overview
Functional magnetic resonance imaging (fMRI) is a powerful tool to safely measure and map brain activity. Though fMRI has revolutionized our understanding of the human brain, higher image quality is desirable to study brain function at the mesoscale level. In high-resolution imaging, there is a tradeoff between signal-to-noise ratio, spatial-temporal resolution, and coverage which can impact diagnostic capabilities. Researchers at the University of Minnesota have developed a novel technique for improving image fidelity in fMRI through an image processing pipeline comprising a denoising step and deep learning-based reconstruction step. This invention offers better denoising performance at higher speeds than competing techniques
Phase of Development
TRL: 4-5Proof of concept demonstrated on 7T brain data.
Desired Partnerships
This technology is now available for:- License
- Sponsored research
- Co-development
Please contact our office to share your business’ needs and learn more.
Researchers
- Steen Moeller, PhD Associate Professor, Department of Radiology
- Mehmet Akçakaya, PhD Jim and Sara Anderson Associate Professor, Department of Electrical and Computer Engineeringt
- Kamil Ugurbil, PhD Professor, Department of Radiology
- Luca Vizioli, PhD Assistant Professor, Department of Neurosurgery
- Cheryl Olman, PhD Associate Professor, Department of Psychology
-
swap_vertical_circlelibrary_booksReferences (1)
- Omer Burak Demirel, Steen Moeller, Luca Vizioli, Burhaneddin Yaman, Logan Dowdle, Essa Yacoub, Kamil Ugurbil, and Mehmet Akçakaya (2022), High-Quality 0.5mm Isotropic Functional MRI Using a Synergistic Combination of NORDIC Denoising and Deep Learning Reconstruction, ISMRM Abstract
-
swap_vertical_circlecloud_downloadSupporting documents (0)