Meeting Banner
Abstract #5246

Robust Resolution Improvement of UTE-MR Angiogram using 3D Super-Resolution Generative Adversarial Network

Abel Worku Tessema1,2 and HyungJoon Cho1
1Department of Biomedical Engineering, Ulsan National Institute of Science and Technology, Ulsan, Korea, Republic of, 2School of Biomedical Engineering, Jimma Institute of Technology, Jimma University, Jimma, Ethiopia

Synopsis

Keywords: Vessels, Blood vessels, MR Angiogram, Super-resolution neural networkUTE-MRA is used to visualize the vasculature of the body. But the visibility of smaller blood vessels is highly dependent on the resolution which requires a long scanning time. We applied a customized 3D-SRGAN network on UTE-MRA data to increase the resolution and have achieved a structural similarity, peak signal-to-noise ratio, and mean squared error of 0.932, 32.001, and 0.00064 respectively compared with the ground truth high-resolution data. The proposed method performed better than 3D-SRGAN and cubic spline interpolation and can be used reduce the scanning time significantly and provide better image quality.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords