Meeting Banner
Abstract #4285

Improving Low-Angular Resolution Diffusion MRI with 3D Deep Learning: A Model Assessment

Nontharat Tucksinapinunchai1, Salita Angkurawaranon2, Ratthaporn Boonsuth1, and Uten Yarach1
1Department of Radiologic Technology, Faculty of Associated Medical Sciences, Chiang Mai University, Chiang Mai, Thailand, 2Department of Radiology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand

Synopsis

Keywords: Analysis/Processing, Machine Learning/Artificial Intelligence, Neuro, Brain, White Matter

Motivation: AI and DL show promising potential in medical imaging, especially in MRI; however, the DL requires validation for reliability in clinical applications.

Goal(s): To validate the 3D-DL model in improving the low-angular resolution diffusion parametric maps while reducing acquisition time.

Approach: Using 3D-DL, the model learns from low-angular resolution data to predict high- angular resolution outputs, evaluated against conventional denoising methods, BM4D and AONLM, using 33 new cases. FA map will undergo TBSS and measure FA value.

Results: Our 3D-DL model improves diffusion parametric maps by enhancing overall image quality and outperforming other denoising techniques with increased PSNR and SSIM and decreased NRMSE.

Impact: The improved quality and reliability of the diffusion parametric maps produced by our trained 3D-DL model may be advantageous for clinical applications or the investigation of white matter microstructure in various demographics, including transgender individuals, in future research.

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