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

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.