Keywords: Diffusion Reconstruction, Diffusion Denoising
Motivation: DTI acquires multiple diffusional directional images with repetition, containing large redundancy within the dataset. Denoising this dataset may improve image quality and reduce scan times. However, its effectiveness at different processing stages has not been investigated yet.
Goal(s): This study aimed to compare the performance of denoising networks applied at different stages of DTI processing.
Approach: Networks were trained for three stages: DWIs, diffusion tensor maps, and parameter maps. Their performance was compared using voxel-wise and ROI-wise analysis in a cuprizone mouse model.
Results: Denoising diffusion parameter maps showed the best overall performance, preserving image quality while maintaining the integrity of group-level analyses.
Impact: This study compares deep learning-powered denoising methods across different DTI processing stages, evaluating their effects on DTI analysis. Our findings suggest that denoising diffusion parameter maps offers the best outcomes.
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.
Keywords