What type of study is this?

This is a Quantitative Study study.

September 17, 2025

Performance Evaluation of Denoising Deep Neural Network Applied in Different Diffusion Tensor Image Processing Stages

Key Points

Denoising diffusion parameter maps shows the best overall performance in preserving image quality.
Networks were trained on three stages: DWIs, diffusion tensor maps, and parameter maps, demonstrating efficiency.
Voxel-wise and ROI-wise analysis was utilized in a cuprizone mouse model to evaluate denoising effectiveness.
Findings suggest enhanced DTI analysis outcomes when denoising diffusion parameter maps at various processing stages.

Abstract

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.

Mark Helpful

Bookmark

Relay