Enhancing Diffusion-Weighted Images (DWI) for Diffusion MRI: Is it Enough without Non-Diffusion-Weighted B=0 Reference?

2025-04-14

IEEE International Symposium on Biomedical Imaging

AI Summary

In diffusion MRI super-resolution, neglecting the physiological dependency of diffusion-weighted images (DWIs) on the b=0 reference image leads to distortions in DWI/b=0 ratios, compromising the accuracy of quantitative diffusion metrics such as ADC, FA, and MD. To address this, we propose an end-to-end deep learning framework that operates without explicit b=0 image input. Our key innovation is a log-space ratio loss that explicitly enforces the biophysically grounded intensity ratio relationship between DWIs and the implicit b=0 reference—overcoming the limitations of conventional pixel-wise MSE loss in modeling relative intensities. Jointly optimized with a reconstruction loss, this formulation ensures physiological interpretability and clinical reliability of derived diffusion metrics. Experiments demonstrate that our method significantly reduces ratio reconstruction error, improves PSNR, and better preserves quantitative consistency essential for downstream metrics (e.g., FA, MD), enabling high-fidelity diffusion parameter reconstruction even in the absence of explicit b=0 constraints.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Learning with Manifolds
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Diffusion MRI (dMRI) is essential for studying brain microstructure, but high-resolution imaging remains challenging due to the inherent trade-offs between acquisition time and signal-to-noise ratio (SNR). Conventional methods often optimize only the diffusion-weighted images (DWIs) without considering their relationship with the non-diffusion-weighted (b=0) reference images. However, calculating diffusion metrics, such as the apparent diffusion coefficient (ADC) and diffusion tensor with its derived metrics like fractional anisotropy (FA) and mean diffusivity (MD), relies on the ratio between each DWI and the b=0 image, which is crucial for clinical observation and diagnostics. In this study, we demonstrate that solely enhancing DWIs using a conventional pixel-wise mean squared error (MSE) loss is insufficient, as the error in ratio between generated DWIs and b=0 diverges. We propose a novel ratio loss, defined as the MSE loss between the predicted and ground-truth log of DWI/b=0 ratios. Our results show that incorporating the ratio loss significantly improves the convergence of this ratio error, achieving lower ratio MSE and slightly enhancing the peak signal-to-noise ratio (PSNR) of generated DWIs. This leads to improved dMRI super-resolution and better preservation of b=0 ratio-based features for the derivation of diffusion metrics.

Problem

• Improving DWI quality without b=0 reference in MRI
• Addressing ratio errors between DWIs and b=0 images
• Enhancing diffusion metrics accuracy via novel loss

Innovation

• Proposes ratio loss for DWI enhancement
• Improves convergence of DWI/b=0 ratio error
• Enhances dMRI super-resolution and feature preservation