D2Diff : A Dual Domain Diffusion Model for Accurate Multi-Contrast MRI Synthesis

TL;DR

This paper introduces D2Diff, a dual domain diffusion model that combines spatial and frequency domain features for more accurate multi-contrast MRI synthesis, addressing limitations of existing methods.

Contribution

The paper presents a novel dual domain learning framework with mutually trained denoising networks and an uncertainty-driven mask loss for improved MRI synthesis.

Findings

Outperforms state-of-the-art baselines in synthesis accuracy.

Enhances downstream segmentation performance.

Effectively models both local and global contrast features.

Abstract

Multi contrast MRI synthesis is inherently challenging due to the complex and nonlinear relationships among different contrasts. Each MRI contrast highlights unique tissue properties, but their complementary information is difficult to exploit due to variations in intensity distributions and contrast specific textures. Existing methods for multi contrast MRI synthesis primarily utilize spatial domain features, which capture localized anatomical structures but struggle to model global intensity variations and distributed patterns. Conversely, frequency domain features provide structured inter contrast correlations but lack spatial precision, limiting their ability to retain finer details. To address this, we propose a dual domain learning framework that integrates spatial and frequency domain information across multiple MRI contrasts for enhanced synthesis. Our method employs two mutually trained denoising networks, one conditioned on spatial domain and the other on frequency domain contrast features through a shared critic network. Additionally, an uncertainty driven mask loss directs the models focus toward more critical regions, further improving synthesis accuracy. Extensive experiments show that our method outperforms SOTA baselines, and the downstream segmentation performance highlights the diagnostic value of the synthetic results.