3D Wavelet Latent Diffusion Model for Whole-Body MR-to-CT Modality Translation

TL;DR

This paper introduces a 3D Wavelet Latent Diffusion Model for more accurate and high-quality whole-body MR-to-CT translation, improving spatial alignment and detail preservation for clinical applications.

Contribution

It proposes a novel latent diffusion framework with wavelet residuals and dual skip connections to enhance image quality and anatomical fidelity in MR-to-CT synthesis.

Findings

Improved spatial alignment between generated CT and input MR images.

Enhanced preservation of fine-scale features and anatomical structures.

High-resolution CT synthesis with better bony and soft-tissue detail.

Abstract

Magnetic Resonance (MR) imaging plays an essential role in contemporary clinical diagnostics. It is increasingly integrated into advanced therapeutic workflows, such as hybrid Positron Emission Tomography/Magnetic Resonance (PET/MR) imaging and MR-only radiation therapy. These integrated approaches are critically dependent on accurate estimation of radiation attenuation, which is typically facilitated by synthesizing Computed Tomography (CT) images from MR scans to generate attenuation maps. However, existing MR-to-CT synthesis methods for whole-body imaging often suffer from poor spatial alignment between the generated CT and input MR images, and insufficient image quality for reliable use in downstream clinical tasks. In this paper, we present a novel 3D Wavelet Latent Diffusion Model (3D-WLDM) that addresses these limitations by performing modality translation in a learned latent space. By incorporating a Wavelet Residual Module into the encoder-decoder architecture, we enhance the capture and reconstruction of fine-scale features across image and latent spaces. To preserve anatomical integrity during the diffusion process, we disentangle structural and modality-specific characteristics and anchor the structural component to prevent warping. We also introduce a Dual Skip Connection Attention mechanism within the diffusion model, enabling the generation of high-resolution CT images with improved representation of bony structures and soft-tissue contrast.