Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution

Guangyuan Li, Chen Rao, Juncheng Mo, Zhanjie Zhang, Wei Xing, Lei Zhao, "Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution", CVPR2024

Abstract: Recently, diffusion models (DM) have been introduced in magnetic resonance imaging (MRI) super-resolution (SR) reconstruction, exhibiting impressive performance, particularly with regard to detailed reconstruction. However, the current DM-based SR reconstruction methods still face the following issues: (1) They require a large number of iterations to reconstruct the final image, which is inefficient and consumes a significant amount of computational resources. (2) The results reconstructed by these methods are often misaligned with the real high-resolution images, leading to remarkable distortion in the reconstructed MR images. To address the aforementioned issues, we propose an efficient diffusion model for multi-contrast MRI SR, named as McDiff. Specifically, we apply DM in a highly compact low-dimensional latent space to generate prior knowledge with high-frequency detail information. The highly compact latent space ensures that DM requires only a few simple iterations to produce accurate prior knowledge. In addition, we design the Prior-Guide Large Window Transformer (PLWformer) as the decoder for DM, which can extend the receptive field while fully utilizing the prior knowledge generated by DM to ensure that the reconstructed MR image remains undistorted. Extensive experiments on public and clinical datasets demonstrate that our McDiff outperforms state-of-the-art methods.

To Run Our Code

• Train the model

bash train_S1.sh

bash train_S2.sh

• Test the model

bash test.sh

Acknowledgements

This code is built on BasicSR, DiffIR, and SRFormer.