Author: Yifei Hao, Wenxuan Li, Xiang Li, Tao Peng, Yulu Wu, Fang-Fang Yin, Yue Yuan, Lei Zhang, Yaogong Zhang 👨🔬
Affiliation: Duke University, School of Future Science and Engineering, Soochow University, Medical Physics Graduate Program, Duke Kunshan University 🌍
Purpose: Diffusion-based deep-learning frameworks have been recently used in MRI resolution enhancement, or super-resolution. Multi-contrast MRI share common anatomical structures while holding complementary soft-tissue information. This study aims to incorporate both shared and contrast-specific features of multi-contrast MRI into a diffusion-based deep-learning framework for simultaneous multi-contrast MRI super-resolution.
Methods: Public IXI brain dataset consisting of 576 healthy participants was used. High resolution (HR) multi-contrast MRI (T1-w and T2-w, 0.9375mm x 0.9375mm) were defined as ground truth. Low resolution (LR) multi-contrast MRI (T1-w and T2-w, 3.75mm x 3.75mm) were simulated by low-pass filtering in K-space and used as input. LR T1-w and T2-w images were combined into a dual-channel representation in the forward diffusion process. In the backward process, a cross-contrast encoder with a spatial self-attention module was added to capture shared structural features and contrast-specific information. The separation was guided by a disentanglement term. All extracted features were processed through a Squeeze-and-Excitation module for channel-wise weighting. Charbonnier loss and a progressive training strategy were employed for training stability. To compare and be consistent with other methods, the method was examined on the IXI dataset with training, validation, and testing split of 500:6:70.
Results: The method achieved simultaneous high-quality T1-w and T2-w super-resolution, enhancing resolution by 4 times. The PSNR/SSIM were 35.76 dB/0.9742 for T1-w and 30.91 dB/0.9488 for T2-w MRI. Notably different from other multi-contrast methods, our method does not need HR MRI as input, while achieving the highest PSNR (30.91dB) and 2nd highest SSIM (0.9488) among the state-of-the-art (SOTA) methods.
Conclusion: To our knowledge, this is the first study of simultaneous multi-contrast MRI super-resolution using diffusion-based framework. Our network effectively achieves high quality super-resolution of two MRI contrasts without need of high-resolution guidance. Future work includes extension studies in additional contrasts and 3D image scenarios.