Noise Level Adaptive Diffusion Model for Robust Reconstruction of Accelerated MRI
This addresses a critical issue for MRI reconstruction in scenarios like low-field systems in low- and middle-income countries or high-resolution imaging, where existing methods can fail, making it domain-specific but impactful for medical imaging.
The paper tackles the problem of diffusion model-based MRI reconstruction failing due to inherent noise in real-world acquisitions, proposing a noise level adaptive method that surpasses state-of-the-art techniques and shows robustness across various noise levels on datasets from 0.3T to 3T.
In general, diffusion model-based MRI reconstruction methods incrementally remove artificially added noise while imposing data consistency to reconstruct the underlying images. However, real-world MRI acquisitions already contain inherent noise due to thermal fluctuations. This phenomenon is particularly notable when using ultra-fast, high-resolution imaging sequences for advanced research, or using low-field systems favored by low- and middle-income countries. These common scenarios can lead to sub-optimal performance or complete failure of existing diffusion model-based reconstruction techniques. Specifically, as the artificially added noise is gradually removed, the inherent MRI noise becomes increasingly pronounced, making the actual noise level inconsistent with the predefined denoising schedule and consequently inaccurate image reconstruction. To tackle this problem, we propose a posterior sampling strategy with a novel NoIse Level Adaptive Data Consistency (Nila-DC) operation. Extensive experiments are conducted on two public datasets and an in-house clinical dataset with field strength ranging from 0.3T to 3T, showing that our method surpasses the state-of-the-art MRI reconstruction methods, and is highly robust against various noise levels. The code for Nila is available at https://github.com/Solor-pikachu/Nila.