Denoising Diffusion Probabilistic Models for Magnetic Resonance Fingerprinting
This work addresses the problem of reducing scan times for quantitative MRI, offering a novel application in the medical field, though it is incremental as it adapts an existing method to a new domain.
The paper tackles the challenge of accurate reconstructions in highly accelerated Magnetic Resonance Fingerprinting (MRF) scans by proposing a conditional diffusion probabilistic model, which outperforms established deep learning and compressed sensing algorithms on in-vivo brain scan data.
Magnetic Resonance Fingerprinting (MRF) is a time-efficient approach to quantitative MRI, enabling the mapping of multiple tissue properties from a single, accelerated scan. However, achieving accurate reconstructions remains challenging, particularly in highly accelerated and undersampled acquisitions, which are crucial for reducing scan times. While deep learning techniques have advanced image reconstruction, the recent introduction of diffusion models offers new possibilities for imaging tasks, though their application in the medical field is still emerging. Notably, diffusion models have not yet been explored for the MRF problem. In this work, we propose for the first time a conditional diffusion probabilistic model for MRF image reconstruction. Qualitative and quantitative comparisons on in-vivo brain scan data demonstrate that the proposed approach can outperform established deep learning and compressed sensing algorithms for MRF reconstruction. Extensive ablation studies also explore strategies to improve computational efficiency of our approach.