Learning the Domain Specific Inverse NUFFT for Accelerated Spiral MRI using Diffusion Models
This work addresses the problem of enabling real-time 3D imaging in MRI by combining efficient spiral sampling with deep learning, offering incremental improvements in acceleration and quality for medical imaging applications.
The paper tackled accelerated MRI reconstruction for noncartesian spiral trajectories using a generative diffusion model, achieving high-quality images (structural similarity > 0.87) with ultrafast scan times of 0.02 seconds for 2D images and identifying optimal trajectories that improve image quality over conventional methods.
Deep learning methods for accelerated MRI achieve state-of-the-art results but largely ignore additional speedups possible with noncartesian sampling trajectories. To address this gap, we created a generative diffusion model-based reconstruction algorithm for multi-coil highly undersampled spiral MRI. This model uses conditioning during training as well as frequency-based guidance to ensure consistency between images and measurements. Evaluated on retrospective data, we show high quality (structural similarity > 0.87) in reconstructed images with ultrafast scan times (0.02 seconds for a 2D image). We use this algorithm to identify a set of optimal variable-density spiral trajectories and show large improvements in image quality compared to conventional reconstruction using the non-uniform fast Fourier transform. By combining efficient spiral sampling trajectories, multicoil imaging, and deep learning reconstruction, these methods could enable the extremely high acceleration factors needed for real-time 3D imaging.