Current browse context:
cs.AI
Change to browse by:
References & Citations
Computer Science > Artificial Intelligence
Title: Learning the Domain Specific Inverse NUFFT for Accelerated Spiral MRI using Diffusion Models
(Submitted on 18 Apr 2024 (this version), latest version 10 May 2024 (v2))
Abstract: 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.
Submission history
From: Trevor Chan [view email][v1] Thu, 18 Apr 2024 17:40:23 GMT (7404kb,D)
[v2] Fri, 10 May 2024 18:47:01 GMT (7404kb,D)
Link back to: arXiv, form interface, contact.