Work

Synthetizing SWI from 3T to 7T by generative diffusion network for deep medullary veins visualization

Year: 2025

Type: article

Abstract: • In this prospective study, synthetic 7T SWI images produced by conditional based diffusion denoising probability model (CDDPM) from 50 participants had a comparable image quality with the 7T SWI images (P>0.05), and superior image quality compared to the 3T SWI images (P<0.05). • Almost concordance was observed between real and synthetic 7T SWI images for the visualization of the proximal deep medullary veins (P>0.05) and difference in the distal deep medullary veins (P<0.01). • The synthetic 7T SWI images better depicted the peri-ventricular venules than 3T (P<0.05) and there was no significant difference with 7T (P>0.05). Ultrahigh-field susceptibility-weighted imaging (SWI) provides excellent tissue contrast and anatomical details of brain. However, ultrahigh-field magnetic resonance (MR) scanner often expensive and provides uncomfortable noise experience for patient. Therefore, some deep learning approaches have been proposed to synthesis high-field MR images from low-filed MR images, most existing methods rely on generative adversarial network (GAN) and achieve acceptable results. While the dilemma in train process of GAN, generally recognized, limits the synthesis performance in SWI images for its microvascular structure. Diffusion models, as a promising alternative, indirectly characterize the gaussian noise to the target image with a slow sampling through a considerable number of steps. To address this limitation, we presented a generative diffusion-based deep learning imaging model, named conditional denoising diffusion probabilistic model (CDDPM), for synthesizing high-field (7 Tesla) SWI images form low-field (3 Tesla) SWI images and assess clinical applicability. Crucially, the experiment results demonstrate that the diffusion-based model that synthesizes 7T SWI from 3T SWI images is potentially to providing an alternative way to achieve the advantages of ultra-high field 7T MR images for deep medullary veins visualization.

Source: NeuroImage

DOI: 10.1016/j.neuroimage.2025.121475