Synthetizing SWI from 3T to 7T by generative diffusion network for deep medullary veins visualization.
Authors
Affiliations (8)
Affiliations (8)
- 7T Magnetic Resonance Imaging Translational Medical Center, Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing 400038, China.
- College of Medicine and Biological Information Engineering, Northeastern University, Shengyang 110169, China.
- Jiangsu JITRI Sioux Technologies Co., Ltd.
- Department of Radiology and Nuclear Medicine, Radboud University Medical Centre, Geert Grooteplein 10, 6525GA, Nijmegen, The Netherlands.; Department of Radiology, Netherlands Cancer Institute (NKI), Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands.
- Department of Radiology, The Second Affiliated Hospital Zhejiang University School of Medicine, Zhejiang 310009, China.
- Department of Radiology, Netherlands Cancer Institute (NKI), Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands.; Department of Radiology and Nuclear Medicine, Radboud University Medical Centre, Geert Grooteplein 10, 6525GA, Nijmegen, The Netherlands.
- Faculty of Applied Sciences, Macao Polytechnic University, R. de Luís Gonzaga Gomes, Macao 999078, China.. Electronic address: [email protected].
- 7T Magnetic Resonance Imaging Translational Medical Center, Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing 400038, China.. Electronic address: [email protected].
Abstract
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.