EUVIMEDEUVIMED entdecken
VergleichsstudieEvaluationsstudie

Diffusion model based on generalized map for accelerated MRI

Zengwei Xiao, Yujuan Lu, Binzhong He, Pinhuang Tan, Shanshan Wang iD, Xiaoling Xu, Qiegen Liu

NMR in Biomedicine · 2024-12 · 37 (12)

DOI: 10.1002/nbm.5232 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift NMR in Biomedicine, online erschienen am 04.08.2024. Verfasst von Zengwei Xiao und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Information Engineering, Nanchang University, Nanchang, China. Hauptthemen laut MEDLINE: Diffusion Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Models, Statistical, Algorithms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Project of Science and Technology of China, National Science and Technology Major Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, diffusion models have made significant progress in accelerating magnetic resonance imaging. Nevertheless, it still has inherent limitations, such as prolonged iteration times and sluggish convergence rates. In this work, we present a novel generalized map generation model based on mean‐reverting SDE, called GM‐SDE, to alleviate these shortcomings. Notably, the core idea of GM‐SDE is optimizing the initial values of the iterative algorithm. Specifically, the training process of GM‐SDE diffuses the original k‐space data to an intermediary degraded state with fixed Gaussian noise, while the reconstruction process generates the data by reversing this process. Based on the generalized map, three variants of GM‐SDE are proposed to learn k‐space data with different structural characteristics to improve the effectiveness of model training. GM‐SDE also exhibits flexibility, as it can be integrated with traditional constraints, thereby further enhancing its overall performance. Experimental results showed that the proposed method can reduce reconstruction time and deliver excellent image reconstruction capabilities compared to the complete diffusion‐based method.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diffusion Magnetic Resonance ImagingImage Processing, Computer-AssistedModels, StatisticalAlgorithmsSignal-To-Noise RatioStochastic ProcessesDatasets as TopicBrainHumans

Stichwörter der Autor:innen

generalized maplow‐rank constraintmean‐reverting SDEparallel MRI

Autor:innen und Institutionen

  • Department of Electronic Information Engineering, Nanchang University, Nanchang, China.
  • Department of Mathematics and Computer Sciences, Nanchang University, Nanchang, China.
  • Paul C. Lauterbur Research Center for Biomedical Imaging, SIAT, Chinese Academy of Sciences, Shenzhen, China.

ORCID-Profile: Shanshan Wang

Förderung

  • National Natural Science Foundation of China
  • Key Project of Science and Technology of China
  • National Science and Technology Major Project

Zitieren

APA

Xiao, Z., Lu, Y., He, B., Tan, P., Wang, S., Xu, X., & Liu, Q. (2024). Diffusion model based on generalized map for accelerated MRI. NMR in Biomedicine, 37(12). https://doi.org/10.1002/nbm.5232

Vancouver

Xiao Z, Lu Y, He B, Tan P, Wang S, Xu X, et al. Diffusion model based on generalized map for accelerated MRI. NMR in Biomedicine. 2024;37(12). doi:10.1002/nbm.5232

BibTeX
@article{Xiao2024,
  author = {Xiao, Zengwei and Lu, Yujuan and He, Binzhong and Tan, Pinhuang and Wang, Shanshan and Xu, Xiaoling and Liu, Qiegen},
  title = {Diffusion model based on generalized map for accelerated MRI},
  journal = {NMR in Biomedicine},
  year = {2024},
  volume = {37},
  number = {12},
  doi = {10.1002/nbm.5232}
}
Kostenlos starten →