Saved in:
Bibliographic Details
Main Authors: Yu, Guan, Jianhua, Zhang, Dong, Liang, Qiegen, Liu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.06997
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909776685826048
author Yu, Guan
Jianhua, Zhang
Dong, Liang
Qiegen, Liu
author_facet Yu, Guan
Jianhua, Zhang
Dong, Liang
Qiegen, Liu
contents Owing to the inherently dynamic and complex characteristics of cardiac magnetic resonance (CMR) imaging, high-quality and diverse k-space data are rarely available in practice, which in turn hampers robust reconstruction of dynamic cardiac MRI. To address this challenge, we perform feature-level learning directly in the frequency domain and employ a temporal-fusion strategy as the generative guidance to synthesize k-space data. Specifically, leveraging the global representation capacity of the Fourier transform, the frequency domain can be considered a natural global feature space. Therefore, unlike traditional methods that use pixel-level convolution for feature learning and modeling in the image domain, this letter focuses on feature-level modeling in the frequency domain, enabling stable and rich generation even with ultra low-data regimes. Moreover, leveraging the advantages of feature-level modeling in the frequency domain, we integrate k-space data across time frames with multiple fusion strategies to steer and further optimize the generative trajectory. Experimental results demonstrate that the proposed method possesses strong generative ability in low-data regimes, indicating practical potential to alleviate data scarcity in dynamic MRI reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06997
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle K-Syn: K-space Data Synthesis in Ultra Low-data Regimes
Yu, Guan
Jianhua, Zhang
Dong, Liang
Qiegen, Liu
Computer Vision and Pattern Recognition
Owing to the inherently dynamic and complex characteristics of cardiac magnetic resonance (CMR) imaging, high-quality and diverse k-space data are rarely available in practice, which in turn hampers robust reconstruction of dynamic cardiac MRI. To address this challenge, we perform feature-level learning directly in the frequency domain and employ a temporal-fusion strategy as the generative guidance to synthesize k-space data. Specifically, leveraging the global representation capacity of the Fourier transform, the frequency domain can be considered a natural global feature space. Therefore, unlike traditional methods that use pixel-level convolution for feature learning and modeling in the image domain, this letter focuses on feature-level modeling in the frequency domain, enabling stable and rich generation even with ultra low-data regimes. Moreover, leveraging the advantages of feature-level modeling in the frequency domain, we integrate k-space data across time frames with multiple fusion strategies to steer and further optimize the generative trajectory. Experimental results demonstrate that the proposed method possesses strong generative ability in low-data regimes, indicating practical potential to alleviate data scarcity in dynamic MRI reconstruction.
title K-Syn: K-space Data Synthesis in Ultra Low-data Regimes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.06997