{"ID":2896556,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.17764","arxiv_id":"2507.17764","title":"Diffusion-Assisted Frequency Attention Model for Whole-body Low-field MRI Reconstruction","abstract":"By integrating the generative strengths of diffusion models with the representation capabilities of frequency-domain attention, DFAM effectively enhances reconstruction performance under low-SNR condi-tions. Experimental results demonstrate that DFAM consistently outperforms both conventional reconstruction algorithms and recent learning-based approaches. These findings highlight the potential of DFAM as a promising solution to advance low-field MRI reconstruction, particularly in resource-constrained or underdeveloped clinical settings.","short_abstract":"By integrating the generative strengths of diffusion models with the representation capabilities of frequency-domain attention, DFAM effectively enhances reconstruction performance under low-SNR condi-tions. Experimental results demonstrate that DFAM consistently outperforms both conventional reconstruction algorithms...","url_abs":"https://arxiv.org/abs/2507.17764","url_pdf":"https://arxiv.org/pdf/2507.17764v1","authors":"[\"Xin Xie\",\"Yu Guan\",\"Zhuoxu Cui\",\"Dong Liang\",\"Qiegen Liu\"]","published":"2025-07-09T12:30:06Z","proceeding":"physics.med-ph","tasks":"[\"physics.med-ph\",\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}