Sparse Subspace Diffusion Model for Physically Consistent Accelerated MRI Reconstruction

Xiangyao Deng, Zhiqiang Shen, Sanuwani Dayarathna, Juan P. Meneses, Sergio Uribe, Zhaolin Chen
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:2388-2403, 2026.

Abstract

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast but suffers from long acquisition times. Accelerated MRI alleviates this issue by undersampling k-space, but this approach introduces aliasing artifacts and information loss. Traditional compressed sensing methods exploit handcrafted sparse priors, whereas deep learning approaches learn data-driven priors, but both often struggle at high acceleration rates due to severe information degradation. This study introduces a diffusion-based reconstruction framework, termed the Sparse Subspace Diffusion Model (SSDM), that performs MRI reconstruction within an adaptive sparse space. The proposed approach integrates coupling convolutional dictionary learning with diffusion-based generative modeling to decompose MR images into multiple orthogonal sparse subspaces and reconstruct them under measurement-consistency constraints. This formulation enables diffusion modeling in a physically meaningful latent space, effectively bridging the gap between data-driven learning and physics-guided reconstruction. Experimental results on the fastMRI dataset demonstrate that the proposed method achieves higher reconstruction quality than existing diffusion- and sparsity-based approaches, with better preservation of fine details and suppression of artifacts across various acceleration factors.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-deng26a, title = {Sparse Subspace Diffusion Model for Physically Consistent Accelerated MRI Reconstruction}, author = {Deng, Xiangyao and Shen, Zhiqiang and Dayarathna, Sanuwani and Meneses, Juan P. and Uribe, Sergio and Chen, Zhaolin}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {2388--2403}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/deng26a/deng26a.pdf}, url = {https://proceedings.mlr.press/v315/deng26a.html}, abstract = {Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast but suffers from long acquisition times. Accelerated MRI alleviates this issue by undersampling k-space, but this approach introduces aliasing artifacts and information loss. Traditional compressed sensing methods exploit handcrafted sparse priors, whereas deep learning approaches learn data-driven priors, but both often struggle at high acceleration rates due to severe information degradation. This study introduces a diffusion-based reconstruction framework, termed the Sparse Subspace Diffusion Model (SSDM), that performs MRI reconstruction within an adaptive sparse space. The proposed approach integrates coupling convolutional dictionary learning with diffusion-based generative modeling to decompose MR images into multiple orthogonal sparse subspaces and reconstruct them under measurement-consistency constraints. This formulation enables diffusion modeling in a physically meaningful latent space, effectively bridging the gap between data-driven learning and physics-guided reconstruction. Experimental results on the fastMRI dataset demonstrate that the proposed method achieves higher reconstruction quality than existing diffusion- and sparsity-based approaches, with better preservation of fine details and suppression of artifacts across various acceleration factors.} }
Endnote
%0 Conference Paper %T Sparse Subspace Diffusion Model for Physically Consistent Accelerated MRI Reconstruction %A Xiangyao Deng %A Zhiqiang Shen %A Sanuwani Dayarathna %A Juan P. Meneses %A Sergio Uribe %A Zhaolin Chen %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-deng26a %I PMLR %P 2388--2403 %U https://proceedings.mlr.press/v315/deng26a.html %V 315 %X Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast but suffers from long acquisition times. Accelerated MRI alleviates this issue by undersampling k-space, but this approach introduces aliasing artifacts and information loss. Traditional compressed sensing methods exploit handcrafted sparse priors, whereas deep learning approaches learn data-driven priors, but both often struggle at high acceleration rates due to severe information degradation. This study introduces a diffusion-based reconstruction framework, termed the Sparse Subspace Diffusion Model (SSDM), that performs MRI reconstruction within an adaptive sparse space. The proposed approach integrates coupling convolutional dictionary learning with diffusion-based generative modeling to decompose MR images into multiple orthogonal sparse subspaces and reconstruct them under measurement-consistency constraints. This formulation enables diffusion modeling in a physically meaningful latent space, effectively bridging the gap between data-driven learning and physics-guided reconstruction. Experimental results on the fastMRI dataset demonstrate that the proposed method achieves higher reconstruction quality than existing diffusion- and sparsity-based approaches, with better preservation of fine details and suppression of artifacts across various acceleration factors.
APA
Deng, X., Shen, Z., Dayarathna, S., Meneses, J.P., Uribe, S. & Chen, Z.. (2026). Sparse Subspace Diffusion Model for Physically Consistent Accelerated MRI Reconstruction. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:2388-2403 Available from https://proceedings.mlr.press/v315/deng26a.html.

Related Material