Image Content Matters: An Image Content Aware State Space Model for Accelerated MRI Reconstruction

Yucong Meng; Zhiwei Yang; Kexue Fu; Zhijian Song; Yonghong Shi

AAAI 2026technical0 citations

Image Content Matters: An Image Content Aware State Space Model for Accelerated MRI Reconstruction

Yucong Meng, Zhiwei Yang, Kexue Fu, Zhijian Song, Yonghong Shi

Abstract

The challenge of accelerated MRI reconstruction lies in recovering high-quality images from undersampled k-space. Recently, the selective state space model (Mamba) has shown promising results in various tasks with balanced global receptive field and computational efficiency, shedding new light on MRI reconstruction. However, existing approaches directly flatten 2D images based on spatial positions and apply Mamba to vision tasks, failing to preserve and explore the content properties. In this paper, we posit that the key to unlocking Mamba

BibTeX

@inproceedings{aaai2026_imagecontentmatt,
  title = {Image Content Matters: An Image Content Aware State Space Model for Accelerated MRI Reconstruction},
  author = {Yucong Meng and Zhiwei Yang and Kexue Fu and Zhijian Song and Yonghong Shi},
  booktitle = {AAAI 2026},
  year = {2026}
}