Saved in:
Bibliographic Details
Main Authors: Chen, Zhibo, Guan, Yu, Huang, Yajuan, Chen, Chaoqi, XiangJi, Fan, Qiuyun, Liang, Dong, Liu, Qiegen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.07820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908820058406912
author Chen, Zhibo
Guan, Yu
Huang, Yajuan
Chen, Chaoqi
XiangJi
Fan, Qiuyun
Liang, Dong
Liu, Qiegen
author_facet Chen, Zhibo
Guan, Yu
Huang, Yajuan
Chen, Chaoqi
XiangJi
Fan, Qiuyun
Liang, Dong
Liu, Qiegen
contents Simultaneous multi-slice (SMS) imaging with in-plane undersampling enables highly accelerated MRI but yields a strongly coupled inverse problem with deterministic inter-slice interference and missing k-space data. Most diffusion-based reconstructions are formulated around Gaussian-noise corruption and rely on additional consistency steps to incorporate SMS physics, which can be mismatched to the operator-governed degradations in SMS acquisition. We propose an operator-guided framework that models the degradation trajectory using known acquisition operators and inverts this process via deterministic updates. Within this framework, we introduce an operator-conditional dual-stream interaction network (OCDI-Net) that explicitly disentangles target-slice content from inter-slice interference and predicts structured degradations for operator-aligned inversion, and we instantiate reconstruction as a two-stage chained inference procedure that performs SMS slice separation followed by in-plane completion. Experiments on fastMRI brain data and prospectively acquired in vivo diffusion MRI data demonstrate improved fidelity and reduced slice leakage over conventional and learning-based SMS reconstructions.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07820
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Back to Physics: Operator-Guided Generative Paths for SMS MRI Reconstruction
Chen, Zhibo
Guan, Yu
Huang, Yajuan
Chen, Chaoqi
XiangJi
Fan, Qiuyun
Liang, Dong
Liu, Qiegen
Computer Vision and Pattern Recognition
Simultaneous multi-slice (SMS) imaging with in-plane undersampling enables highly accelerated MRI but yields a strongly coupled inverse problem with deterministic inter-slice interference and missing k-space data. Most diffusion-based reconstructions are formulated around Gaussian-noise corruption and rely on additional consistency steps to incorporate SMS physics, which can be mismatched to the operator-governed degradations in SMS acquisition. We propose an operator-guided framework that models the degradation trajectory using known acquisition operators and inverts this process via deterministic updates. Within this framework, we introduce an operator-conditional dual-stream interaction network (OCDI-Net) that explicitly disentangles target-slice content from inter-slice interference and predicts structured degradations for operator-aligned inversion, and we instantiate reconstruction as a two-stage chained inference procedure that performs SMS slice separation followed by in-plane completion. Experiments on fastMRI brain data and prospectively acquired in vivo diffusion MRI data demonstrate improved fidelity and reduced slice leakage over conventional and learning-based SMS reconstructions.
title Back to Physics: Operator-Guided Generative Paths for SMS MRI Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.07820