Multi-Contrast MRI Motion Correction via Parameter-Informed Disentanglement and Adaptive Experts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiong, Honglin, Tang, Yuxian, Li, Feng, Wang, Yulin, Xiang, Lei, Shen, Dinggang, Wang, Qian
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913174737911808
author Xiong, Honglin
Tang, Yuxian
Li, Feng
Wang, Yulin
Xiang, Lei
Shen, Dinggang
Wang, Qian
author_facet Xiong, Honglin
Tang, Yuxian
Li, Feng
Wang, Yulin
Xiang, Lei
Shen, Dinggang
Wang, Qian
contents Motion artifacts in magnetic resonance imaging (MRI) degrade diagnostic reliability. Existing deep learning methods are typically contrast-specific and fail to generalize across diverse modalities and artifact severities. We propose a unified framework combining parameter-informed contrast disentanglement with severity-aware adaptive correction. ScanCLIP, pretrained on over 30,000 MRI text-image pairs, derives contrast embeddings from acquisition parameters to disentangle contrast style from anatomical content, yielding contrast-free features. A Vision Transformer then estimates motion severity and routes features through a Mixture-of-Experts network, enabling targeted artifact correction. A dual-pathway decoder reconstructs both the clean image and residual artifact map, enforcing image-space consistency. On IXI and HCP benchmarks, our method improves PSNR by 0.75 dB and SSIM by up to 0.0279 over state-of-the-art approaches, with larger gains at higher artifact severities. It further demonstrates robust zero-shot generalization on real-world clinical data acquired with unseen scanning parameters, where existing methods either fail to remove artifacts or introduce additional distortions.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00146
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Contrast MRI Motion Correction via Parameter-Informed Disentanglement and Adaptive Experts
Xiong, Honglin
Tang, Yuxian
Li, Feng
Wang, Yulin
Xiang, Lei
Shen, Dinggang
Wang, Qian
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Motion artifacts in magnetic resonance imaging (MRI) degrade diagnostic reliability. Existing deep learning methods are typically contrast-specific and fail to generalize across diverse modalities and artifact severities. We propose a unified framework combining parameter-informed contrast disentanglement with severity-aware adaptive correction. ScanCLIP, pretrained on over 30,000 MRI text-image pairs, derives contrast embeddings from acquisition parameters to disentangle contrast style from anatomical content, yielding contrast-free features. A Vision Transformer then estimates motion severity and routes features through a Mixture-of-Experts network, enabling targeted artifact correction. A dual-pathway decoder reconstructs both the clean image and residual artifact map, enforcing image-space consistency. On IXI and HCP benchmarks, our method improves PSNR by 0.75 dB and SSIM by up to 0.0279 over state-of-the-art approaches, with larger gains at higher artifact severities. It further demonstrates robust zero-shot generalization on real-world clinical data acquired with unseen scanning parameters, where existing methods either fail to remove artifacts or introduce additional distortions.
title Multi-Contrast MRI Motion Correction via Parameter-Informed Disentanglement and Adaptive Experts
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2606.00146