cs.AINov 9, 2026

Multi-Stage Phase-Aware Self-Supervised Reconstruction for Multi-Echo Gradient-Echo MRI

Authors: Juan Liu, Nian Wang

Organizations: Advanced Imaging Research Center, University of Texas Southwestern Medical Center, USA · Department of Biomedical Engineering, University of Texas Southwestern Medical Center, USA · Peter O’Donnell Jr. Brain Institute, University of Texas Southwestern Medical Center, USA

Abstract

Purpose: To develop a phase-aware self-supervised framework for accelerated high-resolution multi-echo gradient-echo (mGRE) MRI that preserves anatomical detail and complex echo information for quantitative mapping. Methods: We developed multi-stage phase-aware self-supervised reconstruction (MSPR-GRE), integrating progressive k-space expansion with phase estimation and refinement. Sequential unrolled networks reconstruct complex multi-echo images and update echo-dependent phase priors. A relaxation-informed temporal subspace is used for acquisitions with at least four echoes, while shorter echo trains are reconstructed in the image domain. Training uses held-out acquired k-space samples without fully sampled targets. Evaluation included 9.4 T ex vivo mouse-brain data 30um eight-echo and 18um dual-echo) and retrospectively undersampled 7 T AHEAD human-brain data, with supervised ablations. Results:MSPR-GRE reduced artifacts in regions of rapid phase variation and preserved fine mouse-brain anatomy. Across five AHEAD test datasets at R = 4, 8, and 12, it generally improved magnitude-image, T2* map, and QSM metrics, particularly at higher acceleration. At R = 12, fourth-echo magnitude NRMSE was 12.09±\pm0.60% versus 21.55±\pm1.12% for SSDU. Ablations indicated benefits of phase refinement, while supervised experiments supported multi-stage phase-aware reconstruction. Conclusion: MSPR-GRE improves accelerated mGRE reconstruction and quantitative-map agreement without fully sampled training targets. Further validation of generalizability and phase-estimation accuracy is needed.

Figures & tables

Explore similar work

CardsList
  1. SGAM: Shared Gaussian Geometry with Implicit Amplitude Modeling for Scan-Specific 3D Multi-Contrast MRI Reconstruction

    Sep 21, 2026Jingran Xu, Dong Liang, Hairong Zheng +2Accelerated MRI ReconstructionMagnetic Resonance Imaging

  2. AGGR-Mamba: Mamba-based Network with Attention-Guided Gated Residual Refinement for Undersampled MRI Reconstruction

    Oct 20, 2026Yue Zhuo, Wenbin Deng, Lingjun Liu +2Accelerated MRI ReconstructionResidual Learning

  3. Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors

    Aug 18, 2026Mahdi Saberi, Yaşar Utku Alçalar, Merve Gülle +2Accelerated MRI ReconstructionMagnetic Resonance Imaging