Aug 2026· IEEE Transactions on Medical Imaging· Vol PP, pp. 1-1· 0 citations
Medicine
TL;DR
I2SB-Inversion is proposed, a multi-contrast guided reconstruction framework based on the Schrödinger Bridge that achieves a a high acceleration factor of R=11.38 and consistently outperforms existing methods in both quantitative and qualitative evaluations.
Abstract
Magnetic Resonance Imaging (MRI) is an inherently multi-contrast modality, where cross-contrast priors can be exploited to improve image reconstruction from undersampled data. Recently, diffusion models have shown remarkable performance in MRI reconstruction. However, they still struggle to effectively utilize such priors, mainly because existing methods rely on feature-level fusion in image or latent spaces, which lacks explicit structural correspondence and thus leads to suboptimal performance. To address this issue, we propose I2SB-Inversion, a multi-contrast guided reconstruction framework based on the Schrödinger Bridge (SB). The proposed method performs pixel-wise translation between paired contrasts, providing explicit structural constraints between the guidance and target images. Furthermore, an inversion strategy is intro-duced to correct inter-modality misalignment, which often occurs in guided reconstruction, thereby mitigating artifacts and improving reconstruction accuracy. Experiments on paired T1- and T2-weighted datasets demonstrate that I2SB-Inversion achieves a a high acceleration factor of R=11.38 and consistently outperforms existing methods in both quantitative and qualitative evaluations.
A model-driven bilevel optimization framework that couples SENSE-based image reconstruction with SPIRiT-based k-space calibration through shared CSMs, and introduces a deep-prior-guided regularization strategy that preserves the structure of classical linear regularizers while adaptively learning spatially varying regularization weights from denoised intermediate reconstructions.
Weipeng Chen, Yan-Ran Li, Raymond H. Chan et al.· Journal of Mathematical Imag...· 0 citations
Diffusion models (DMs) have emerged as powerful generative priors for MRI reconstruction with promising results. Yet DM-based methods require extensive iterative refinement, limiting their practical deployment. Consistency models (CMs) provide a compelling alternative, aiming to map out the diffusion trajectory in a single pass, enabling faster generation. In this work, we propose CM-RED, a novel MRI reconstruction method that integrates a pretrained CM into the regularization by denoising (RED) scheme. Our method builds on accelerated proximal gradient RED (RED-APG), and further incorporates controlled noise injection during the update steps to enhance generative diversity and accelerate convergence. Extensive experiments on the fastMRI knee and brain datasets demonstrate that CM-RED achieves high-quality reconstructions across multiple anatomies, contrast weights, acceleration factors, and undersampling patterns, using only 4 network function evaluations (NFEs). The proposed method consistently outperforms existing DM- and CM-based approaches in both quantitative metrics and visual fidelity, and exhibits strong robustness to hyperparameter variations, highlighting CM-RED as an efficient and effective generative framework for accelerated MRI reconstruction. The source code and pretrained models are publicly available at https://github.com/MerveGulle/CM-RED.
Merve Gülle, Junno Yun, Y. Alçalar et al.· 0 citations
Introduction Sparse-view computed tomography (CT) reconstruction is crucial for clinical diagnostics, as reducing radiation exposure is essential to minimize risks to patients. Existing dual-domain reconstruction methods leverage both image and projection domains but often process them sequentially, overlooking their implicit correlations. Methods To address this limitation, we propose Cross-Domain TransNet, a Transformer-based dual-domain framework for sparse-view CT reconstruction. The proposed model captures long-range dependencies within each domain and integrates image and sinogram representations through a hybrid self-attention mechanism. In addition, a Convolution Fusion Layer (CFL) is introduced to enhance feature interactions and facilitate more effective utilization of dual-domain information. Results Extensive experiments on the NIH-AAPM dataset demonstrate the superior performance and generalization capability of the proposed method under various sparse-view settings. The results show that Cross-Domain TransNet consistently improves reconstruction quality, effectively suppresses noise, and reduces artifacts, outperforming both conventional reconstruction algorithms and state-of-the-art deep learning approaches. Conclusion Cross-Domain TransNet provides an effective and robust solution for sparse-view CT reconstruction. By fully exploiting complementary information from both image and projection domains, the proposed framework enhances diagnostic image quality while supporting radiation dose reduction.
Junling Wang, Chunhua Zou, Hongjie Yang et al.· Frontiers in Nuclear Medicin...· 0 citations
OBJECTIVE
Parallel imaging is ubiquitous in MRI, enabling higher spatial and/or temporal resolution. However, successful unfolding is contingent on robust and accurate estimation of relative coil sensitivities, which often involves computation times that preclude online deployment. We present a computationally efficient method of robustly estimating coil sensitivities, and reconstructing under-sampled images using a data-driven regularised SENSE formalism that is commensurate with online deployment for Cartesian k-space acquisitions.
MATERIALS AND METHODS
The proposed image reconstruction method via Multiple Orthogonal Reference Sensitivity Encoding (MORSE) estimates multiple sensitivities per voxel to address issues, such as rapidly varying sensitivities, chemical shift artefact, or insufficient fields of view. It simultaneously provides a data-driven regularisation term for noise control providing inherent adaptability to diverse imaging contexts.
RESULTS
MORSE has been successfully deployed in multiple neuroimaging studies at both 3T and 7T, including functional studies of autobiographical memory processing, visual and auditory perception, and quantitative MRI studies of neurodegenerative diseases including Huntington's, Alzheimer's and Parkinson's. Exemplar image reconstructions are presented and compared with GRAPPA, ENLIVE, ESPIRiT and LORAKS. We also showcase application of MORSE outside of the brain via application in liver and knee imaging. MORSE consistently produced high-quality, artefact-free images with reconstruction times feasible for online deployment.
DISCUSSION
The proposed method of sensitivity estimation and unfolding regularisation is flexible and robust. It is made available to the community in open-source as a library of functions within the vendor-agnostic Gadgetron image reconstruction framework.
Oliver Josephs, B. Dymerska, Nadine N. Graedel et al.· MAGMA· 3 citations
This work proposes an image-domain dual-branch INR framework, termed I-FP-INR, which extends the original INR design by introducing an additional feature-processing branch, which aims to extract complementary feature embeddings to enhance the overall representation, thereby benefiting reconstruction.
Donghang Lyu, Marius Staring, Yiming Dong et al.· 0 citations
While multishot interleaved echo‐planar imaging (iEPI) enables higher resolution diffusion kurtosis imaging (DKI) compared to single‐shot EPI, its clinical application is hindered by the lengthy acquisition time. This study proposes a novel model‐based reconstruction approach to accelerate iEPI DKI acquisition.
Jian Lyu, Li Guo, Wen Zhong et al.· Magnetic Resonance in Medici...· 0 citations