Answers are grounded in this paper and cite their sources.
Proposed guided reconstruction method improves image quality in MRI, suggesting better integration with image editing techniques.
Motivation: Magnetic Resonance Imaging (MRI) suffers from slow acquisition speeds, particularly in multi-modal imaging. Existing techniques experience image quality degradation and lack robustness under high-factor undersampling. Goal(s): A novel guided reconstruction framework is proposed to model structural similarities and differences across contrasts. Approach: The Schrödinger Bridge is used to model diffusion relationships between contrasts, capturing similarities, while data consistency constraints ensure fidelity. An image inversion strategy is employed to adjust the guiding contrast, compensating for differences between the guided image and the reconstructed image. Results: The proposed method outperformed traditional approaches in terms of reconstruction quality and convergence speed. Impact: A novel approach combines structural similarity modeling with difference compensation, introducing image editing techniques to MRI reconstruction. This paves the way for integrating MRI-guided reconstruction and image editing methods.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: