Magnetic Resonance Imaging (MRI) is an essential tool for the early detection, risk stratification, prognosis, treatment selection, and monitoring of many diseases, including cancer, cardiovascular disease, metabolic, musculoskeletal, and brain disorders, among many others. Its ability to produce multi-contrast and multi-parametric images of soft tissues, coupled with its non-invasive and radiation-free nature, makes it a highly valuable tool in clinical practice. Over the past five decades, the technology behind MRI has undergone significant advancements, especially in terms of the magnetic field strengths used for imaging. Early MRI systems operated at low field strengths (0.15 T to 0.35 T) [1-3], and while they offered important diagnostic insights, they were limited by low signal-to-noise ratio (SNR) and image resolution. Over time, several advancements led to the development of systems operating at higher field strengths, such as 1.5 T and 3 T, which are now considered the clinical standard due to their superior SNR and image quality [4, 5]. Recent developments have even pushed field strengths to ultra-high levels ( 3 T), including 5 T, 7 T and beyond, further enhancing the spatial and temporal resolution of MRI [4, 6, 7]. However, high-field MRI has its challenges [8].

Low-field (LF) MRI scanners (<1T) are still prevalent in settings with limited resources or unreliable power supply. However, they often yield images with lower spatial resolution and contrast than high-field (HF) scanners. This quality disparity can result in inaccurate clinician interpretations. Image Quality Transfer (IQT) has been developed to enhance the quality of images by learning a mapping function between low and high-quality images. Existing IQT models often fail to restore high-frequency features, leading to blurry output. In this paper, we propose a 3D conditional diffusion model to improve 3D volumetric data, specifically LF MR images. Additionally, we incorporate a cross-batch mechanism into the self-attention and padding of our network, ensuring broader contextual awareness even under small 3D patches. Experiments on the publicly available Human Connectome Project (HCP) dataset for IQT and brain parcellation demonstrate that our model outperforms existing methods both quantitatively and qualitatively. The code is publicly available at \url{https://github.com/edshkim98/DiffusionIQT}.

Magnetic resonance imaging (MRI) is known to have reduced signal-to-noise ratios (SNR) at lower field strengths, leading to signal degradation when producing a low-field MRI image from a high-field one. Therefore, reconstructing a high-field-like image from a low-field MRI is a complex problem due to the ill-posed nature of the task. Additionally, obtaining paired low-field and high-field MR images is often not practical. We theoretically uncovered that the combination of these challenges renders conventional deep learning methods that directly learn the mapping from a low-field MR image to a high-field MR image unsuitable. To overcome these challenges, we introduce a novel meta-learning approach that employs a teacher-student mechanism. Firstly, an optimal-transport-driven teacher learns the degradation process from high-field to low-field MR images and generates pseudo-paired high-field and low-field MRI images. Then, a score-based student solves the inverse problem of reconstructing a high-field-like MR image from a low-field MRI within the framework of iterative regularization, by learning the joint distribution of pseudo-paired images to act as a regularizer. Experimental results on real low-field MRI data demonstrate that our proposed method outperforms state-of-the-art unpaired learning methods.