Recent advances in MR neuroimaging: toward quantitative and AI-driven brain and spinal cord imaging

Abstract

Magnetic resonance neuroimaging is undergoing a major paradigm shift from traditional qualitative anatomical mapping toward integrated, quantitative measurement systems with biological interpretability. This review systematically synthesizes nine methodological pillars driving this transformation, encompassing advances ranging from hardware innovation to artificial intelligence algorithms. We first explore the pivotal role of deep learning in image reconstruction and acceleration, followed by detailed analyses of quantitative brain oxygen metabolism assessment, standardized spinal cord imaging frameworks, and the non-invasive monitoring of the glymphatic system using diffusion MRI. Furthermore, the review delves into tractometry, susceptibility-based myelin mapping, the clinical standardization of arterial spin labeling, and the application of radiomics in extracting high-dimensional phenotypes. Finally, the importance of open science and workflow coordination in enhancing research reproducibility is highlighted. Through the deep integration of hardware, sequences, and artificial intelligence, these technologies form a synergistic ecosystem that provides unprecedented precision tools and translational potential for both basic neuroscience research and clinical precision medicine. Across these domains, AI contributes not only to acceleration and reconstruction but also to segmentation, quality control, quantitative parameter extraction, and multiparametric pattern recognition that can support diagnostic interpretation. The quantitative emphasis of this review therefore lies in measurable outputs such as image-quality metrics, metabolic and perfusion parameters, tract-specific diffusion indices, susceptibility-based components, and radiomic features.