MRI Super-Resolution with Deep Learning: A Comprehensive Survey

2025-11-20

AI Summary

High-resolution (HR) MRI is critical for clinical diagnosis and research but faces fundamental limitations—including hardware cost, prolonged acquisition time, and low signal-to-noise ratio. This paper presents a systematic review of deep learning–based MRI super-resolution (SR), proposing a multidimensional taxonomy integrating computer vision, computational imaging, inverse problem modeling, and MR physics–driven priors. We conduct a unified evaluation of mainstream architectures—including CNNs, GANs, and self-supervised models—focusing on anatomical fidelity, artifact suppression, and adherence to MR physical consistency. Performance boundaries and generalization limitations are quantitatively assessed using standardized metrics and publicly available datasets. To facilitate reproducibility and translation, we release an open-source codebase, pretrained models, and practical tutorials. The work identifies key clinical deployment challenges—such as domain shift and scanner variability—and outlines actionable pathways for algorithmic refinement and multi-center validation, establishing a rigorous, benchmarked foundation for future SR research in MRI.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

High-resolution (HR) magnetic resonance imaging (MRI) is crucial for many clinical and research applications. However, achieving it remains costly and constrained by technical trade-offs and experimental limitations. Super-resolution (SR) presents a promising computational approach to overcome these challenges by generating HR images from more affordable low-resolution (LR) scans, potentially improving diagnostic accuracy and efficiency without requiring additional hardware. This survey reviews recent advances in MRI SR techniques, with a focus on deep learning (DL) approaches. It examines DL-based MRI SR methods from the perspectives of computer vision, computational imaging, inverse problems, and MR physics, covering theoretical foundations, architectural designs, learning strategies, benchmark datasets, and performance metrics. We propose a systematic taxonomy to categorize these methods and present an in-depth study of both established and emerging SR techniques applicable to MRI, considering unique challenges in clinical and research contexts. We also highlight open challenges and directions that the community needs to address. Additionally, we provide a collection of essential open-access resources, tools, and tutorials, available on our GitHub: https://github.com/mkhateri/Awesome-MRI-Super-Resolution. IEEE keywords: MRI, Super-Resolution, Deep Learning, Computational Imaging, Inverse Problem, Survey.

Problem

• Enhancing MRI resolution through deep learning techniques
• Overcoming hardware limitations with computational super-resolution methods
• Surveying deep learning approaches for MRI image reconstruction

Innovation

• Deep learning methods for MRI super-resolution
• Generating high-resolution images from low-resolution scans
• Systematic taxonomy of emerging MRI enhancement techniques