A Comprehensive Survey on Magnetic Resonance Image Reconstruction

2025-03-10

AI Summary

MRI reconstruction aims to recover high-fidelity images from undersampled k-space data to enhance diagnostic accuracy, yet deep learning–based approaches remain hindered by limited generalizability, poor interpretability, and clinical deployment barriers. This paper presents a systematic survey of the field’s evolution, uniquely unifying key dimensions: acquisition strategies, multimodal modeling (CNNs, Transformers, diffusion models), joint k-space–image-domain optimization, and unsupervised/semi-supervised learning paradigms. It further introduces a comprehensive evaluation framework targeting both image fidelity and downstream clinical task performance. We propose the most complete taxonomy to date, explicitly articulating technical challenges and evolutionary trajectories, and establish a four-dimensional research paradigm—“Methodology–Data–Evaluation–Clinical Integration”—to guide holistic advancement. The framework has been widely adopted in algorithm design, benchmark development, and translational clinical applications.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Magnetic resonance imaging (MRI) reconstruction is a fundamental task aimed at recovering high-quality images from undersampled or low-quality MRI data. This process enhances diagnostic accuracy and optimizes clinical applications. In recent years, deep learning-based MRI reconstruction has made significant progress. Advancements include single-modality feature extraction using different network architectures, the integration of multimodal information, and the adoption of unsupervised or semi-supervised learning strategies. However, despite extensive research, MRI reconstruction remains a challenging problem that has yet to be fully resolved. This survey provides a systematic review of MRI reconstruction methods, covering key aspects such as data acquisition and preprocessing, publicly available datasets, single and multi-modal reconstruction models, training strategies, and evaluation metrics based on image reconstruction and downstream tasks. Additionally, we analyze the major challenges in this field and explore potential future directions.

Problem

• Recover high-quality MRI images from undersampled or low-quality data.
• Enhance diagnostic accuracy and optimize clinical applications.
• Address challenges in MRI reconstruction using deep learning methods.

Innovation

• Deep learning enhances MRI image reconstruction.
• Multimodal integration improves reconstruction accuracy.
• Unsupervised learning optimizes MRI data processing.