Low-Rank Augmented Implicit Neural Representation for Unsupervised High-Dimensional Quantitative MRI Reconstruction

2025-06-10

AI Summary

To address the ill-posedness of multi-parametric quantitative MRI (MP-qMRI) reconstruction under high undersampling, this paper proposes LoREIN, an unsupervised dual-prior fusion framework. LoREIN jointly reconstructs 3D multi-contrast weighted images and quantitative parameter maps with high fidelity via physics-driven zero-shot optimization—without requiring paired training data. Its key innovations are: (i) a novel coupled modeling mechanism integrating low-rank representation (LRR) and continuity prior implicitly encoded by implicit neural representations (INRs); and (ii) a fully unsupervised, training-free reconstruction paradigm. Experiments demonstrate that LoREIN significantly improves reconstruction accuracy and robustness at extremely low sampling rates (e.g., 5% undersampling), outperforming state-of-the-art methods. This work establishes a new pathway toward clinically viable, unsupervised qMRI reconstruction.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Quantitative magnetic resonance imaging (qMRI) provides tissue-specific parameters vital for clinical diagnosis. Although simultaneous multi-parametric qMRI (MP-qMRI) technologies enhance imaging efficiency, robustly reconstructing qMRI from highly undersampled, high-dimensional measurements remains a significant challenge. This difficulty arises primarily because current reconstruction methods that rely solely on a single prior or physics-informed model to solve the highly ill-posed inverse problem, which often leads to suboptimal results. To overcome this limitation, we propose LoREIN, a novel unsupervised and dual-prior-integrated framework for accelerated 3D MP-qMRI reconstruction. Technically, LoREIN incorporates both low-rank prior and continuity prior via low-rank representation (LRR) and implicit neural representation (INR), respectively, to enhance reconstruction fidelity. The powerful continuous representation of INR enables the estimation of optimal spatial bases within the low-rank subspace, facilitating high-fidelity reconstruction of weighted images. Simultaneously, the predicted multi-contrast weighted images provide essential structural and quantitative guidance, further enhancing the reconstruction accuracy of quantitative parameter maps. Furthermore, our work introduces a zero-shot learning paradigm with broad potential in complex spatiotemporal and high-dimensional image reconstruction tasks, further advancing the field of medical imaging.

Problem

• Reconstructing high-dimensional qMRI from undersampled data
• Overcoming limitations of single-prior methods in ill-posed inverse problems
• Enhancing accuracy of quantitative parameter maps in MP-qMRI

Innovation

• Combines low-rank and implicit neural representations
• Unsupervised dual-prior framework for MRI
• Zero-shot learning for high-dimensional reconstruction