Predicting before Reconstruction: A generative prior framework for MRI acceleration

2025-10-22

AI Summary

Long MRI acquisition times hinder clinical efficiency. To address this, we propose a novel “prediction-before-reconstruction” paradigm that pioneers the integration of generative priors into accelerated MRI. Specifically, we leverage deep generative models to predict high-fidelity target images end-to-end from multi-source conditioning inputs—including multi-contrast images, acquisition parameters, and patient-specific metadata—thereby establishing a data-driven prior for reconstructing highly undersampled k-space data. Our method natively supports multi-coil input and unifies prediction and reconstruction within a single framework. Evaluated on a large-scale, multi-center dataset comprising 14,921 scans (1,051,904 slices), it achieves superior performance over state-of-the-art methods across acceleration factors of ×4–×12, with particularly marked improvements in FLAIR and T1-weighted reconstructions. This work advances MRI beyond conventional model-based or learned reconstruction toward a new predictive imaging paradigm.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Recent advancements in artificial intelligence have created transformative capabilities in image synthesis and generation, enabling diverse research fields to innovate at revolutionary speed and spectrum. In this study, we leverage this generative power to introduce a new paradigm for accelerating Magnetic Resonance Imaging (MRI), introducing a shift from image reconstruction to proactive predictive imaging. Despite being a cornerstone of modern patient care, MRI's lengthy acquisition times limit clinical throughput. Our novel framework addresses this challenge by first predicting a target contrast image, which then serves as a data-driven prior for reconstructing highly under-sampled data. This informative prior is predicted by a generative model conditioned on diverse data sources, such as other contrast images, previously scanned images, acquisition parameters, patient information. We demonstrate this approach with two key applications: (1) reconstructing FLAIR images using predictions from T1w and/or T2w scans, and (2) reconstructing T1w images using predictions from previously acquired T1w scans. The framework was evaluated on internal and multiple public datasets (total 14,921 scans; 1,051,904 slices), including multi-channel k-space data, for a range of high acceleration factors (x4, x8 and x12). The results demonstrate that our prediction-prior reconstruction method significantly outperforms other approaches, including those with alternative or no prior information. Through this framework we introduce a fundamental shift from image reconstruction towards a new paradigm of predictive imaging.

Problem

• Predicting MRI contrast images before reconstruction
• Using generative models to accelerate MRI acquisition
• Reconstructing highly under-sampled data with data-driven priors

Innovation

• Predictive imaging replaces traditional MRI reconstruction methods
• Generative model creates data-driven prior from multi-source inputs
• Framework reconstructs accelerated scans using predicted contrast images