Motion-Robust T2* Quantification from Gradient Echo MRI with Physics-Informed Deep Learning

2025-02-24

AI Summary

In gradient-echo MRI, T2* quantification is highly susceptible to motion artifacts and magnetic field inhomogeneities, leading to signal dropout and quantitative inaccuracies. To address this, we propose a physics-informed deep learning framework that tightly integrates motion modeling, gradient-echo signal physics constraints, and an end-to-end differentiable reconstruction network. Our approach extends the PHIMO framework by embedding acquisition-specific priors—explicitly encoding k-space trajectory, echo-time dependence, and field inhomogeneity effects—thereby enhancing robustness against severe B0 inhomogeneity and complex motion patterns. Quantitatively, our method achieves T2* map accuracy comparable to conventional redundant-sampling techniques while outperforming state-of-the-art learning-based motion correction baselines. Critically, it reduces scan time by over 40%, achieving a favorable trade-off among accuracy, robustness, and efficiency. This work establishes a new paradigm for rapid, reliable clinical T2* quantification.

Technology Category

• Machine Learning: Learning with Manifolds
• Search and Optimization: Learning to Search
• Computer Vision: Motion & Tracking

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
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Purpose: T2* quantification from gradient echo magnetic resonance imaging is particularly affected by subject motion due to the high sensitivity to magnetic field inhomogeneities, which are influenced by motion and might cause signal loss. Thus, motion correction is crucial to obtain high-quality T2* maps. Methods: We extend our previously introduced learning-based physics-informed motion correction method, PHIMO, by utilizing acquisition knowledge to enhance the reconstruction performance for challenging motion patterns and increase PHIMO's robustness to varying strengths of magnetic field inhomogeneities across the brain. We perform comprehensive evaluations regarding motion detection accuracy and image quality for data with simulated and real motion. Results: Our extended version of PHIMO outperforms the learning-based baseline methods both qualitatively and quantitatively with respect to line detection and image quality. Moreover, PHIMO performs on-par with a conventional state-of-the-art motion correction method for T2* quantification from gradient echo MRI, which relies on redundant data acquisition. Conclusion: PHIMO's competitive motion correction performance, combined with a reduction in acquisition time by over 40% compared to the state-of-the-art method, make it a promising solution for motion-robust T2* quantification in research settings and clinical routine.

Problem

• Motion correction for T2* MRI
• Enhancing PHIMO robustness
• Reducing acquisition time significantly

Innovation

• Physics-informed deep learning
• Enhanced motion correction
• Reduced acquisition time