MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRI

2026-01-30

AI Summary

This work addresses the severe artifacts caused by metallic implants in MRI, a challenge often tackled by decoupling artifact suppression from accelerated imaging. In contrast, this study proposes a unified reinforcement learning framework that jointly models both tasks as a sequential decision-making problem, enabling synergistic optimization of metal-aware k-space sampling and artifact correction. Leveraging a physically simulated paired dataset, the method integrates a U-Net-based correction module with Proximal Policy Optimization to enable end-to-end training. Experimental results demonstrate that the learned sampling strategy outperforms conventional approaches, yielding significantly improved image reconstruction quality. Furthermore, the model exhibits strong generalization capability, as evidenced by its robust performance on cross-dataset evaluation using the FastMRI benchmark.

Technology Category

• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Multiagent Learning

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
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Metal implants in MRI cause severe artifacts that degrade image quality and hinder clinical diagnosis. Traditional approaches address metal artifact reduction (MAR) and accelerated MRI acquisition as separate problems. We propose MASC, a unified reinforcement learning framework that jointly optimizes metal-aware k-space sampling and artifact correction for accelerated MRI. To enable supervised training, we construct a paired MRI dataset using physics-based simulation, generating k-space data and reconstructions for phantoms with and without metal implants. This paired dataset provides simulated 3D MRI scans with and without metal implants, where each metal-corrupted sample has an exactly matched clean reference, enabling direct supervision for both artifact reduction and acquisition policy learning. We formulate active MRI acquisition as a sequential decision-making problem, where an artifact-aware Proximal Policy Optimization (PPO) agent learns to select k-space phase-encoding lines under a limited acquisition budget. The agent operates on undersampled reconstructions processed through a U-Net-based MAR network, learning patterns that maximize reconstruction quality. We further propose an end-to-end training scheme where the acquisition policy learns to select k-space lines that best support artifact removal while the MAR network simultaneously adapts to the resulting undersampling patterns. Experiments demonstrate that MASC's learned policies outperform conventional sampling strategies, and end-to-end training improves performance compared to using a frozen pre-trained MAR network, validating the benefit of joint optimization. Cross-dataset experiments on FastMRI with physics-based artifact simulation further confirm generalization to realistic clinical MRI data. The code and models of MASC have been made publicly available: https://github.com/hrlblab/masc

Problem

• metal artifact reduction
• accelerated MRI
• k-space sampling
• MRI reconstruction
• metal implants

Innovation

• reinforcement learning
• metal artifact reduction
• accelerated MRI
• k-space sampling
• end-to-end optimization