Retrospective motion correction in MRI using disentangled embeddings

2025-11-11

AI Summary

MRI physiological motion artifacts severely degrade diagnostic image quality. Existing retrospective correction methods exhibit poor generalizability, particularly across diverse motion patterns and anatomical regions. To address this, we propose a universal motion artifact correction framework based on disentangled embedding. Specifically, we design a Hierarchical Quantized Variational Autoencoder (HQ-VQ-VAE) that learns disentangled representations—separating motion-related features from anatomical structure features. Furthermore, we incorporate multi-resolution codebooks and autoregressive priors to enable robust generalization to unseen motion types without task-specific fine-tuning. Extensive evaluation on simulated whole-body multi-site motion data demonstrates that our method robustly restores fine anatomical details and achieves significant improvements in PSNR and SSIM. Crucially, it exhibits strong cross-motion-type and cross-anatomical-region generalization, outperforming existing approaches in adaptability and robustness.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Deep Generative Models & Autoencoders
• Intelligent Robots: Motion and Path Planning

Application Category

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

Abstract

Physiological motion can affect the diagnostic quality of magnetic resonance imaging (MRI). While various retrospective motion correction methods exist, many struggle to generalize across different motion types and body regions. In particular, machine learning (ML)-based corrections are often tailored to specific applications and datasets. We hypothesize that motion artifacts, though diverse, share underlying patterns that can be disentangled and exploited. To address this, we propose a hierarchical vector-quantized (VQ) variational auto-encoder that learns a disentangled embedding of motion-to-clean image features. A codebook is deployed to capture finite collection of motion patterns at multiple resolutions, enabling coarse-to-fine correction. An auto-regressive model is trained to learn the prior distribution of motion-free images and is used at inference to guide the correction process. Unlike conventional approaches, our method does not require artifact-specific training and can generalize to unseen motion patterns. We demonstrate the approach on simulated whole-body motion artifacts and observe robust correction across varying motion severity. Our results suggest that the model effectively disentangled physical motion of the simulated motion-effective scans, therefore, improving the generalizability of the ML-based MRI motion correction. Our work of disentangling the motion features shed a light on its potential application across anatomical regions and motion types.

Problem

• Generalizing MRI motion correction across diverse motion types and body regions
• Disentangling shared motion artifact patterns from clean image features
• Eliminating need for artifact-specific training in motion correction methods

Innovation

• Hierarchical VQ autoencoder learns disentangled motion embeddings
• Codebook captures finite motion patterns at multiple resolutions
• Autoregressive model guides correction using motion-free priors