A Physics-Informed Deep Learning Model for MRI Brain Motion Correction

2025-02-13

AI Summary

Long scan durations in MRI acquisition often induce motion artifacts, degrading image quality and diagnostic reliability. To address this, we propose PI-MoCoNet—a fully end-to-end motion correction network that bypasses explicit motion parameter estimation. Methodologically, we introduce, for the first time in MRI motion correction, a joint optimization framework integrating physics-driven k-space data consistency constraints with the LPIPS perceptual loss. Furthermore, we design a hybrid architecture synergistically combining U-Net and Swin Transformer modules to jointly detect corrupted k-space lines and reconstruct high-fidelity images. Evaluated on the IXI and MR-ART datasets, PI-MoCoNet significantly outperforms Pix2Pix, CycleGAN, and U-Net: PSNR improves by up to 17.96 dB, SSIM approaches 1.00, and NMSE is reduced by over 90%. Ablation studies confirm that our key loss design contributes approximately 1 dB PSNR gain.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Mixture of Experts (MoE)
• Intelligent Robots: Motion and Path Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Background: MRI is crucial for brain imaging but is highly susceptible to motion artifacts due to long acquisition times. This study introduces PI-MoCoNet, a physics-informed motion correction network that integrates spatial and k-space information to remove motion artifacts without explicit motion parameter estimation, enhancing image fidelity and diagnostic reliability. Materials and Methods: PI-MoCoNet consists of a motion detection network (U-net with spatial averaging) to identify corrupted k-space lines and a motion correction network (U-net with Swin Transformer blocks) to reconstruct motion-free images. The correction is guided by three loss functions: reconstruction (L1), perceptual (LPIPS), and data consistency (Ldc). Motion artifacts were simulated via rigid phase encoding perturbations and evaluated on IXI and MR-ART datasets against Pix2Pix, CycleGAN, and U-net using PSNR, SSIM, and NMSE. Results: PI-MoCoNet significantly improved image quality. On IXI, for minor artifacts, PSNR increased from 34.15 dB to 45.95 dB, SSIM from 0.87 to 1.00, and NMSE reduced from 0.55% to 0.04%. For moderate artifacts, PSNR improved from 30.23 dB to 42.16 dB, SSIM from 0.80 to 0.99, and NMSE from 1.32% to 0.09%. For heavy artifacts, PSNR rose from 27.99 dB to 36.01 dB, SSIM from 0.75 to 0.97, and NMSE decreased from 2.21% to 0.36%. On MR-ART, PI-MoCoNet achieved PSNR gains of ~10 dB and SSIM improvements of up to 0.20, with NMSE reductions of ~6%. Ablation studies confirmed the importance of data consistency and perceptual losses, yielding a 1 dB PSNR gain and 0.17% NMSE reduction. Conclusions: PI-MoCoNet effectively mitigates motion artifacts in brain MRI, outperforming existing methods. Its ability to integrate spatial and k-space information makes it a promising tool for clinical use in motion-prone settings. Code: https://github.com/mosaf/PI-MoCoNet.git.

Problem

• MRI brain motion artifact correction
• Physics-informed deep learning model
• Enhancing image fidelity and reliability

Innovation

• U-net with Swin Transformer blocks
• Physics-informed motion correction network
• Reconstruction, perceptual, data consistency losses