用物理约束的深度学习模型，自动修复脑部MRI运动伪影。
A Physics-Informed Deep Learning Model for MRI Brain Motion Correction
- 结合空间与k空间信息，无需估计运动参数直接纠错
- 在多个数据集上提升图像质量，峰值信噪比最高增10分贝
- 适合临床脑部MRI扫描中易受运动干扰的场景
MRI对脑部成像至关重要，但因采集时间长易受运动伪影影响。本文提出PI-MoCoNet，一种融合物理先验的运动校正网络，通过整合空间与k空间信息，在不显式估计运动参数的前提下有效去除伪影，提升图像保真度与诊断可靠性。该模型包含两个U-net结构：一个用于检测受损k空间线，另一个用于重建无运动伪影图像，训练时采用重建（L1）、感知（LPIPS）和数据一致性（Ldc）三项损失函数。运动伪影通过刚性相位编码扰动生成，在IXI与MR-ART数据集上与Pix2Pix、CycleGAN及U-net对比，评估指标包括PSNR、SSIM与NMSE。结果显示：在IXI数据集上，轻微伪影下PSNR从34.15 dB升至45.95 dB，SSIM由0.87增至1.00，NMSE从0.55%降至0.04%；中等伪影下，PSNR由30.23 dB升至42.16 dB，SSIM由0.80升至0.99，NMSE从1.32%降至0.09%；重度伪影下，PSNR由27.99 dB升至36.01 dB，SSIM由0.75升至0.97，NMSE从2.21%降至0.36%。在MR-ART上，平均提升约10 dB PSNR，SSIM改善达0.20，NMSE下降约6%。消融实验表明，数据一致性和感知损失对性能至关重要，分别带来1 dB PSNR提升和0.17% NMSE降低。结论：PI-MoCoNet能有效抑制脑部MRI运动伪影，优于现有方法，具备临床应用潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。