用可变分辨率采样+深度学习，加速金属附近多光谱MRI扫描
Variable Resolution Sampling and Deep Learning Image Recovery for Accelerated Multi-Spectral MRI Near Metal Implants
- 设计可变分辨率采样方案，提升采集效率约40%
- 深度学习重建使图像结构相似性与信噪比显著提升（p<0.001）
- 适合需要快速成像的金属植入物患者，尤其关注图像边缘清晰度
目的：本研究提出一种针对金属植入物附近的多光谱磁共振成像（MSI）的可变分辨率（VR）采样与深度学习重建方法，旨在缩短扫描时间的同时保持图像质量。背景：金属植入物使用增加导致受金属伪影影响的MRI检查增多。多光谱成像可减少伪影，但牺牲了采集效率。方法：对1.5T MSI膝关节和髋关节数据进行回顾性研究，采用新型光谱欠采样方案，将采集效率提升约40%。基于U-Net的深度学习模型用于图像重建。通过结构相似性（SSIM）、峰值信噪比（PSNR）和残差误差指数（RESI）评估图像质量。结果：深度学习重建的欠采样VR数据（DL-VR）相比传统重建（CR-VR）在SSIM和PSNR上显著更高（p<0.001），边缘锐度更优；其边缘锐度与全采样参考图像无显著差异（p=0.5）。结论：该方法有望通过缩短扫描时间或实现更高分辨率，改善金属植入物附近的MRI检查。需进一步前瞻性研究评估其临床价值。
原文摘要 · Abstract (English)
Purpose: This study presents a variable resolution (VR) sampling and deep learning reconstruction approach for multi-spectral MRI near metal implants, aiming to reduce scan times while maintaining image quality. Background: The rising use of metal implants has increased MRI scans affected by metal artifacts. Multi-spectral imaging (MSI) reduces these artifacts but sacrifices acquisition efficiency. Methods: This retrospective study on 1.5T MSI knee and hip data from patients with metal hardware used a novel spectral undersampling scheme to improve acquisition efficiency by ~40%. U-Net-based deep learning models were trained for reconstruction. Image quality was evaluated using SSIM, PSNR, and RESI metrics. Results: Deep learning reconstructions of undersampled VR data (DL-VR) showed significantly higher SSIM and PSNR values (p<0.001) compared to conventional reconstruction (CR-VR), with improved edge sharpness. Edge sharpness in DL-reconstructed images matched fully sampled references (p=0.5). Conclusion: This approach can potentially enhance MRI examinations near metal implants by reducing scan times or enabling higher resolution. Further prospective studies are needed to assess clinical value.
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。