多对比度MRI运动校正：基于参数信息解缠与自适应专家网络
Multi-Contrast MRI Motion Correction via Parameter-Informed Disentanglement and Adaptive Experts
AI总结：
提出一种结合参数信息对比度解缠与严重度感知自适应校正的统一框架，通过ScanCLIP提取对比度嵌入以分离解剖内容，利用视觉Transformer估计运动严重度并路由至专家混合网络，实现跨对比度与严重度的运动伪影校正，在IXI和HCP基准上优于现有方法。
摘要：
磁共振成像中的运动伪影降低了诊断可靠性。现有的深度学习方法通常针对特定对比度，无法泛化到不同模态和伪影严重度。我们提出一个统一框架，结合参数信息对比度解缠与严重度感知自适应校正。ScanCLIP在超过30,000个MRI文本-图像对上预训练，从采集参数中导出对比度嵌入，将对比度风格与解剖内容分离，得到无对比度特征。然后，视觉Transformer估计运动严重度，并通过专家混合网络路由特征，实现针对性伪影校正。双路径解码器重建干净图像和残差伪影图，强制执行图像空间一致性。在IXI和HCP基准上，我们的方法在PSNR上提升0.75 dB，SSIM最高提升0.0279，优于现有方法，且在更高伪影严重度下增益更大。该方法在真实临床数据上展现出鲁棒的零样本泛化能力，这些数据使用未见过的扫描参数采集，而现有方法要么无法去除伪影，要么引入额外失真。
英文摘要：
Motion artifacts in magnetic resonance imaging (MRI) degrade diagnostic reliability. Existing deep learning methods are typically contrast-specific and fail to generalize across diverse modalities and artifact severities. We propose a unified framework combining parameter-informed contrast disentanglement with severity-aware adaptive correction. ScanCLIP, pretrained on over 30,000 MRI text-image pairs, derives contrast embeddings from acquisition parameters to disentangle contrast style from anatomical content, yielding contrast-free features. A Vision Transformer then estimates motion severity and routes features through a Mixture-of-Experts network, enabling targeted artifact correction. A dual-pathway decoder reconstructs both the clean image and residual artifact map, enforcing image-space consistency. On IXI and HCP benchmarks, our method improves PSNR by 0.75 dB and SSIM by up to 0.0279 over state-of-the-art approaches, with larger gains at higher artifact severities. It further demonstrates robust zero-shot generalization on real-world clinical data acquired with unseen scanning parameters, where existing methods either fail to remove artifacts or introduce additional distortions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
