一个能通用所有MRI扫描的深度模型，性能随规模提升可预测。
SDUM: A Scalable Deep Unrolled Model for Universal MRI Reconstruction
- 用可扩展的级联结构统一处理不同扫描协议和加速方式。
- 单个模型在四个挑战赛中均达顶尖水平，最高比专用模型高1.0dB。
- 组件设计明确有效，适合临床部署和跨中心应用。
临床MRI涵盖多种成像协议——包括心脏、脑、膝关节等解剖目标，T1、T2、定量成像等对比方式，笛卡尔、径向、螺旋、kt空间等采样模式，以及不同的加速因子。然而当前深度学习重建方法通常针对特定协议，难以泛化与部署。本文提出可扩展的深度展开模型（SDUM），结合基于Restormer的重构器、学习型线圈敏感度估计器（CSME）、采样感知加权数据一致性（SWDC）、对级联索引与协议元数据的通用条件输入（UC），以及渐进式级联扩展训练策略。SDUM展现出类似基础模型的扩展特性：重建质量与参数量呈对数关系，相关系数r=0.986（R²=0.973），在最多18级联时仍保持良好表现，性能随模型深度可预测提升。仅用异构数据训练的单一SDUM，在CMRxRecon2025四项挑战（多中心、多疾病、5T、儿科）中均达到最先进水平，无需任务微调，优于专用基线最高达+1.0 dB。在CMRxRecon2024上，较胜出方法PromptMR+高出+0.55 dB；在fastMRI脑部数据集上，超越PC-RNN达+1.8 dB。消融实验验证各组件有效性：SWDC相比标准数据一致性提升+0.43 dB，每级联独立的CSME带来+0.51 dB，UC贡献+0.38 dB。结果表明，SDUM为实现通用、可扩展的MRI重建提供了实用路径。
原文摘要 · Abstract (English)
Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We introduce Scalable Deep Unrolled Model (SDUM), a universal framework combining a Restormer-based reconstructor, a learned coil sensitivity map estimator (CSME), sampling-aware weighted data consistency (SWDC), universal conditioning (UC) on cascade index and protocol metadata, and progressive cascade expansion training. SDUM exhibits foundation-model-like scaling behavior: reconstruction quality follows PSNR ${\sim}$ log(parameters) with correlation $r{=}0.986$ ($R^2{=}0.973$) up to 18 cascades, demonstrating predictable performance gains with model depth. A single SDUM trained on heterogeneous data achieves state-of-the-art results across all four CMRxRecon2025 challenge tracks--multi-center, multi-disease, 5T, and pediatric--without task-specific fine-tuning, surpassing specialized baselines by up to ${+}1.0$~dB. On CMRxRecon2024, SDUM outperforms the winning method PromptMR+ by ${+}0.55$~dB; on fastMRI brain, it exceeds PC-RNN by ${+}1.8$~dB. Ablations validate each component: SWDC ${+}0.43$~dB over standard DC, per-cascade CSME ${+}0.51$~dB, UC ${+}0.38$~dB. These results establish SDUM as a practical path toward universal, scalable MRI reconstruction.
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。