发表机构
Biomedical Basic Research Center (BBRC) of Jiangsu; State Key Laboratory of Precision and Intelligent Chemistry（江苏省生物医学基础研究中心; 精准与智能化学国家重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MARR通过解耦策略路由、模态私有残差执行和输出校准，实现无需退化标签的PET、CT和MRI全能恢复，在基准上以34.43 dB平均PSNR超越十三种方法。
AI 中文摘要
全能医学图像恢复旨在用单一模型恢复异质临床图像，但PET、CT和MRI在退化统计、解剖对比度和输出空间偏差上差异显著。完全共享的网络会纠缠模态特定的残差误差，而分离的模态特定网络则牺牲了统一部署的实际优势。因此，我们将全能恢复重新表述为有限适应应置于何处的问题：策略选择、特征执行或输出校准。我们提出MARR，一个紧凑的恢复框架，将多模态适应约束为退化感知的策略路由、模态私有残差执行和图像域残差校正，无需退化标签或分离的模态特定模型。策略分支从输入统计、潜在内容和模态身份形成路由提示，并仅将其用作控制信号。提示门控的模态私有适配器随后在中间解码器阶段执行轻量级残差细化，而零初始化的模态特定输出头校准最终图像域残差，不干扰初始共享预测。在PET、CT和MRI的全能恢复基准上，MARR优于在同一协议下重新训练的十三种方法，在PET、CT和MRI上分别达到37.34 dB、33.85 dB和32.09 dB的PSNR值，以及最佳的模态平均PSNR 34.43 dB。代码公开于该https URL。
英文摘要
All-in-one medical image restoration seeks to recover heterogeneous clinical images with a single model, but PET, CT, and MRI differ substantially in degradation statistics, anatomical contrast, and output-space bias. A fully shared network can entangle modality-specific residual errors, whereas separate modality-specific networks sacrifice the practical advantages of unified deployment. We therefore recast all-in-one restoration as a question of where limited adaptation should be placed: policy selection, feature execution, or output calibration. We propose MARR, a compact restoration framework that constrains multi-modality adaptation into degradation-aware policy routing, modality-private residual execution, and image-domain residual correction without requiring degradation labels or separate modality-specific models. The policy branch forms a routing prompt from input statistics, latent content, and modality identity, and uses it only as a control signal. Prompt-gated modality-private adapters then perform lightweight residual refinement at intermediate decoder stages, while zero-initialized modality-specific output heads calibrate the final image-domain residual without perturbing the initial shared prediction. On an all-in-one PET, CT, and MRI restoration benchmark, MARR outperforms thirteen methods re-trained under the same protocol, achieving PSNR values of 37.34 dB, 33.85 dB, and 32.09 dB on PET, CT, and MRI, respectively, and the best modality-average PSNR of 34.43 dB. The code is publicly available at https://github.com/CHB-learner/MARR.
Comments8 pages, 4 figures, 2 tables
