发表机构
Faculty of Information Engineering and Automation, Kunming University of Science and Technology; Academy of Artificial Intelligence and Advanced Technology, Xi’an Jiaotong-Liverpool University; Massachusetts General Hospital; Harvard Medical School（昆明理工大学信息工程与自动化学院; 西交利物浦大学人工智能与先进技术研究院; 麻省总医院; 哈佛医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ContiLNN通过在二维复原骨干中加入Bi-CfC模块，提升了CT去噪、MRI超分辨率等医学图像复原任务的性能，且延迟和内存占用低于Bi-GRU，具备良好的数据效率与兼容性。
AI 中文摘要
解剖连续性为医学图像复原提供了互补信息，但使用该信息需考虑局部解剖结构及切片采样的变化。本文提出ContiLNN，它在二维复原骨干网络中加入双向闭式连续时间（Bi-CfC）模块以实现跨切片建模，同时保留平面内特征提取功能。切片索引间隔会调节由局部特征和隐藏状态决定的门控，使传播能响应采样变化而无需数值常微分方程（ODE）积分。参考引导一致性将一阶和二阶跨切片强度差异对齐，以保留解剖结构变化，而冻结骨干网络的知识蒸馏则有助于维持平面内保真度。在5个训练随机种子下，ContiLNN在CT去噪、MRI超分辨率、低计数PET复原任务中，相比Restore-RWKV分别将平均峰值信噪比（PSNR）提升0.1907、1.0176、1.2482分贝，且在这三项任务中均降低了均方根误差（RMSE）。CT结果对一名保留患者具有描述性，PET消融实验支持有序传播超出额外逐点容量的结论。在连续训练下，Bi-CfC在所有测试采样条件下，相比参数数量和计算成本相近的双向门控循环单元（Bi-GRU）实现了更高的保真度；匹配的7切片分析显示，Bi-CfC的延迟比Bi-GRU低52.8%，峰值GPU内存使用量低57.0%。混合间隔训练提升了两种算子在稀疏和不规则上下文下的性能，但在不同指标和上下文间无统一排名；减少训练患者数量及使用第二个骨干网络的实验，进一步验证了其数据效率和骨干网络兼容性。
英文摘要
Anatomical continuity provides complementary information for medical image restoration, but its use requires accounting for local anatomy and variations in slice sampling. We introduce ContiLNN, which augments two-dimensional restoration backbones with bidirectional closed-form continuous-time (Bi-CfC) modules for cross-slice modeling while retaining in-plane feature extraction. Slice-index intervals modulate gates determined by local features and hidden states, enabling propagation to respond to sampling variations without numerical ODE integration. Reference-guided consistency aligns first- and second-order cross-slice intensity differences to preserve anatomical variation, while distillation from a frozen backbone helps retain in-plane fidelity. Across five training seeds, ContiLNN improves mean PSNR over Restore-RWKV by 0.1907, 1.0176, and 1.2482 dB for CT denoising, MRI super-resolution, and reduced-count PET restoration, respectively, with lower RMSE in all three tasks. CT results are descriptive for one held-out patient. PET ablations support ordered propagation beyond additional pointwise capacity. Under contiguous training, Bi-CfC achieves higher fidelity than a Bi-GRU with similar parameter counts and arithmetic costs across all tested sampling conditions. Matched seven-slice profiling shows 52.8% lower latency and 57.0% lower peak GPU memory use than Bi-GRU. Mixed-gap training improves sparse and irregular-context performance for both operators, without a uniform ranking across metrics and contexts. Experiments with fewer training patients and a second backbone further support data efficiency and backbone compatibility.
