标题： D2IP：用于三维时间序列肺部阻抗成像的深度动态图像先验 显示英文标题

标题： D2IP: Deep Dynamic Image Prior for 3D Time-sequence Pulmonary Impedance Imaging

摘要： 无监督学习方法，如深度图像先验（DIP），由于其无需训练数据且泛化能力强，已在断层成像中展现出巨大潜力。然而，它们依赖于大量的网络参数迭代，导致计算成本高，限制了其实际应用，尤其是在复杂的3D或时间序列断层成像任务中。为克服这些挑战，我们提出了深度动态图像先验（D2IP），一种用于3D时间序列成像的新框架。D2IP引入了三种关键策略——无监督参数热启动（UPWS）、时间参数传播（TPP）以及定制的轻量级重建主干网络3D-FastResUNet，以加速收敛、增强时间一致性并提高计算效率。在模拟和临床肺部数据集上的实验结果表明，D2IP能够实现快速且准确的3D时间序列电阻抗断层成像（tsEIT）重建。与最先进的基线方法相比，D2IP提供了更优的图像质量，平均MSSIM提高了24.8%，ERR降低了8.1%，同时计算时间显著减少（快7.1倍），突显了其在临床动态肺部成像中的前景。 显示英文摘要

摘要： Unsupervised learning methods, such as Deep Image Prior (DIP), have shown great potential in tomographic imaging due to their training-data-free nature and high generalization capability. However, their reliance on numerous network parameter iterations results in high computational costs, limiting their practical application, particularly in complex 3D or time-sequence tomographic imaging tasks. To overcome these challenges, we propose Deep Dynamic Image Prior (D2IP), a novel framework for 3D time-sequence imaging. D2IP introduces three key strategies - Unsupervised Parameter Warm-Start (UPWS), Temporal Parameter Propagation (TPP), and a customized lightweight reconstruction backbone, 3D-FastResUNet - to accelerate convergence, enforce temporal coherence, and improve computational efficiency. Experimental results on both simulated and clinical pulmonary datasets demonstrate that D2IP enables fast and accurate 3D time-sequence Electrical Impedance Tomography (tsEIT) reconstruction. Compared to state-of-the-art baselines, D2IP delivers superior image quality, with a 24.8% increase in average MSSIM and an 8.1% reduction in ERR, alongside significantly reduced computational time (7.1x faster), highlighting its promise for clinical dynamic pulmonary imaging.