D2IP加速肺部阻抗成像，让3D动态成像更快更准。
D2IP: Deep Dynamic Image Prior for 3D Time-sequence Pulmonary Impedance Imaging
- 用动态参数初始化与传播，减少网络迭代次数。
- 相比顶尖方法，图像质量提升24.8%（MSSIM），误差降低8.1%。
- 适合临床实时肺功能动态成像，计算速度提升7.1倍。
无监督学习方法如深度图像先验（DIP）因其无需训练数据且泛化能力强，在断层成像中展现出巨大潜力。然而，其依赖大量网络参数迭代导致计算成本高，限制了在复杂3D或时序断层成像中的应用。为此，我们提出深度动态图像先验（D2IP）框架，用于3D时序成像。D2IP引入三项关键策略：无监督参数预热（UPWS）、时间参数传播（TPP）及定制轻量级重建主干网络3D-FastResUNet，以加速收敛、保证时序一致性并提升计算效率。在模拟与临床肺部数据集上的实验表明，D2IP实现了快速准确的3D时序电学阻抗断层成像（tsEIT）重建。相较于现有最优基线方法，其平均MSSIM提升24.8%，误差（ERR）降低8.1%，同时计算时间减少7.1倍，展现出在临床动态肺部成像中的巨大潜力。
原文摘要 · Abstract (English)
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.
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。