D2IP: Deep Dynamic Image Prior for 3D Time-sequence Pulmonary Impedance Imaging
This addresses computational efficiency for clinical dynamic pulmonary imaging, though it appears incremental as it builds on existing Deep Image Prior methods.
The paper tackled the high computational cost of unsupervised learning methods like Deep Image Prior in 3D time-sequence tomographic imaging by proposing D2IP, which achieved a 24.8% increase in MSSIM, 8.1% reduction in ERR, and 7.1x faster computational time compared to baselines.
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.