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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Hao, Yu, Hao, Teng, Sihao, Zhang, Tao, Yuan, Siyi, He, Huaiwu, Liu, Zhe, Yang, Yunjie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908455707607040
author Fang, Hao
Yu, Hao
Teng, Sihao
Zhang, Tao
Yuan, Siyi
He, Huaiwu
Liu, Zhe
Yang, Yunjie
author_facet Fang, Hao
Yu, Hao
Teng, Sihao
Zhang, Tao
Yuan, Siyi
He, Huaiwu
Liu, Zhe
Yang, Yunjie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14046
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle D2IP: Deep Dynamic Image Prior for 3D Time-sequence Pulmonary Impedance Imaging
Fang, Hao
Yu, Hao
Teng, Sihao
Zhang, Tao
Yuan, Siyi
He, Huaiwu
Liu, Zhe
Yang, Yunjie
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
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.
title D2IP: Deep Dynamic Image Prior for 3D Time-sequence Pulmonary Impedance Imaging
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2507.14046