Physics-informed 4D X-ray image reconstruction from ultra-sparse spatiotemporal data

2025-04-04

AI Summary

This work addresses the ill-posed 4D dynamic reconstruction problem from ultra-sparse spatiotemporal X-ray data—characterized by extremely few projections and sparse temporal sampling. We propose 4D-PIONIX, a physics-informed neural X-ray imaging framework. Methodologically, it integrates a full physical process model (e.g., fluid dynamics) into a neural implicit representation for the first time, surpassing prior approaches that only incorporate ray-propagation physics; it jointly unifies X-ray forward modeling, physics-constrained optimization, and end-to-end differentiable neural reconstruction. Evaluated on binary droplet collision simulations, 4D-PIONIX achieves high-fidelity 4D structural and dynamical reconstruction using minimal projection and temporal data. Quantitatively and qualitatively, it significantly outperforms conventional analytical methods and state-of-the-art AI-based reconstruction techniques.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

The unprecedented X-ray flux density provided by modern X-ray sources offers new spatiotemporal possibilities for X-ray imaging of fast dynamic processes. Approaches to exploit such possibilities often result in either i) a limited number of projections or spatial information due to limited scanning speed, as in time-resolved tomography, or ii) a limited number of time points, as in stroboscopic imaging, making the reconstruction problem ill-posed and unlikely to be solved by classical reconstruction approaches. 4D reconstruction from such data requires sample priors, which can be included via deep learning (DL). State-of-the-art 4D reconstruction methods for X-ray imaging combine the power of AI and the physics of X-ray propagation to tackle the challenge of sparse views. However, most approaches do not constrain the physics of the studied process, i.e., a full physical model. Here we present 4D physics-informed optimized neural implicit X-ray imaging (4D-PIONIX), a novel physics-informed 4D X-ray image reconstruction method combining the full physical model and a state-of-the-art DL-based reconstruction method for 4D X-ray imaging from sparse views. We demonstrate and evaluate the potential of our approach by retrieving 4D information from ultra-sparse spatiotemporal acquisitions of simulated binary droplet collisions, a relevant fluid dynamic process. We envision that this work will open new spatiotemporal possibilities for various 4D X-ray imaging modalities, such as time-resolved X-ray tomography and more novel sparse acquisition approaches like X-ray multi-projection imaging, which will pave the way for investigations of various rapid 4D dynamics, such as fluid dynamics and composite testing.

Problem

• Reconstructing 4D X-ray images from ultra-sparse spatiotemporal data
• Combining full physical models with deep learning for sparse-view imaging
• Enabling 4D dynamic process studies like fluid dynamics via X-ray imaging

Innovation

• Combines full physical model with deep learning
• Reconstructs 4D X-ray images from sparse views
• Optimizes neural implicit X-ray imaging