Interlaced dynamic XCT reconstruction with spatio-temporal implicit neural representations

2025/10/09 by Boulanger, Mathias, Ericmoore Jossou, Jossou, Ericmoore
Engineering · Medicine · Physics and Astronomy · #Advanced X-ray Imaging Techniques #Advanced X-ray and CT Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Physical sciences #Image and Video Processing (eess.IV) #Materials Science (cond-mat.mtrl-sci) #Medical Imaging Techniques and Applications #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2510.08641

openalex publication_date 2025/10/09 · openalex created_date 2025/10/14 · openalex updated_date 2026/07/28

Abstract

In this work, we investigate the use of spatio-temporalImplicit Neural Representations (INRs) for dynamic X-ray computed tomography (XCT) reconstruction under interlaced acquisition schemes. The proposed approach combines ADMM-based optimization with INCODE, a conditioning framework incorporating prior knowledge, to enable efficient convergence. We evaluate our method under diverse acquisition scenarios, varying the severity of global undersampling, spatial complexity (quantified via spatial information), and noise levels. Across all settings, our model achieves strong performance and outperforms Time-Interlaced Model-Based Iterative Reconstruction (TIMBIR), a state-of-the-art model-based iterative method. In particular, we show that the inductive bias of the INR provides good robustness to moderate noise levels, and that introducing explicit noise modeling through a weighted least squares data fidelity term significantly improves performance in more challenging regimes. The final part of this work explores extensions toward a practical reconstruction framework. We demonstrate the modularity of our approach by explicitly modeling detector non-idealities, incorporating ring artifact correction directly within the reconstruction process. Additionally, we present a proof-of-concept 4D volumetric reconstruction by jointly optimizing over batched axial slices, an approach which opens up the possibilities for massive parallelization, a critical feature for processing large-scale datasets.

Citations

• Accelerated Optimization of Implicit Neural Representations for CT Reconstruction
• Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCT
• INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings
• Instant neural graphics primitives with a multiresolution hash encoding
• Dynamic CT Reconstruction from Limited Views with Implicit Neural\n Representations and Parametric Motion Fields
• CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
• TorchRadon: Fast Differentiable Routines for Computed Tomography
• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
• PyLops -- A Linear-Operator Python Library for large scale optimization
• Complexity of Linear Regions in Deep Networks
• Image quality assessment: from error visibility to structural similarity
• Nonlinear total variation based noise removal algorithms

Related

• Accelerated Optimization of Implicit Neural Representations for CT Reconstruction
• Distributed Stochastic Optimization of a Neural Representation Network for Time-Space Tomography Reconstruction
• Dynamic CT Reconstruction from Limited Views with Implicit Neural\n Representations and Parametric Motion Fields
• Data-Driven Interpolation for Super-Scarce X-Ray Computed Tomography
• Dynamic CBCT Imaging using Prior Model-Free Spatiotemporal Implicit Neural Representation (PMF-STINR)