Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine

2025-03-25

AI Summary

In X-ray nanotomography, limited-angle acquisition induces the “missing wedge” problem, causing severe streaking artifacts and anisotropic resolution degradation. To address this, we propose a physics-informed reconstruction method that integrates perceptual priors: a lightweight CNN serves as an interpretable perceptual regularizer embedded within an ADMM-based multi-domain joint optimization framework—unifying physical consistency (projection domain) and visual fidelity (image domain). Unlike data-driven deep learning methods, our approach requires no additional training for sparse-projection generalization, eliminating dependence on full-angle data. Under extreme missing-wedge conditions (>100°), it effectively suppresses streaking and structural artifacts while recovering isotropic spatial resolution. We validate its robustness and generalizability across multiple real-world X-ray microscopy datasets, demonstrating consistent performance without task-specific retraining.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

A long-standing challenge in tomography is the 'missing wedge' problem, which arises when the acquisition of projection images within a certain angular range is restricted due to geometrical constraints. This incomplete dataset results in significant artifacts and poor resolution in the reconstructed image. To tackle this challenge, we propose an approach dubbed Perception Fused Iterative Tomography Reconstruction Engine, which integrates a convolutional neural network (CNN) with perceptional knowledge as a smart regularizer into an iterative solving engine. We employ the Alternating Direction Method of Multipliers to optimize the solution in both physics and image domains, thereby achieving a physically coherent and visually enhanced result. We demonstrate the effectiveness of the proposed approach using various experimental datasets obtained with different x-ray microscopy techniques. All show significantly improved reconstruction even with a missing wedge of over 100 degrees - a scenario where conventional methods fail. Notably, it also improves the reconstruction in case of sparse projections, despite the network not being specifically trained for that. This demonstrates the robustness and generality of our method of addressing commonly occurring challenges in 3D x-ray imaging applications for real-world problems.

Problem

• Addresses 'missing wedge' issue in limited-angle x-ray nano-tomography
• Integrates CNN with iterative reconstruction to reduce artifacts
• Improves resolution in sparse or incomplete projection datasets

Innovation

• Machine-learning enabled iterative reconstruction engine
• CNN integrated as smart regularizer
• Alternating Direction Method of Multipliers optimization