Visible Singularities Guided Correlation Network for Limited-Angle CT Reconstruction

2026-01-30

AI Summary

This study addresses directional artifacts and structural information loss in limited-angle CT reconstruction caused by missing projections. To tackle this challenge, the authors introduce visible singularity theory into the task for the first time and propose a visible singularity-guided correlation network. The method extracts visible singularity edge features, models their correlations with other image regions, and incorporates a multi-scale anisotropic loss function to guide network optimization. Experimental results on both simulated and real-world datasets demonstrate that the proposed approach significantly improves reconstruction quality under highly limited angular ranges, achieving a 2.45 dB gain in PSNR and a 1.5% improvement in SSIM, outperforming existing state-of-the-art methods.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Learning with Manifolds
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Limited-angle computed tomography (LACT) offers the advantages of reduced radiation dose and shortened scanning time. Traditional reconstruction algorithms exhibit various inherent limitations in LACT. Currently, most deep learning-based LACT reconstruction methods focus on multi-domain fusion or the introduction of generic priors, failing to fully align with the core imaging characteristics of LACT-such as the directionality of artifacts and directional loss of structural information, which are caused by the absence of projection angles in certain directions. Inspired by the theory of visible and invisible singularities, taking into account the aforementioned core imaging characteristics of LACT, we propose a Visible Singularities Guided Correlation network for LACT reconstruction (VSGC). The design philosophy of VSGC consists of two core steps: First, extract VS edge features from LACT images and focus the model's attention on these VS. Second, establish correlations between the VS edge features and other regions of the image. Additionally, a multi-scale loss function with anisotropic constraint is employed to constrain the model to converge in multiple aspects. Finally, qualitative and quantitative validations are conducted on both simulated and real datasets to verify the effectiveness and feasibility of the proposed design. Particularly, in comparison with alternative methods, VSGC delivers more prominent performance in small angular ranges, with the PSNR improvement of 2.45 dB and the SSIM enhancement of 1.5\%. The code is publicly available at https://github.com/yqx7150/VSGC.

Problem

• Limited-angle CT
• directional artifacts
• structural information loss
• visible singularities
• CT reconstruction

Innovation

• Visible Singularities
• Limited-Angle CT
• Directional Artifact
• Correlation Network
• Anisotropic Constraint