PLOT-CT: Pre-log Voronoi Decomposition Assisted Generation for Low-dose CT Reconstruction

2026-02-12

AI Summary

This work addresses the challenge of low-dose CT reconstruction, where reduced radiation dose leads to severe noise and degraded data fidelity. Conventional approaches operating in the image domain or log-transformed projection domain struggle to effectively exploit structural information present in pre-log measurements and are prone to noise amplification. To overcome these limitations, this paper proposes PLOT-CT, a novel framework that introduces Voronoi decomposition into pre-log CT reconstruction for the first time. By decomposing the sinogram into multiple underlying components and embedding them into distinct latent spaces, PLOT-CT directly models the reconstruction process in the pre-log domain, explicitly separating signal from noise and avoiding distortions induced by logarithmic transformation. The method achieves state-of-the-art performance, improving PSNR by 2.36 dB over existing methods at an incident photon level of 1e4.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Low Level & Physics-based Vision

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
• Web Mining and Content Analysis: Web traffic and log analysis

Abstract

Low-dose computed tomography (LDCT) reconstruction is fundamentally challenged by severe noise and compromised data fidelity under reduced radiation exposure. Most existing methods operate either in the image or post-log projection domain, which fails to fully exploit the rich structural information in pre-log measurements while being highly susceptible to noise. The requisite logarithmic transformation critically amplifies noise within these data, imposing exceptional demands on reconstruction precision. To overcome these challenges, we propose PLOT-CT, a novel framework for Pre-Log vOronoi decomposiTion-assisted CT generation. Our method begins by applying Voronoi decomposition to pre-log sinograms, disentangling the data into distinct underlying components, which are embedded in separate latent spaces. This explicit decomposition significantly enhances the model's capacity to learn discriminative features, directly improving reconstruction accuracy by mitigating noise and preserving information inherent in the pre-log domain. Extensive experiments demonstrate that PLOT-CT achieves state-of-the-art performance, attaining a 2.36dB PSNR improvement over traditional methods at the 1e4 incident photon level in the pre-log domain.

Problem

• Low-dose CT
• pre-log domain
• noise amplification
• data fidelity
• CT reconstruction

Innovation

• Pre-log domain
• Voronoi decomposition
• Low-dose CT reconstruction
• Noise suppression
• Latent space disentanglement