Noise Controlled CT Super-Resolution with Conditional Diffusion Model

TL;DR

This paper presents a novel noise-controlled CT super-resolution framework using a conditional diffusion model, effectively enhancing image resolution while managing noise, validated on real CT images for practical use.

Contribution

It introduces a new diffusion-based approach trained on hybrid datasets for noise-controlled super-resolution in CT imaging, addressing noise amplification issues.

Findings

Effective resolution enhancement demonstrated on real CT images

Noise control capability validated in practical scenarios

Hybrid dataset training improves model robustness

Abstract

Improving the spatial resolution of CT images is a meaningful yet challenging task, often accompanied by the issue of noise amplification. This article introduces an innovative framework for noise-controlled CT super-resolution utilizing the conditional diffusion model. The model is trained on hybrid datasets, combining noise-matched simulation data with segmented details from real data. Experimental results with real CT images validate the effectiveness of our proposed framework, showing its potential for practical applications in CT imaging.