Progressively Texture-Aware Diffusion for Contrast-Enhanced Sparse-View CT

TL;DR

This paper introduces a progressive, texture-aware diffusion model for sparse-view CT that improves image quality by combining coarse reconstruction with a conditional diffusion process for detailed textures.

Contribution

The proposed PTD framework uniquely integrates a deterministic low-frequency reconstruction with a dual-domain guided diffusion for high-fidelity textures in SVCT.

Findings

PTD outperforms existing methods in structure similarity.

PTD achieves superior visual quality with fewer sampling steps.

The model effectively balances image fidelity and texture detail.

Abstract

Diffusion-based sparse-view CT (SVCT) imaging has achieved remarkable advancements in recent years, thanks to its more stable generative capability. However, recovering reliable image content and visually consistent textures is still a crucial challenge. In this paper, we present a Progressively Texture-aware Diffusion (PTD) model, a coarse-to-fine learning framework tailored for SVCT. Specifically, PTD comprises a basic reconstructive module PTD$_{\textit{rec}}$ and a conditional diffusion module PTD$_{\textit{diff}}$. PTD$_{\textit{rec}}$ first learns a deterministic mapping to recover the majority of the underlying low-frequency signals (i.e., coarse content with smoothed textures), which serves as the initial estimation to enable fidelity. Moreover, PTD$_{\textit{diff}}$ aims to reconstruct high-fidelity details for coarse prediction, which explores a dual-domain guided conditional diffusion to generate reliable and consistent textures. Extensive experiments on sparse-view CT reconstruction demonstrate that our PTD achieves superior performance in terms of structure similarity and visual appeal with only a few sampling steps, which mitigates the randomness inherent in general diffusion models and enables a better trade-off between visual quality and fidelity of high-frequency details.