Data-iterative Optimization Score Model for Stable Ultra-Sparse-View CT Reconstruction

TL;DR

This paper introduces a data-iterative optimization score model (DOSM) for ultra-sparse-view CT reconstruction, effectively balancing data consistency and generative modeling to improve image quality even with very few views.

Contribution

The paper proposes a novel DOSM that integrates data consistency into the SDE framework and introduces an inference strategy for stable, high-quality reconstructions from sparse data.

Findings

DOSM outperforms existing methods on numerical and clinical datasets.

Achieves high-quality reconstructions with as few as 10 views.

Demonstrates superior stability and accuracy in ultra-sparse-view CT imaging.

Abstract

Score-based generative models (SGMs) have gained prominence in sparse-view CT reconstruction for their precise sampling of complex distributions. In SGM-based reconstruction, data consistency in the score-based diffusion model ensures close adherence of generated samples to observed data distribution, crucial for improving image quality. Shortcomings in data consistency characterization manifest in three aspects. Firstly, data from the optimization process can lead to artifacts in reconstructed images. Secondly, it often neglects that the generation model and original data constraints are independently completed, fragmenting unity. Thirdly, it predominantly focuses on constraining intermediate results in the inverse sampling process, rather than ideal real images. Thus, we propose an iterative optimization data scoring model. This paper introduces the data-iterative optimization score-based model (DOSM), integrating innovative data consistency into the Stochastic Differential Equation, a valuable constraint for ultra-sparse-view CT reconstruction. The novelty of this data consistency element lies in its sole reliance on original measurement data to confine generation outcomes, effectively balancing measurement data and generative model constraints. Additionally, we pioneer an inference strategy that traces back from current iteration results to ideal truth, enhancing reconstruction stability. We leverage conventional iteration techniques to optimize DOSM updates. Quantitative and qualitative results from 23 views of numerical and clinical cardiac datasets demonstrate DOSM's superiority over other methods. Remarkably, even with 10 views, our method achieves excellent performance.