Tomographic Foundation Model -- FORCE: Flow-Oriented Reconstruction Conditioning Engine

TL;DR

This paper introduces FORCE, a novel CT reconstruction framework that combines data fidelity with advanced generative AI models, achieving superior results in challenging clinical scenarios without relying on paired training data.

Contribution

The paper presents FORCE, integrating Poisson flow generative models with data fidelity for improved CT image reconstruction, addressing data scarcity and hallucination issues.

Findings

Outperforms existing unsupervised methods in CT reconstruction tasks.

Effective in low-dose, sparse-view, and metal artifact scenarios.

Demonstrates robustness without paired training data.

Abstract

Computed tomography (CT) is a major medical imaging modality. Clinical CT scenarios, such as low-dose screening, sparse-view scanning, and metal implants, often lead to severe noise and artifacts in reconstructed images, requiring improved reconstruction techniques. The introduction of deep learning has significantly advanced CT image reconstruction. However, obtaining paired training data remains rather challenging due to patient motion and other constraints. Although deep learning methods can still perform well with approximately paired data, they inherently carry the risk of hallucination due to data inconsistencies and model instability. In this paper, we integrate the data fidelity with the state-of-the-art generative AI model, referred to as the Poisson flow generative model (PFGM) with a generalized version PFGM++, and propose a novel CT framework: Flow-Oriented Reconstruction Conditioning Engine (FORCE). In our experiments, the proposed method shows superior performance in various CT imaging tasks, outperforming existing unsupervised reconstruction approaches.