One CT Unified Model Training Framework to Rule All Scanning Protocols

TL;DR

This paper introduces a novel unsupervised framework called UMS that enhances CT image reconstruction across various scanning protocols by bridging sub-manifold gaps and dynamically adapting to domain-specific features.

Contribution

It proposes a new Uncertainty-Guided Manifold Smoothing framework that effectively models discrete sub-manifolds in feature space and dynamically incorporates global and sub-manifold features for improved CT reconstruction.

Findings

UMS improves generalization across different scanning protocols.

The framework achieves superior reconstruction quality in experiments.

It effectively bridges gaps between sub-manifolds in feature space.

Abstract

Non-ideal measurement computed tomography (NICT), which lowers radiation at the cost of image quality, is expanding the clinical use of CT. Although unified models have shown promise in NICT enhancement, most methods require paired data, which is an impractical demand due to inevitable organ motion. Unsupervised approaches attempt to overcome this limitation, but their assumption of homogeneous noise neglects the variability of scanning protocols, leading to poor generalization and potential model collapse. We further observe that distinct scanning protocols, which correspond to different physical imaging processes, produce discrete sub-manifolds in the feature space, contradicting these assumptions and limiting their effectiveness. To address this, we propose an Uncertainty-Guided Manifold Smoothing (UMS) framework to bridge the gaps between sub-manifolds. A classifier in UMS identifies sub-manifolds and predicts uncertainty scores, which guide the generation of diverse samples across the entire manifold. By leveraging the classifier's capability, UMS effectively fills the gaps between discrete sub-manifolds, and promotes a continuous and dense feature space. Due to the complexity of the global manifold, it's hard to directly model it. Therefore, we propose to dynamically incorporate the global- and sub-manifold-specific features. Specifically, we design a global- and sub-manifold-driven architecture guided by the classifier, which enables dynamic adaptation to subdomain variations. This dynamic mechanism improves the network's capacity to capture both shared and domain-specific features, thereby improving reconstruction performance. Extensive experiments on public datasets are conducted to validate the effectiveness of our method across different generation paradigms.