SCOUT: Fast Spectral CT Imaging in Ultra LOw-data Regimes via PseUdo-label GeneraTion

TL;DR

This paper introduces SCOUT, a fast, self-supervised spectral CT reconstruction method that effectively handles ultra-low data regimes without external data or lengthy training, achieving high-quality results and artifact reduction.

Contribution

SCOUT presents a novel self-supervised approach leveraging pseudo-label generation for ultra-low-data spectral CT reconstruction, eliminating the need for external data or pre-training.

Findings

Mitigates detector-induced ring artifacts

Achieves high-fidelity detail recovery

Operates efficiently in ultra-low-data regimes

Abstract

Noise and artifacts during computed tomography (CT) scans are a fundamental challenge affecting disease diagnosis. However, current methods either involve excessively long reconstruction times or rely on data-driven models for optimization, failing to adequately consider the valuable information inherent in the data itself, especially medical 3D data. This work proposes a reconstruction method under ultra-low raw data conditions, requiring no external data and avoiding lengthy pre-training processes. By leveraging spatial nonlocal similarity and the conjugate properties of the projection domain to generate pseudo-3D data for self-supervised training, high-fidelity results can be achieved in a very short time. Extensive experiments demonstrate that this method not only mitigates detector-induced ring artifacts but also exhibits unprecedented capabilities in detail recovery. This method provides a new paradigm for research using unlabeled raw projection data. Code is available at https://github.com/yqx7150/SCOUT.