Abstract
Photon-counting computed tomography (PCCT) has emerged as a transformative imaging modality, enabling enhanced spatial resolution, and multi-energy acquisition with energy-discriminating detectors of significantly smaller detector elements. However, both energy discriminating power and reduced detector pixel size result in fewer detected photons per measurement, inherently increasing noise in reconstructed images. In this study, we propose ZS4D, a zero-shot self-similarity-steered denoiser for PCCT reconstruction. Specifically, a self-similarity denoiser is pre-trained in a self-supervised manner by leveraging spectral correlations through multi-energy extraction and capturing volumetric context via the complementary synergy of axial and sagittal planes. The pre-trained denoiser is then integrated as a prior into an iterative reconstruction framework, enabling effective noise suppression and structural preservation. Extensive experiments demonstrate that ZS4D adapts well to varying noise levels and significantly enhances image quality in both simulated and pre-clinical PCCT datasets. Also, ZS4D demonstrates effectiveness in deblurring tasks. Furthermore, our denoiser pretrained on clinical PCCT data is shown to enhance the spatial resolution of conventional CT images.