Work

Robust image reconstruction with real-world noise modeling for low-dose photon-counting detector CT

Year: 2025

Type: article

Abstract: • Robust Noise Modeling. With explicit noise modeling in the image domain, our presented method demonstrates superior generalization capability across diverse PCD-CT imaging scenarios. This principled statistical approach provides inherent robustness to real-world noise variations, enabling reliable performance under different acquisition conditions. • Flexible Reconstruction Scheme. The reconstruction scheme synergistically combines our novel noise-based regularization with conventional 3DTV constraints, while maintaining the flexibility to incorporate additional image-based regularizations. This modular architecture allows for task-specific optimization without compromising the method’s theoretical foundations. • Improved Real-World Denoising Performance. Comprehensive validation on both phantom and real-world datasets demonstrated the presented method in terms of denoising efficacy and material decomposition accuracy compared to state-of-the-art methods. Model-based image reconstruction methods with regularization terms have been developed to suppress noise in the photon-counting detector CT (PCD-CT) images. Meanwhile, most regularization terms are usually designed based on the image characteristics, but do not account for the real-world noise distribution within the images, which may produce undesired biases in the reconstruction results. In this work, we analyze the noise characteristics of PCD-CT images, i.e., material dependent, spatial location dependent, and energy dependent characteristics, and present a N oise C haracterized M odel-based I terative R econstruction (NCM-IR) method for high-fidelity PCD-CT imaging. Specifically, a three-dimensional total variation (3DTV) is utilized to describe the texture characteristics in the PCD-CT images. Then, the characteristics of noise are modeled in an explicit form with a universal approximator, i.e., Gaussian mixture model (GMM). Moreover, both the GMM and 3DTV are introduced into the presented NCM-IR method. Finally, in the presented NCM-IR, we optimize the parameters of the noise distribution and 3DTV with respect to the reconstruction accuracy by using a designed Expectation Maximization algorithm. The presented NCM-IR method is extensively evaluated in numerical and preclinical studies and we demonstrate the presented NCM-IR method with characterized noise distribution outperforms the competing methods that either utilize only characterized noise distribution or lack it entirely in terms of noise reduction, structure preservation, and material decomposition accuracy. A Search-Based File Recommendation Approach for Infrastructure-as-Code Evolution

Source: Pattern Recognition

DOI: 10.1016/j.patcog.2025.112942