A multienergy computed tomography method without image segmentation or prior knowledge of X-ray spectra or materials.

Many methods have been proposed for multienergy computed tomography (CT) imaging based on traditional CT systems. Usually, either prior knowledge of the X-ray spectra distribution or materials or the segmentation of the projection or reconstructed image is needed. To avoid these requirements, a multienergy CT method is proposed in this paper. A CT image can be seen as a linear combination of energy-dependent components and spatially dependent components. The latter components are the base images, while the former components are the coefficients. A blind decomposition model is constructed to decompose the multivoltage projections to obtain the base images and the energies. Multienergy CT images are computationally synthesized with the base images and the energies. Multivoltage projections can be acquired based on one scan with stepped voltages. X-ray scattering is considered an important factor in imaging errors and appears as a low-frequency signal. The variance is used to describe the low-frequency features and is minimized as the optimized objective function of the decomposition model. The solution of the model uses Karush-Kuhn-Tucker (KKT) conditions. In the experiments, the images reconstructed with the proposed method exhibit weak beam-hardening artifacts. Additionally, the X-ray energies of the different materials represented have small relative errors. Therefore, the reconstructed images have narrow energy intervals. This shows the effectiveness of the proposed method.