Spectral computed tomography based on a photon-counting detector (PCD) attracts more and more attentions since it has the capability to provide more accurate identification and quantitative analysis for biomedical materials. The limited number of photons within narrow energy bins leads to imaging results of low signal-noise ratio. The existing supervised deep reconstruction networks for CT reconstruction are difficult to address these challenges because it is usually impossible to acquire noise-free clinical images with clear structures as references. In this paper, we propose an iterative deep reconstruction network to synergize unsupervised method and data priors into a unified framework, named as Spectral2Spectral. Our Spectral2Spectral employs an unsupervised deep training strategy to obtain high-quality images from noisy data in an end-to-end fashion. The structural similarity prior within image-spectral domain is refined as a regularization term to further constrain the network training. The weights of neural network are automatically updated to capture image features and structures within the iterative process. Three large-scale preclinical datasets experiments demonstrate that the Spectral2spectral reconstructs better image quality than other the state-of-the-art methods.
For bench-top X-ray fluorescence computed tomography (XFCT), the X-ray tube source will bring extreme Compton background noise, resulting in a low signal-to-noise ratio and low contrast detection limit. In this paper, a noise2noise denoising algorithm based on the UNet deep learning network is proposed. The network can use noise image learning to convert the noise image into a clean image. Two sets of phantoms (high concentration Gd phantom and low concentration Bi phantom) are used for scanning to simulate the imaging process under different noise levels and generate the required data set. Additionally, the data set is generated by Geant4 simulation. In the training process, the L1 loss function is used for its good convergence. The image quality is evaluated according to CNR and pixel profile, which shows that our algorithm is better than BM3D, both visually and quantitatively.