Spectral2Spectral: Image-spectral Similarity Assisted Spectral CT Deep Reconstruction without Reference
This addresses the challenge of acquiring noise-free reference images for spectral CT in biomedical applications, offering an incremental improvement over existing methods.
The paper tackles the problem of low signal-noise ratio in spectral CT reconstruction due to limited photons in narrow energy bins, proposing an unsupervised deep learning method called Spectral2Spectral that integrates image-spectral similarity priors, and demonstrates it achieves better image quality than state-of-the-art methods on three preclinical datasets.
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.