Spectral2Spectral: Image-spectral Similarity Assisted Spectral CT Deep Reconstruction without Reference

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 re...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-11
Main Authors: Guo, Xiaodong, Li, Longhui, Chang, Dingyue, He, Peng, Peng, Feng, Yu, Hengyong, Wu, Weiwen
Format: Article
Language:English
Subjects:
Biomedical materials
Computed tomography
Image quality
Image reconstruction
Iterative methods
Medical imaging
Neural networks
Photons
Regularization
Signal to noise ratio
Similarity
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422