An Alternative Bayesian Reconstruction of Sparse-view CT by Optimizing Deep Learning Parameters

被引:0
|
作者
Chen, Changyu [1 ,2 ]
Chen, Zhiqiang [1 ,2 ]
Zhang, Li [1 ,2 ]
Xing, Yuxiang [1 ,2 ]
机构
[1] Tsinghua Univ, Dept Engn Phys, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Minist Educ, Key Lab Particle & Radiat Imaging, Beijing 100084, Peoples R China
来源
MEDICAL IMAGING 2024: PHYSICS OF MEDICAL IMAGING, PT 1 | 2024年 / 12925卷
基金
中国国家自然科学基金;
关键词
Computed Tomography; Ill-posed Problem; Bayesian Reconstruction; Deep Learning; Domain Adaptation; NETWORK;
D O I
10.1117/12.3008509
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sparse-view computed tomography (CT) has great potential in reducing radiation dose and accelerating the scan process. Although deep learning (DL) methods have exhibited promising results in mitigating streaking artifacts caused by very few projections, their generalization remains a challenge. In this work, we proposed a DL-driven alternative Bayesian reconstruction method that efficiently integrates data-driven priors and the data consistency constraints. This methodology involves two stages: universal embedding and consistency adaptation respectively. In the embedding stage, we optimize DL parameters to learn and eliminate the general sparse-view artifacts on a large-scale paired dataset. In the subsequent consistency adaptation stage, an alternative Bayesian reconstruction further optimizes the DL parameters according to individual projection data. Our proposed technique is validated within both image-domain and dual-domain DL frameworks leveraging simulated sparse-view (90 views) projections. The results underscore the superior generalization and context structure recovery of our approach compared to networks solely trained via supervised loss.
引用
收藏
页数:4
相关论文
共 50 条
  • [31] Generative Modeling in Sinogram Domain for Sparse-View CT Reconstruction
    Guan, Bing
    Yang, Cailian
    Zhang, Liu
    Niu, Shanzhou
    Zhang, Minghui
    Wang, Yuhao
    Wu, Weiwen
    Liu, Qiegen
    IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES, 2024, 8 (02) : 195 - 207
  • [32] VVBPNet: Deep learning model in view-by-view backprojection (VVBP) domain for sparse-view CBCT reconstruction
    Zhao, Xuzhi
    Du, Yi
    Peng, Yahui
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2025, 102
  • [33] Dual-Domain Reconstruction Network for Sparse-View CT
    Zhang, Yi
    Chen, Hu
    Xia, Wenjun
    Chen, Yang
    Liu, Baodong
    Liu, Yan
    Sun, Huaiqiang
    Zhou, Jiliu
    DEVELOPMENTS IN X-RAY TOMOGRAPHY XIII, 2021, 11840
  • [34] Sinogram interpolation for sparse-view micro-CT with deep learning neural network
    Dong, Xu
    Vekhande, Swapnil
    Cao, Guohua
    MEDICAL IMAGING 2019: PHYSICS OF MEDICAL IMAGING, 2019, 10948
  • [35] Linear diffusion noise boosted deep image prior for unsupervised sparse-view CT reconstruction
    Wu, Jia
    Jiang, Xiaoming
    Zhong, Lisha
    Zheng, Wei
    Li, Xinwei
    Lin, Jinzhao
    Li, Zhangyong
    PHYSICS IN MEDICINE AND BIOLOGY, 2024, 69 (16):
  • [36] Dual-domain sparse-view CT reconstruction with Transformers
    Shi, Changrong
    Xiao, Yongshun
    Chen, Zhiqiang
    PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 2022, 101 : 1 - 7
  • [37] A cascaded deep-learning reconstruction method for sparse-view kV-switching dual-energy CT
    Zhang, Ruoqiao
    Zhou, Jian
    Yu, Zhou
    MEDICAL IMAGING 2020: PHYSICS OF MEDICAL IMAGING, 2020, 11312
  • [38] Sparse-view and limited-angle CT reconstruction with untrained networks and deep image prior
    Shu, Ziyu
    Entezari, Alireza
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2022, 226
  • [39] A Transformer-Based Iterative Reconstruction Model for Sparse-View CT Reconstruction
    Xia, Wenjun
    Yang, Ziyuan
    Zhou, Qizheng
    Lu, Zexin
    Wang, Zhongxian
    Zhang, Yi
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT VI, 2022, 13436 : 790 - 800
  • [40] Combining convolutional sparse coding with total variation for sparse-view CT reconstruction
    Li, Xuru
    Li, Yu
    Chen, Ping
    Li, Fuzhong
    APPLIED OPTICS, 2022, 61 (06) : C116 - C124