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
  • [21] Artifact Reduction for Sparse-View CT Using Deep Learning With Band Patch
    Okamoto, Takayuki
    Ohnishi, Takashi
    Haneishi, Hideaki
    IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES, 2022, 6 (08) : 859 - 873
  • [22] Deep learning based image reconstruction for sparse-view diffuse optical tomography
    Jalalimanesh, Mohammad Hosein
    Ansari, Mohammad Ali
    WAVES IN RANDOM AND COMPLEX MEDIA, 2021,
  • [23] Report on the AAPM deep-learning sparse-view CT grand challenge
    Sidky, Emil Y.
    Pan, Xiaochuan
    MEDICAL PHYSICS, 2022, 49 (08) : 4935 - 4943
  • [24] Neural architecture search with Deep Radon Prior for sparse-view CT image reconstruction
    Fu, Jintao
    Cong, Peng
    Xu, Shuo
    Chang, Jiahao
    Liu, Ximing
    Sun, Yuewen
    MEDICAL PHYSICS, 2025,
  • [25] Learning to Distill Global Representation for Sparse-View CT
    Li, Zilong
    Ma, Chenglong
    Chen, Jie
    Zhang, Junping
    Shan, Hongming
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 21139 - 21150
  • [26] CAIR: Combining integrated attention with iterative optimization learning for sparse-view CT reconstruction
    Cheng, Weiting
    He, Jichun
    Liu, Yi
    Zhang, Haowen
    Wang, Xiang
    Liu, Yuhang
    Zhang, Pengcheng
    Chen, Hao
    Gui, Zhiguo
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 163
  • [27] Sparse-View CT Reconstruction via Generative Adversarial Networks
    Zhao, Zhongwei
    Sun, Yuewen
    Cong, Peng
    2018 IEEE NUCLEAR SCIENCE SYMPOSIUM AND MEDICAL IMAGING CONFERENCE PROCEEDINGS (NSS/MIC), 2018,
  • [28] Tensor Dictionary Learning with an Enhanced Sparsity Constraint for Sparse-View Spectral CT Reconstruction
    Li, Xuru
    Sun, Xueqin
    Zhang, Yanbo
    Pan, Jinxiao
    Chen, Ping
    PHOTONICS, 2022, 9 (01)
  • [29] Dual-domain sparse-view CT reconstruction with Transformers
    Shi, Changrong
    Xiao, Yongshun
    Chen, Zhiqiang
    PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 2022, 101 : 71 - 78
  • [30] Sparse-View Projection Spectral CT Reconstruction via HAMEN
    Qi Junyu
    Shi Zaifeng
    Kong Fanning
    Ge Tianhao
    Zhang Lili
    LASER & OPTOELECTRONICS PROGRESS, 2024, 61 (12)