Back to all papers

A Kernel Space-based Multidimensional Sparse Model for Dynamic PET Image Denoising.

April 22, 2026pubmed logopapers

Authors

Kuang X,Li B,Liu Y,Rao F,Ma G,Xie Q,S P Mok G,Liu H,Zhu W

Affiliations (9)

  • Zhejiang Polytechnic University of Mechanical and Electrical Engineering, 528 Binwen Road, Hangzhou, Zhejiang, 310053, China.
  • Hefei Comprehensive National Science Center, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, Anhui, 230088, China.
  • School of Electrical and Optical Engineering, Nanjing University of Science and Technology, No. 200 Xiaolingwei Street, Nanjing, 210094, China.
  • Zhejiang Lab, No. 2880 Wenyi West Road, Hangzhou, 311121, China.
  • University of the Chinese Academy of Sciences Hangzhou Institute for Advanced Study, West Lake District, Hangzhou, Zhejiang, 310024, China.
  • University of Science and Technology of China Department of Electronic Engineering and Information, No. 443, Huangshan Road, Hefei, Anhui Province, Hefei, Anhui, 230026, China.
  • University of Macau, Avenida da Universidade, Taipa, Macau, China, Taipa, 999078, China.
  • Department of Optical Engineering, Zhejiang University, Zheda road 38#, Hangzhou, 310058, China.
  • College of Biomedical Engineering and Instrument Science, Zhejiang University, West Lake District, Hangzhou, 310058, China.

Abstract

Achieving high image quality for temporal frames in dynamic positron emission tomography (PET) is challenging due to the limited statistic especially for the short frames. Recent studies have shown that deep learning (DL) is useful in a wide range of medical image denoising tasks. In this paper, we propose a model-based neural network for dynamic PET image denoising. The inter-frame spatial correlation and intra-frame structural consistency in dynamic PET are used to establish the kernel space-based multidimensional sparse (KMDS) model. We then substitute the inherent forms of the parameter estimation with neural networks to enable adaptive parameters optimization, forming the end-to-end neural KMDS-Net. Extensive experimental results from simulated and real data demonstrate that the neural KMDS-Net exhibits strong denoising performance for dynamic PET, outperforming previous baseline methods. The proposed method may be used to effectively achieve high temporal and spatial resolution for dynamic PET. Our source code is available at https://github.com/Kuangxd/Neural-KMDS-Net/tree/main.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.