Boundary-Preserved Deep Denoising of Stochastic Resonance Enhanced Multiphoton Images.

Journal: IEEE journal of translational engineering in health and medicine
PMID:

Abstract

OBJECTIVE: With the rapid growth of high-speed deep-tissue imaging in biomedical research, there is an urgent need to develop a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional denoising filters and models can easily suppress the perturbative noise in high-contrast images; however, for low photon budget multiphoton images, a high detector gain will not only boost the signals but also bring significant background noise. In such a stochastic resonance imaging regime, subthreshold signals may be detectable with the help of noise, meaning that a denoising filter capable of removing noise without sacrificing important cellular features, such as cell boundaries, is desirable.

Authors

  • Sheng-Yong Niu
    Research Center for Information Technology Innovation (CITI)Academia Sinica Taipei 11529 Taiwan.
  • Lun-Zhang Guo
    Department of Biomedical EngineeringNational Taiwan University Taipei 10617 Taiwan.
  • Yue Li
    School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, China.
  • Zhiming Zhang
    Shenzhen Prevention and Treatment Center for Occupational Diseases, Shenzhen 518020, China.
  • Tzung-Dau Wang
    Department of Medicine, National Taiwan University, Taipei 10617, Taiwan. tdwang@ntu.edu.tw.
  • Kai-Chun Liu
  • You-Jin Li
    Research Center for Information Technology Innovation (CITI)Academia Sinica Taipei 11529 Taiwan.
  • Yu Tsao
  • Tzu-Ming Liu
    Institute of Translational Medicine, Faculty of Health Sciences & Ministry of Education Frontiers Science Center for Precision Oncology, University of Macau, Taipa Macau China.