Sparse phase retrieval using a physics-informed neural network for Fourier ptychographic microscopy.

Journal: Optics letters
Published Date:

Abstract

In this paper, we report a sparse phase retrieval framework for Fourier ptychographic microscopy using the recently proposed principle of physics-informed neural networks. The phase retrieval problem is cast as training bidirectional mappings from the measured image space with random noise and the object space to be reconstructed, in which the image formation physics and convolutional neural network are integrated. Meanwhile, we slightly modify the mean absolute error loss function considering the signal characteristics. Two datasets are used to validate this framework. The results indicate that the proposed framework is able to reconstruct sparsely sampled data using a small aperture overlapping rate without additional data driving whereas conventional methods cannot.

Authors

  • Zhonghua Zhang
  • Tian Wang
    Department of Computer Science and Engineering, Huaqiao University, Xiamen, China.
  • Shaowei Feng
  • Yongxin Yang
    Beijing Ekitech Co. Ltd., Beijing 100043, China; University of Edinburgh, 10 Crichton Street, Edinburgh, EH8 9AB, United Kindom.
  • Chunhong Lai
  • Xinwei Li
    Biomedical Engineering Research Center, The Chongqing University of Posts and Telecommunications, Chongqing 400065, P.R.China.
  • Lizhi Shao
    CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Computer Science and Engineering, Southeast University, Nanjing, China.
  • Xiaoming Jiang
    Institute of Language Sciences, Shanghai International Studies University, Shanghai, 201620, China. xiaoming.jiang@shisu.edu.cn.