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.

© 2022 Optica Publishing Group

Physics-informed deep neural network reconstruction framework for propagation-based x ray phase-contrast computed tomography with sparse-view projections

Fangzhi Li, Yuqing Zhao, Shuo Han, Dongjiang Ji, Yimin Li, Mengting Zheng, Wenjuan Lv, Jianbo Jian, Xinyan Zhao, and Chunhong Hu
Opt. Lett. 47(16) 4259-4262 (2022)

Improving the resolution of Fourier ptychographic imaging using an a priori neural network

Junting Sha, Wenmao Qiu, Guannan He, Zhi Luo, and Bo Huang
Opt. Lett. 48(23) 6316-6319 (2023)

Fourier ptychographic microscopy with untrained deep neural network priors

Quan Chen, Duolan Huang, and Rui Chen
Opt. Express 30(22) 39597-39612 (2022)

Phase retrieval with physics informed zero-shot network

Sanjeev Kumar
Opt. Lett. 46(23) 5942-5945 (2021)

Fourier ptychography multi-parameter neural network with composite physical priori optimization

Delong Yang, Shaohui Zhang, Chuanjian Zheng, Guocheng Zhou, Lei Cao, Yao Hu, and Qun Hao
Biomed. Opt. Express 13(5) 2739-2753 (2022)