Phase recovery and holographic image reconstruction using deep learning in neural networks

Abstract

Phase recovery from intensity-only measurements forms the heart of coherent imaging techniques and holography. Here we demonstrate that a neural network can learn to perform phase recovery and holographic image reconstruction after appropriate training. This deep learning-based approach provides an entirely new framework to conduct holographic imaging by rapidly eliminating twin-image and self-interference related spatial artifacts. Compared to existing approaches, this neural network based method is significantly faster to compute, and reconstructs improved phase and amplitude images of the objects using only one hologram, i.e., requires less number of measurements in addition to being computationally faster. We validated this method by reconstructing phase and amplitude images of various samples, including blood and Pap smears, and tissue sections. These results are broadly applicable to any phase recovery problem, and highlight that through machine learning challenging problems in imaging science can be overcome, providing new avenues to design powerful computational imaging systems.

References in corpus (7)

• Deep Learning in Neural Networks: An Overview
• Wide-field, high-resolution Fourier ptychographic microscopy
• Deep Learning Microscopy
• A unified evaluation of iterative projection algorithms for phase retrieval
• Solution to the twin image problem in holography
• Quantitative Imaging of Single, Unstained Viruses with Coherent X-rays
• Ultrafast, ultrabright, X-ray holography using a uniformly-redundant array

Cited by in corpus (38)

• Deep Learning Microscopy
• Hyperspectral terahertz microscopy via nonlinear ghost imaging
• Reliable deep-learning-based phase imaging with uncertainty quantification
• Misalignment Resilient Diffractive Optical Networks
• Diffractive all-optical computing for quantitative phase imaging
• Machine Learning Holography for 3D Particle Field Imaging
• Near-field Fourier ptychography: super-resolution phase retrieval via speckle illumination
• Does deep learning always outperform simple linear regression in optical imaging?
• Deep learning-based color holographic microscopy
• On the interplay between physical and content priors in deep learning for computational imaging
• Exascale Deep Learning for Scientific Inverse Problems
• Imaging through glass diffusers using densely connected convolutional networks
• eFIN: Enhanced Fourier Imager Network for generalizable autofocusing and pixel super-resolution in holographic imaging
• Virtual impactor-based label-free bio-aerosol detection using holography and deep learning
• SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network
• Robust X-ray Sparse-view Phase Tomography via Hierarchical Synthesis Convolutional Neural Networks
• Phase Retrieval with Holography and Untrained Priors: Tackling the Challenges of Low-Photon Nanoscale Imaging
• Blind deblurring for microscopic pathology images using deep learning networks
• Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples
• Learning an optimal PSF-pair for ultra-dense 3D localization microscopy
• A New Deep Learning Method for Image Deblurring in Optical Microscopic Systems
• Deep neural networks for efficient phase demodulation in wavelength shifting interferometry
• Inverse scattering for reflection intensity phase microscopy
• Full-Field, Carrier-Less, Polarization-Diversity, Direct Detection Receiver based on Phase Retrieval
• Deep-learning-driven Reliable Single-pixel Imaging with Uncertainty Approximation
• Performance evaluation of an integrated photonic convolutional neural network based on delay buffering and wavelength division multiplexing
• Learning Illumination Patterns for Coded Diffraction Phase Retrieval
• Temporal phase unwrapping using deep learning
• Single-shot structured illumination microscopy
• Computer-free, all-optical reconstruction of holograms using diffractive networks
• Mode-Multiplexed Full-Field Reconstruction Using Direct and Phase Retrieval Detection
• Fast Computational Ghost Imaging using Unpaired Deep Learning and a Constrained Generative Adversarial Network
• Digital phase-only holography using deep conditional generative models
• Machine learning holography for measuring 3D particle size distribution
• Comprehensive deep learning model for optical holography
• Experimental digital Gabor hologram rendering by a model-trained convolutional neural network
• Uncertainty quantification for ptychography using normalizing flows
• Numerical study of laser micro- and nano-processing of nanocomposite porous materials