Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery

Abstract

Holography encodes the three dimensional (3D) information of a sample in the form of an intensity-only recording. However, to decode the original sample image from its hologram(s), auto-focusing and phase-recovery are needed, which are in general cumbersome and time-consuming to digitally perform. Here we demonstrate a convolutional neural network (CNN) based approach that simultaneously performs auto-focusing and phase-recovery to significantly extend the depth-of-field (DOF) in holographic image reconstruction. For this, a CNN is trained by using pairs of randomly de-focused back-propagated holograms and their corresponding in-focus phase-recovered images. After this training phase, the CNN takes a single back-propagated hologram of a 3D sample as input to rapidly achieve phase-recovery and reconstruct an in focus image of the sample over a significantly extended DOF. This deep learning based DOF extension method is non-iterative, and significantly improves the algorithm time-complexity of holographic image reconstruction from O(nm) to O(1), where n refers to the number of individual object points or particles within the sample volume, and m represents the focusing search space within which each object point or particle needs to be individually focused. These results highlight some of the unique opportunities created by data-enabled statistical image reconstruction methods powered by machine learning, and we believe that the presented approach can be broadly applicable to computationally extend the DOF of other imaging modalities.

References in corpus (1)

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

Cited by in corpus (54)

• PhaseStain: Digital staining of label-free quantitative phase microscopy images using deep learning
• On the use of deep learning for phase recovery
• Three-dimensional virtual refocusing of fluorescence microscopy images using deep learning
• Reliable deep-learning-based phase imaging with uncertainty quantification
• Terahertz Pulse Shaping Using Diffractive Surfaces
• Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light
• Misalignment Resilient Diffractive Optical Networks
• Ensemble learning of diffractive optical networks
• Cross-modality deep learning brings bright-field microscopy contrast to holography
• Quantitative Digital Microscopy with Deep Learning
• Deep learning-based super-resolution in coherent imaging systems
• Fourier Imager Network (FIN): A deep neural network for hologram reconstruction with superior external generalization
• Review: Deep Learning in Electron Microscopy
• Self-supervised learning of hologram reconstruction using physics consistency
• Diffractive all-optical computing for quantitative phase imaging
• Machine Learning Holography for 3D Particle Field Imaging
• Holographic image reconstruction with phase recovery and autofocusing using recurrent neural networks
• Single-shot autofocusing of microscopy images using deep learning
• Scale-, shift- and rotation-invariant diffractive optical networks
• Optical Fringe Patterns Filtering Based on Multi-Stage Convolution Neural Network
• Deep learning enables high-throughput analysis of particle-aggregation-based bio-sensors imaged using holography
• High-Resolution Limited-Angle Phase Tomography of Dense Layered Objects Using Deep Neural Networks
• Deep learning-based holographic polarization microscopy
• Multiplane Quantitative Phase Imaging Using a Wavelength-Multiplexed Diffractive Optical Processor
• Displacement-agnostic coherent imaging through scatter with an interpretable deep neural network
• Neural network-based image reconstruction in swept-source optical coherence tomography using undersampled spectral data
• Recurrent neural network-based volumetric fluorescence microscopy
• On the interplay between physical and content priors in deep learning for computational imaging
• Small-brain neural networks rapidly solve inverse problems with vortex Fourier encoders
• Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network
• Physics-driven universal twin-image removal network for digital in-line holographic microscopy
• Multispectral Quantitative Phase Imaging Using a Diffractive Optical Network
• Dynamic imaging and characterization of volatile aerosols in e-cigarette emissions using deep learning-based holographic microscopy
• Optimal Physical Preprocessing for Example-Based Super-Resolution
• eFIN: Enhanced Fourier Imager Network for generalizable autofocusing and pixel super-resolution in holographic imaging
• Few-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network
• Virtual impactor-based label-free bio-aerosol detection using holography and deep learning
• Deep learning-based virtual refocusing of images using an engineered point-spread function
• Single-shot experimental-numerical twin-image removal in lensless digital holographic microscopy
• Low-intensity illumination for lensless digital holographic microscopy with minimized sample interaction
• Neural Network-Based Processing and Reconstruction of Compromised Biophotonic Image Data
• Experimental optimization of lensless digital holographic microscopy with rotating diffuser-based coherent noise reduction
• Toward a Thinking Microscope: Deep Learning in Optical Microscopy and Image Reconstruction
• Characterization of exhaled e-cigarette aerosols in a vape shop using a field-portable holographic on-chip microscope
• Phase retrieval with physics informed zero-shot learning
• EM based Framework for Single-shot Compressive Holography
• Cycle Consistency-based Uncertainty Quantification of Neural Networks in Inverse Imaging Problems
• DaISy: Diffuser-aided Sub-THz Imaging System
• Second Harmonic Imaging Enhanced by Deep Learning Decipher
• Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram
• Spectroscopic localization of atomic sample plane for precise digital holography
• Computer-free, all-optical reconstruction of holograms using diffractive networks
• Diffractive Interconnects: All-Optical Permutation Operation Using Diffractive Networks
• Fast Autofocusing using Tiny Transformer Networks for Digital Holographic Microscopy