Recognizing three-dimensional phase images with deep learning

Abstract

Optical phase contains key information for biomedical and astronomical imaging. However, it is often obscured by layers of heterogeneous and scattering media, which render optical phase imaging at different depths an utmost challenge. Limited by the memory effect, current methods for phase imaging in strong scattering media are inapplicable to retrieving phases at different depths. To address this challenge, we developed a speckle three-dimensional reconstruction network (STRN) to recognize phase objects behind scattering media, which circumvents the limitations of memory effect. From the single-shot, reference-free and scanning-free speckle pattern input, STRN distinguishes depth-resolving quantitative phase information with high fidelity. Our results promise broad applications in biomedical tomography and endoscopy.

References in corpus (15)

• A Survey on Deep Learning in Medical Image Analysis
• Machine learning and the physical sciences
• Non-invasive real-time imaging through scattering layers and around corners via speckle correlations
• Image Transmission Through an Opaque Material
• On-Chip Random Spectrometer
• Deep speckle correlation: a deep learning approach towards scalable imaging through scattering media
• Learning to see through multimode fibers
• High-fidelity multimode fibre-based endoscopy for deep-brain in vivo imaging
• DeepSTORM3D: dense three dimensional localization microscopy and point spread function design by deep learning
• Reference-less measurement of the transmission matrix of a highly scattering material using a DMD and phase retrieval techniques
• Characterization of the angular memory effect of scattered light in biological tissues
• Non-invasive focusing and imaging in scattering media with a fluorescence-based transmission matrix
• Exploiting speckle correlations to improve the resolution of wide-field fluorescence microscopy
• High-Resolution Limited-Angle Phase Tomography of Dense Layered Objects Using Deep Neural Networks
• The rotational memory effect of a multimode fiber