High-Resolution Limited-Angle Phase Tomography of Dense Layered Objects Using Deep Neural Networks

Abstract

We present a Machine Learning-based method for tomographic reconstruction of dense layered objects, with range of projection angles limited to $\pm$10${}^{\circ }$. Whereas previous approaches to phase tomography generally require two steps, first to retrieve phase projections from intensity projections and then perform tomographic reconstruction on the retrieved phase projections, in our work a physics-informed pre-processor followed by a Deep Neural Network (DNN) conduct the three-dimensional reconstruction directly from the intensity projections. We demonstrate this single-step method experimentally in the visible optical domain on a scaled up integrated circuit phantom. We show that even under conditions of highly attenuated photon fluxes a DNN trained only on synthetic data can be used to successfully reconstruct physical samples disjoint from the synthetic training set. Thus, the need of producing a large number of physical examples for training is ameliorated. The method is generally applicable to tomography with electromagnetic or other types of radiation at all bands.

arXiv comment9 pages, 5 figures, 1 table

References in corpus (16)

• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Deep Learning Microscopy
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Deep speckle correlation: a deep learning approach towards scalable imaging through scattering media
• Learning to see through multimode fibers
• CNN-Based Projected Gradient Descent for Consistent Image Reconstruction
• Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
• Low Photon Count Phase Retrieval Using Deep Learning
• Efficient and accurate inversion of multiple scattering with deep learning
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• Recurrent Generative Adversarial Networks for Proximal Learning and Automated Compressive Image Recovery
• Exploit imaging through opaque wall via deep learning
• Spectral pre-modulation of training examples enhances the spatial resolution of the Phase Extraction Neural Network (PhENN)
• Propagation based phase retrieval of simulated intensity measurements using artificial neural networks
• A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction

Cited by in corpus (16)

• RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
• Diffraction tomography with a deep image prior
• SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors
• A Two-step-training Deep Learning Framework for Real-time Computational Imaging without Physics Priors
• Adaptive 3D descattering with a dynamic synthesis network
• Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning
• Recognizing three-dimensional phase images with deep learning
• Physics-assisted Generative Adversarial Network for X-Ray Tomography
• Robust X-ray Sparse-view Phase Tomography via Hierarchical Synthesis Convolutional Neural Networks
• Attentional Ptycho-Tomography (APT) for three-dimensional nanoscale X-ray imaging with minimal data acquisition and computation time
• Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples
• 3D Computational Cannula Fluorescence Microscopy enabled by Artificial Neural Networks
• Unified treatment of exact and approximate scalar electromagnetic wave scattering
• Inverse scattering for reflection intensity phase microscopy
• Deep-learning-driven Reliable Single-pixel Imaging with Uncertainty Approximation