SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors

Abstract

Two features desired in a three-dimensional (3D) optical tomographic image reconstruction algorithm are the ability to reduce imaging artifacts and to do fast processing of large data volumes. Traditional iterative inversion algorithms are impractical in this context due to their heavy computational and memory requirements. We propose and experimentally validate a novel scalable iterative mini-batch algorithm (SIMBA) for fast and high-quality optical tomographic imaging. SIMBA enables high-quality imaging by combining two complementary information sources: the physics of the imaging system characterized by its forward model and the imaging prior characterized by a denoising deep neural net. SIMBA easily scales to very large 3D tomographic datasets by processing only a small subset of measurements at each iteration. We establish the theoretical fixed-point convergence of SIMBA under nonexpansive denoisers for convex data-fidelity terms. We validate SIMBA on both simulated and experimentally collected intensity diffraction tomography (IDT) datasets. Our results show that SIMBA can significantly reduce the computational burden of 3D image formation without sacrificing the imaging quality.

In press for IEEE Journal Selected Topics in Signal Processing

References in corpus (21)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Spectral Normalization for Generative Adversarial Networks
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Fast Image Recovery Using Variable Splitting and Constrained Optimization
• A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
• Deep-STORM: super-resolution single-molecule microscopy by deep learning
• Deep speckle correlation: a deep learning approach towards scalable imaging through scattering media
• A Deep Learning Approach to Structured Signal Recovery
• Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation
• Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
• An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
• Efficient and accurate inversion of multiple scattering with deep learning
• High-speed in vitro intensity diffraction tomography
• The Singular Values of Convolutional Layers
• Deep Learning Diffuse Optical Tomography
• High-throughput intensity diffraction tomography with a computational microscope
• Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
• High-Resolution Limited-Angle Phase Tomography of Dense Layered Objects Using Deep Neural Networks
• Regularized Fourier Ptychography using an Online Plug-and-Play Algorithm
• DeepRED: Deep Image Prior Powered by RED

Cited by in corpus (19)

• Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imaging
• Dense Recurrent Neural Networks for Accelerated MRI: History-Cognizant Unrolling of Optimization Algorithms
• Deep learning in biomedical optics
• Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
• Adaptive 3D descattering with a dynamic synthesis network
• High-fidelity intensity diffraction tomography with a non-paraxial multiple-scattering model
• The Practicality of Stochastic Optimization in Imaging Inverse Problems
• SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
• Large-scale holographic particle 3D imaging with the beam propagation model
• CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
• Fourier synthesis optical diffraction tomography for kilohertz rate volumetric imaging
• Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples
• Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors
• Learning an optimal PSF-pair for ultra-dense 3D localization microscopy
• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
• Joint Reconstruction and Calibration using Regularization by Denoising
• Inversion of Integral Models: a Neural Network Approach
• A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods
• Stability Bounds for the Unfolded Forward-Backward Algorithm