Missing Cone Artifact Removal in ODT Using Unsupervised Deep Learning in the Projection Domain

  title={Missing Cone Artifact Removal in ODT Using Unsupervised Deep Learning in the Projection Domain},
  author={Hyungjin Chung and Jaeyoung Huh and Geon Kim and Yong Keun Park and Jong-Chul Ye},
  journal={IEEE Transactions on Computational Imaging},
  • Hyungjin Chung, Jaeyoung Huh, +2 authors Jong-Chul Ye
  • Published 2021
  • Computer Science, Engineering
  • IEEE Transactions on Computational Imaging
Optical diffraction tomography (ODT) produces a three-dimensional distribution of the refractive index (RI) by measuring scattering fields at various angles. Although the distribution of the RI is highly informative, due to the missing cone problem stemming from the limited-angle acquisition of holograms, reconstructions have very poor resolution along the axial direction compared to the horizontal imaging plane. To solve this issue, we present a novel unsupervised deep learning framework that… Expand


DeepRegularizer: Rapid Resolution Enhancement of Tomographic Imaging Using Deep Learning
A deep neural network is proposed and experimentally demonstrated that rapidly improves the resolution of a three-dimensional refractive index map and offers more than an order of magnitude faster regularization performance compared to the conventional iterative method. Expand
Diffraction tomography with a deep image prior.
We present a tomographic imaging technique, termed Deep Prior Diffraction Tomography (DP-DT), to reconstruct the 3D refractive index (RI) of thick biological samples at high resolution from aExpand
Comparative study of iterative reconstruction algorithms for missing cone problems in optical diffraction tomography.
Various existing iterative reconstruction algorithms are systematically compared for mitigating the missing cone problem in optical diffraction tomography and three representative regularization schemes, edge preserving, total variation regularization, and the Gerchberg-Papoulis algorithm were evaluated. Expand
Three-dimensional tomography of red blood cells using deep learning
This work accurately reconstruct three-dimensional (3-D) refractive index (RI) distributions from highly ill-posed two-dimensional measurements using a deep neural network (DNN) and confirms the reconstruction accuracy using the DDA to calculate the 2-D projections of the 3-D reconstructions and compare them to the experimentally recorded projections. Expand
Learning approach to optical tomography
A method for imaging 3D phase objects in a tomographic configuration implemented by training an artificial neural network to reproduce the complex amplitude of the experimentally measured scattered light is described. Expand
3-D Object Reconstruction in Emission and Transmission Tomography with Limited Angular Input
The effects of the angular range of data taking in reconstructions in planar positron cameras using the deconvolution method is investigated. It is found that in the absence of any a prioriExpand
Time-multiplexed structured illumination using a DMD for optical diffraction tomography.
The present method effectively eliminates unwanted diffracted beams from binary DMD patterns, which deteriorates the image quality of the ODT in the previous binary Lee hologram method. Expand
CycleGAN With a Blur Kernel for Deconvolution Microscopy: Optimal Transport Geometry
This article presents a novel unsupervised cycle-consistent generative adversarial network (cycleGAN) with a linear blur kernel, which can be used for both blind- and non-blind image deconvolution and significantly improves the robustness and efficiency of network training. Expand
3D Optical Diffraction Tomography Using Deep Learning
We developed a 3D deep convolutional neural network (3D-DCNN) to perform 3D diffraction optical tomography. We experimentally demonstrate the ability of a 3D-DCNN to reconstruct the 3D index ofExpand
Approximation of missing-cone data in 3D electron microscopy
Abstract The range of tilt angles for which projected images of two-dimensionally periodic specimens can be obtained in electron microscopy is limited both by technical aspects, such as goniometerExpand