Missing Cone Artifacts Removal in ODT using Unsupervised Deep Learning in Projection Domain

TL;DR

This paper introduces an unsupervised deep learning method using cycleGAN to effectively remove missing cone artifacts in optical diffraction tomography, improving axial resolution in 3D refractive index reconstructions.

Contribution

The paper presents a novel unsupervised deep learning framework based on cycleGAN to address missing cone artifacts in ODT, without requiring paired training data.

Findings

Significant reduction of missing cone artifacts in ODT reconstructions.

Improved axial resolution in 3D RI distribution.

Effective unsupervised learning approach for artifact removal.

Abstract

Optical diffraction tomography (ODT) produces three dimensional distribution of refractive index (RI) by measuring scattering fields at various angles. Although the distribution of RI index is highly informative, due to the missing cone problem stemming from the limited-angle acquisition of holograms, reconstructions have very poor resolution along axial direction compared to the horizontal imaging plane. To solve this issue, here we present a novel unsupervised deep learning framework, which learns the probability distribution of missing projection views through optimal transport driven cycleGAN. Experimental results show that missing cone artifact in ODT can be significantly resolved by the proposed method.