Physics-driven universal twin-image removal network for digital in-line holographic microscopy

TL;DR

This paper introduces UTIRnet, a physics-based deep learning model that effectively removes twin-image noise in digital in-line holographic microscopy, improving image quality and enabling broader application without extensive experimental data.

Contribution

The paper presents a universal, physics-driven deep learning network trained solely on simulated data for twin-image removal in DIHM, with open-source code for easy adoption.

Findings

UTIRnet achieves fast and robust twin-image suppression.

The method maintains consistency with input holograms, ensuring reliable reconstructions.

Experimental tests on neural cell migration demonstrate practical effectiveness.

Abstract

Digital in-line holographic microscopy (DIHM) enables efficient and cost-effective computational quantitative phase imaging with a large field of view, making it valuable for studying cell motility, migration, and bio-microfluidics. However, the quality of DIHM reconstructions is compromised by twin-image noise, posing a significant challenge. Conventional methods for mitigating this noise involve complex hardware setups or time-consuming algorithms with often limited effectiveness. In this work, we propose UTIRnet, a deep learning solution for fast, robust, and universally applicable twin-image suppression, trained exclusively on numerically generated datasets. The availability of open-source UTIRnet codes facilitates its implementation in various DIHM systems without the need for extensive experimental training data. Notably, our network ensures the consistency of reconstruction results with input holograms, imparting a physics-based foundation and enhancing reliability compared to conventional deep learning approaches. Experimental verification was conducted among others on live neural glial cell culture migration sensing, which is crucial for neurodegenerative disease research.