Deep Learning Cell Imaging through Anderson Localizing Optical Fibre

TL;DR

This paper presents a deep learning-based system for real-time, artifact-free imaging of cells through a meter-long Anderson localizing optical fibre, capable of handling bending, heating, and distant imaging without distal optics.

Contribution

It introduces a neural network approach that enables high-fidelity cell imaging through flexible and heated optical fibres, with robustness to unseen cell types and configurations.

Findings

Successful real-time cell imaging through long, bent fibres

High fidelity reconstruction of cells several millimeters from fibre end

Neural network generalizes to unseen cell morphologies

Abstract

We demonstrate a deep-learning-based fibre imaging system which can transfer real-time artifact-free cell images through a meter-long Anderson localizing optical fibre. The cell samples are illuminated by an incoherent LED light source. A deep convolutional neural network is applied to the image reconstruction process. The network training uses data generated by a set-up with straight fibre at room temperature (~20 {\deg}C) but can be utilized directly for high fidelity reconstruction of cell images that are transported through fibre with a few degrees bend and/or fibre with segments heated up to 50 {\deg}C. In addition, cell images located several millimeters away from the bare fibre end can be transported and recovered successfully without the assistance of any distal optics. We further evidence that the trained neural network is able to reconstruct the images of cells which are never used in the training process and feature very different morphology.