Virtual brightfield and fluorescence staining for Fourier ptychography via unsupervised deep learning

TL;DR

This paper introduces an unsupervised deep learning method to generate high-quality, virtually stained brightfield and fluorescence images from Fourier ptychography microscopy, improving color accuracy and reducing artifacts for digital pathology.

Contribution

It presents a novel cycle-consistent adversarial network that performs unsupervised image translation for FPM, enabling virtual staining without paired training data.

Findings

Effective reduction of coherent artifacts in FPM images

High-quality virtual staining of histology samples

Improved image resolution and color accuracy

Abstract

Fourier ptychographic microscopy (FPM) is a computational approach geared towards creating high-resolution and large field-of-view images without mechanical scanning. To acquire color images of histology slides, it often requires sequential acquisitions with red, green, and blue illuminations. The color reconstructions often suffer from coherent artifacts that are not presented in regular incoherent microscopy images. As a result, it remains a challenge to employ FPM for digital pathology applications, where resolution and color accuracy are of critical importance. Here we report a deep learning approach for performing unsupervised image-to-image translation of FPM reconstructions. A cycle-consistent adversarial network with multiscale structure similarity loss is trained to perform virtual brightfield and fluorescence staining of the recovered FPM images. In the training stage, we feed the network with two sets of unpaired images: 1) monochromatic FPM recovery, and 2) color or fluorescence images captured using a regular microscope. In the inference stage, the network takes the FPM input and outputs a virtually stained image with reduced coherent artifacts and improved image quality. We test the approach on various samples with different staining protocols. High-quality color and fluorescence reconstructions validate its effectiveness.