Deep learning-based virtual histology staining using auto-fluorescence of label-free tissue

TL;DR

This paper introduces a deep learning approach that transforms auto-fluorescence images of unlabeled tissue into virtually-stained images, eliminating the need for traditional staining and streamlining histological analysis.

Contribution

It presents a novel deep learning model that generates virtual histological stains from label-free auto-fluorescence images, reducing time and cost in tissue preparation.

Findings

Successfully generated virtually-stained images of various human tissues.

Validated the method across multiple tissue types and stains.

Eliminated the need for physical staining procedures.

Abstract

Histological analysis of tissue samples is one of the most widely used methods for disease diagnosis. After taking a sample from a patient, it goes through a lengthy and laborious preparation, which stains the tissue to visualize different histological features under a microscope. Here, we demonstrate a label-free approach to create a virtually-stained microscopic image using a single wide-field auto-fluorescence image of an unlabeled tissue sample, bypassing the standard histochemical staining process, saving time and cost. This method is based on deep learning, and uses a convolutional neural network trained using a generative adversarial network model to transform an auto-fluorescence image of an unlabeled tissue section into an image that is equivalent to the bright-field image of the stained-version of the same sample. We validated this method by successfully creating virtually-stained microscopic images of human tissue samples, including sections of salivary gland, thyroid, kidney, liver and lung tissue, also covering three different stains. This label-free virtual-staining method eliminates cumbersome and costly histochemical staining procedures, and would significantly simplify tissue preparation in pathology and histology fields.