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

TLDR

Histological analysis is essential for disease diagnosis but requires laborious sample preparation and staining. The study aims to develop a label‑free method that generates virtually stained microscopic images from a single auto‑fluorescence image of unlabeled tissue. This is achieved with a convolutional neural network trained as a generative adversarial network to map auto‑fluorescence images to bright‑field images equivalent to stained samples. The approach successfully produced virtually stained images of human salivary gland, thyroid, kidney, liver, and lung tissues across three stains, eliminating the need for costly histochemical staining and simplifying pathology workflows.

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.