Virtual staining of label-free tissue using deep learning
Virtual staining of label-free tissue using deep learning
复制标题
使用深度学习对无标记组织进行虚拟染色
DOI：
10.1117/12.2670987
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Ozcan, Aydogan
中科院分区：
文献类型：
--
作者：
Ozcan, Aydogan
在本演讲中，我将概述我们最近在使用深度神经网络推进计算显微镜和传感系统方面的工作，并涵盖其生物医学应用。具体来说，我将讨论通过使用训练的深度神经网络数字化生成组织学染色剂来彻底改变组织染色方法的新兴机会[1-11]，为标准化学组织染色方法提供快速，具有成本效益，准确和环保的替代方案。这些基于深度学习的虚拟染色技术可以成功地从未染色样本的无标记显微图像中生成不同类型的组织学染色剂，[1，11]包括免疫组织化学染色剂[7]，例如使用自体荧光显微镜，[1]定量相位成像（QPI）[2]和反射共聚焦显微镜[10]。我们的团队还展示了类似的方法，用于将已染色的组织样本的图像转换为另一种类型的染色剂，执行虚拟染色剂到染色剂的转换[5，6，11]。
In this presentation, I will provide an overview of our recent work on using deep neural networks in advancing computational microscopy and sensing systems, also covering their biomedical applications. Specifically, I will discuss emerging opportunities to revolutionize tissue staining methods by digitally generating histological stains using trained deep neural networks [1-11], providing rapid, cost-effective, accurate and environmentally friendly alternatives to standard chemical tissue staining methods. These deep learning-based virtual staining techniques can successfully generate different types of histological stains,[1, 11] including immunohistochemical stains,[7] from label-free microscopic images of unstained samples by using, eg, autofluorescence microscopy,[1] quantitative phase imaging (QPI)[2] and reflectance confocal microscopy [10]. Our team also demonstrated similar approaches for transforming images of an already stained tissue sample into another type of stain, performing virtual stain-to-stain transformations [5, 6, 11].