相关实验视频

Updated: Jun 1, 2025

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

染色变化和颜色正常化对病理学预后预测的影响

Siyu Lin¹, Haowen Zhou¹, Mark Watson²

¹Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, 91125, USA.

Scientific reports

|January 18, 2025

概括

数字病理学中的深度神经网络 (DNN) 与图像变化作斗争. 在一批幻灯片上训练的DNN无法预测新一批幻灯片中的癌症转移,即使在斑点正常化后,也无法预测癌症转移,这凸显了对一致的图像处理的需求.

科学领域:

数字病理学数字病理学
计算病理学计算病理学
医学中的人工智能.

背景情况:

深度神经网络 (DNN) 在病理学方面表现有前途,可能超过人类专家的准确性.
在组织学幻灯片中染色质量的变化对DNN概括提出了挑战.
污点正常化是一种常见的技术,用于解决数字病理学数据集中的图像变异性.

研究的目的:

评估经过训练的DNN模型在不同批次组织学幻灯片中的概括能力.
评估染色规范化技术在各种数据集上提高DNN性能方面的有效性.
调查染料变异对DNN在非小细胞肺癌 (NSCLC) 转移预测中的预测准确度的影响.

主要方法:

使用了先前开发的DNN来预测NSCLC转移.
该DNN被训练和测试在两个不同的批次的H&E染色组织部分从相同的组织块,在不同的时间处理.
试图使用传统的色调和循环生成对抗网络 (CycleGAN) 进行污点正常化.

主要成果:

该DNN模型未能对新一批幻灯片进行概括,与同一批表现 (AUC = 0.74-0.81) 相比,呈现出差的跨批预测性能 (AUC = 0.52-0.53).
包括CycleGAN在内的污点规范化方法并没有显著改善DNN的跨批量泛化.
幻灯片批次之间的染料变化被确定为限制DNN模型可重现性的关键因素.

结论:

标准的染色规范化技术不足以克服由组织学幻灯片处理的时间变化引起的概括差距.
这项研究强调了在获得和处理一致的显微镜图像方面,对于在病理学中可靠的DNN应用而言,急需新的方法.
开发强大的图像采集和标准化协议对于在数字病理学中广泛采用预测性DNN算法的临床应用至关重要.

更多相关视频

Optimized Staining and Proliferation Modeling Methods for Cell Division Monitoring using Cell Tracking Dyes

Optimized Staining and Proliferation Modeling Methods for Cell Division Monitoring using Cell Tracking Dyes

Published on: December 13, 2012

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Published on: September 22, 2013

相关概念视频

Fixation and Sectioning

Fixation and Sectioning

Two basic types of preparation are used to visualize specimens with a light microscope: wet mounts and fixed specimens.
The simplest type of preparation is the wet mount, in which the specimen is placed in a drop of liquid on the slide. A liquid specimen can be directly deposited on the slide using a dropper. Solid specimens, such as skin scraping, can be placed on the slide before adding a drop of liquid to prepare the wet mount. Sometimes the liquid is simply water, but stains are often added...