Label-free optical hemogram of granulocytes enhanced by artificial neural networks

作     者：Gupta, Roopam K. Chen, Mingzhou Malcolm, Graeme P. A. Hempler, Nils Dholakia, Kishan Powis, Simon J. 

作者机构：Univ St Andrews Sch Med Biomed Sci Res Complex St Andrews KY16 9TF Fife Scotland Univ St Andrews Sch Phys & Astron SUPA St Andrews KY16 9SS Fife Scotland M Squared Lasers 1 Kelvin CampusWest Scotland Sci Pk Glasgow G20 0SP Lanark Scotland 

出 版 物：《OPTICS EXPRESS》 (光学快报)

年 卷 期：2019年第27卷第10期

页      面：13706-13720页

核心收录：

学科分类：070207[理学-光学] 07[理学] 08[工学] 0803[工学-光学工程] 0702[理学-物理学] 

基　　金：Medical Research Scotland [PhD 873-2015] UK Engineering and Physical Sciences Research Council [EP/R004854/1, EP/P030017/1] EPSRC [EP/P030017/1] Funding Source: UKRI UUI [EP/R004854/1] Funding Source: UKRI 

主　　题：Forward scattering Holographic microscopy Image processing Neural networks Raman scattering Stochastic gradient descent 

摘      要：An outstanding challenge for immunology is the classification of immune cells in a label-free fashion with high speed. For this purpose, optical techniques such as Raman spectroscopy or digital holographic microscopy have been used successfully to identify immune cell subsets. To achieve high accuracy, these techniques require a post-processing step using linear methods of multivariate processing, such as principal component analysis. Here we demonstrate for the first time a comparison between artificial neural networks and principal component analysis (PCA) to classify the key granulocyte cell lineages of neutrophils and eosinophils using both digital holographic microscopy and Raman spectroscopy. Artificial neural networks can offer advantages in terms of classification accuracy and speed over a PCA approach. We conclude that digital holographic microscopy with convolutional neural networks based analysis provides a route to a robust, stand-alone and high-throughput hemogram with a classification accuracy of 91.3 % at a throughput rate of greater than 100 cells per second. Published by The Optical Society under the terms of the Creative Commons Attributton 4.0 license.