Classification of Human White Blood Cells Using Machine Learning for Stain-Free Imaging Flow Cytometry
Classification of Human White Blood Cells Using Machine Learning for Stain-Free Imaging Flow Cytometry
复制标题
DOI：
10.1002/cyto.a.23920
复制
发表时间：
2019-11-05
期刊：
影响因子：
3.7
通讯作者：
Peralta, Daniel
中科院分区：
文献类型：
--
作者：
Lippeveld, Maxim;Knill, Carly;Peralta, Daniel
成像流式细胞术（IFC）可产生多达12个光谱清晰、信息丰富的单细胞图像，通量为每秒5，000个细胞。然而，通常仍使用手动门控来研究细胞群体，手动门控是一种具有若干缺点的技术，因此用自动化过程代替手动门控将是有利的。理想情况下，这种自动化过程将基于无染色测量，因为目前使用的染色技术是昂贵的，并可能混淆。这些无污染测量源自明场和暗场图像通道，分别捕获透射光和散射光。为了实现这种自动化、无污染的方法，需要先进的机器学习（ML）方法。以前的工作已经成功地测试了这种方法在细胞周期阶段分类上的应用，包括基于手动工程特征的经典ML方法和深度学习（DL）方法。在这项工作中，我们比较了这两种方法广泛的问题上的白色血细胞分类。在ImageStream-X MK II成像流式细胞仪上测定4份人全血样品。对两个样本进行染色以鉴定八种白色血细胞类型，而对另外两个样本组进行染色以鉴定静息和活性嗜酸性粒细胞。对于这两个数据集，四个ML分类器进行了评估，无染色图像分层5倍交叉验证。在白色血细胞数据集上，经典ML和DL的最佳平衡准确度分别为0.778和0.703。在嗜酸性粒细胞数据集上，这是0.871和0.856平衡准确度。我们的结论是，分类细胞类型的基础上，只有染色免费的图像是可能的，所有四个分类。值得注意的是，我们还发现，在这项工作中测试的DL方法不优于基于手动设计的功能的方法。(c)2019年国际细胞计数促进学会
Imaging flow cytometry (IFC) produces up to 12 spectrally distinct, information-rich images of single cells at a throughput of 5,000 cells per second. Yet often, cell populations are still studied using manual gating, a technique that has several drawbacks, hence it would be advantageous to replace manual gating with an automated process. Ideally, this automated process would be based on stain-free measurements, as the currently used staining techniques are expensive and potentially confounding. These stain-free measurements originate from the brightfield and darkfield image channels, which capture transmitted and scattered light, respectively. To realize this automated, stain-free approach, advanced machine learning (ML) methods are required. Previous works have successfully tested this approach on cell cycle phase classification with both a classical ML approach based on manually engineered features, and a deep learning (DL) approach. In this work, we compare both approaches extensively on the problem of white blood cell classification. Four human whole blood samples were assayed on an ImageStream-X MK II imaging flow cytometer. Two samples were stained for the identification of eight white blood cell types, while two other sample sets were stained for the identification of resting and active eosinophils. For both data sets, four ML classifiers were evaluated on stain-free imagery with stratified 5-fold cross-validation. On the white blood cell data set, the best obtained results were 0.778 and 0.703 balanced accuracy for classical ML and DL, respectively. On the eosinophil data set, this was 0.871 and 0.856 balanced accuracy. We conclude that classifying cell types based on only stain-free images is possible with all four classifiers. Noteworthy, we also find that the DL approaches tested in this work do not outperform the approaches based on manually engineered features. (c) 2019 International Society for Advancement of Cytometry