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. © 2019 International Society for Advancement of Cytometry

Imaging flow cytometry (IFC) produces up to 12 different information-rich images of single cells at a throughput of 5000 cells per second. Yet often, cell populations are still studied using manual gating, a technique that has several drawbacks. Firstly, it is hard to reproduce. Secondly, it is subjective and biased. And thirdly, it is time-consuming for large experiments. Therefore, it would be advantageous to replace manual gating with an automated process, which could be based on stain-free measurements originating from the brightfield and darkfield image channels.To realise this potential, advanced data analysis methods are required, in particular, machine learning. Previous works have successfully tested this approach on cell cycle phase classification with both a classical machine learning approach based on manually engineered features, and a deep learning approach. In this work, we compare both approaches extensively on the complex 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 8 white blood cell types, while two other sample sets were stained for the identification of resting and active eosinophils. For both datasets, four machine learning classifiers were evaluated on stain-free imagery using stratified 5-fold cross-validation. On the white blood cell dataset the best obtained results were 0.776 and 0.697 balanced accuracy for classical machine learning and deep learning, respectively. On the eosinophil dataset this was 0.866 and 0.867 balanced accuracy. From the experiments we conclude that classifying distinct cell types based on only stain-free images is possible with these techniques. However, both approaches did not always succeed in making reliable cell subtype classifications. Also, depending on the cell type, we find that even though the deep learning approach requires less expert input, it performs on par with a classical approach.