Understanding the intricacies of particle-cell interactions is essential for many applications such as imaging, phototherapy, and drug/gene delivery, because it is the key to accurate control of the particle properties for the improvement of their therapeutic and diagnostic efficiency. Recently, high-throughput methods have emerged for the detailed investigation of these interactions. For example, imaging flow cytometry (IFC) collects up to 60,000 images of cells per second (in 12 optical channels) and provides information about morphology and organelle localization in combination with fluorescence and side scatter intensity data. However, analysis of IFC data is extremely difficult to perform using conventional methods that calculate integral parameters or use mask-based object recognition. Here, we show application of a convolutional neural network (CNN) for precise quantitative analysis of particle targeting of cells using IFC data. CNN provides high-throughput object detection with almost human precision but avoids the subjective choice of image processing parameters that often leads to incorrect data interpretation. The method allows accurate counting of cell-bound particles with reliable discrimination from the nonbound particles in the field of view. The proposed method expands capabilities of spot counting applications (such as organelle counting, quantification of cell-cell and cell-bacteria interactions) and is going to be useful not only for high-throughput analysis of IFC data but also for other imaging techniques. © 2019 International Society for Advancement of Cytometry.
Keywords: HER2/neu; cancer cell targeting; convolutional neural network; faster R-CNN; imaging flow cytometry; object detection; particles; targeted drug delivery.
© 2019 International Society for Advancement of Cytometry.