Oral Presentation Australasian Cytometry Society 44th Annual Conference and Workshop

Potential of macrophage classification based on flow cytometry autofluorescence (24559)

Tetiana Hourani 1 , Alexis Perez Gonzalez 1 , Rodney Luwor 1 , Adrian Achuthan 1 , Akram Al-Hourani 2
  1. The University of Melbourne, Carlton, VIC, Australia
  2. School of Engineering, RMIT University, Melbounne, Victoria, Australia

Macrophages are innate immune cells that are very responsive to the surrounding microenvironment which shapes their morphology, metabolism, expressed markers, and functions. While expressed markers are the most used property to describe phenotypes, multiple reports indicate that macrophage morphology and autofluorescence are also valuable characteristics that can be used for identification. In this presentation, we will provide an overview of our recent work on using flow cytometry autofluorescence signature to classify six different macrophage phenotypes. The identification was based on extracted signals from multi-detector flow cytometer with multiple laser wavelengths. To achieve the identification, we applied three machine learning methods to detect phenotype fingerprint based on the response vector, where the fully connected neural network architecture provided the highest classification accuracy. These results indicate the potential of the intrinsic autofluorescence for classifying macrophage phenotypes, with the proposed method being quick, simple, and cost-effective way to accelerate the discovery of macrophage responsiveness to various stimuli.