AI based analysis of red blood cells in oscillating microchannels

The flow dynamics of red blood cells in vivo in blood capillaries and in vitro in microfluidic channels is rather complex. Cells can obtain differnet shapes such as discoid, parachute, slipper-like shapes and various intermediate states depending on flow conditions and their viscoelastic properties. We use artificial based analysis of shapes in an oscillating mircorchannel to categorize red blood cells (RBCs). Two population are prepared and tested for comparison. Healthy red blood cells and red blood cells treated with diamid to chemically modify their viscoelastic behavior. Based on image analysis and tensor flow decision making we group them into two categories and validate the algorithm on a separate samples achieving a 90% confidence. This methode is a first step to a non-invasive, lable free characterization of diseased red blood cells and will be useful for diagnostic purposes in haematology labs. The methode give quatitative data on the number of affected cells on a single cell level.