Determining the Concentration of Red Blood Cells using Dielectric Properties
- Resource Type
- Conference
- Authors
- Camilleri, Jeantide Said; Farrugia, Lourdes; Bonello, Julian; Pace, Nikolai P.; Santorelli, Adam; Porter, Emily; O'Halloran, Martin; Sammut, Charles V.
- Source
- 2020 14th European Conference on Antennas and Propagation (EuCAP) Antennas and Propagation (EuCAP), 2020 14th European Conference on. :1-5 Mar, 2020
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Photonics and Electrooptics
Signal Processing and Analysis
White blood cells
Plasma properties
Red blood cells
Permittivity measurement
Artificial neural networks
Predictive models
Dielectric measurement
Dielectric measurements
biological material
human blood
red blood cells
artificial neural networks
- Language
This paper investigates an innovative method to determine the red and white blood cell concentrations in blood using their dielectric properties at microwave frequencies. The dielectric properties characterise the interaction of a time-varying electric field with the biological tissue. The concentrations of red blood cells (RBCs) and white blood cells in a sample of whole blood can vary due to illness or disease. This study is a proof-of-concept, where the dielectric properties of samples containing RBCs and plasma are investigated. The dielectric properties of samples of different concentration of RBCs in plasma are measured and used to train artificial neural networks which relate the measured properties to the known concentrations of RBCs. The results show that a trained neural network can predict the RBC concentrations in arbitrary samples not used to train the model with an average error of 1.37 % with respect to the actual concentration in the samples.