Abstract
AbstractFlow based deformation cytometry has shown potential for cell classification. We demonstrate the principle with an injection moulded microfluidic chip from which we capture videos of adult and fetal red blood cells, as they are being deformed in a microfluidic chip. Using a deep neural network - SlowFast - that takes the temporal behavior into account, we are able to discriminate between the cells with high accuracy. The accuracy was larger for adult blood cells than for fetal blood cells. However, no significant difference was observed between donors of the two types.
Funder
Strategiske Forskningsråd
Carlsbergfondet
Technical University of Denmark
Publisher
Springer Science and Business Media LLC
Subject
Molecular Biology,Biomedical Engineering
Reference24 articles.
1. D. Bento, R.O. Rodrigues, V. Faustino et al., Deformation of red blood cells, air bubbles, and droplets in microfluidic devices: Flow visualizations and measurements. Micromachines 9(4), 1–18 (2018). https://doi.org/10.3390/mi9040151
2. K. Berg-Sørensen, R. Marie, M.H. Dziegiel et al., Deformation of single cells - optical two-beam traps and more. In: SPIE Photonics West - Complex Light and Optical Forces XIII. SPIE-Intl Soc. Opt. Eng., p 39 (2019). https://doi.org/10.1117/12.2513407
3. R. Eskesen, T. Friis, Hydrodynamic Deformability-based Classification of Fetal and Adult Red Blood Cells Using Deep Learning . MSc Thesis, DTU Compute, Technical University of Denmark (2019)
4. C. Feichtenhofer, H. Fan, J. Malik et al., Slowfast networks for video recognition (2018). https://doi.org/10.48550/ARXIV.1812.03982, https://arxiv.org/abs/1812.03982
5. G. Gopakumar, K. Hari Babu, D. Mishra et al., Cytopathological image analysis using deep-learning networks in microfluidic microscopy. J. Opt. Soc. Am. A 34(1), 111 (2017). https://doi.org/10.1364/josaa.34.000111