Improving the classification accuracy in label-free flow cytometry using event-based vision and simple logistic regression
- Author
- Muhammed Gouda Ahmed Gouda (UGent) , Alessio Lugnan (UGent) , Joni Dambre (UGent) , Gerd van den Branden, Christoph Posch and Peter Bienstman (UGent)
- Organization
- Project
- Abstract
- Event-based cameras are novel bio-inspired vision sensors that do not follow the mechanism of traditional frame-based cameras. In the field of data acquisition, the replacement of CMOS cameras with event-based cameras has proved to enhance the accuracy of machine learning methods in situations where critical lighting conditions and rapid dynamics are paramount. In this paper, we investigate for the first time the use of extreme learning machines on data coming from event-based cameras in the context of flow cytometry. Except for the image sensor, the experimental setup is similar to a setup we used in (Lugnan et al., 2020) where we showed that a simple linear classifier can achieve around 10% error rate on background-subtracted cell frames. Here, we show that the the error rate of this simple imaging flow cytometer could be decreased to less than 2% just by making use of the capabilities of an event camera. Moreover, additional benefits like more sensitivity and efficient memory usage are gained. Finally, we suggest further possible improvements to the experimental setup used to record events from flowing micro-particles allowing for more accurate and stable cellx sorting.
- Keywords
- Cameras, Particle measurements, Atmospheric measurements, Training, Machine learning, Semiconductor device modeling, Photonics, Event-based camera, extreme learning machine, flow cytometry, image classification
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 5.01 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01HR9QBZ8NQJS565YXEQ2EH52A
- MLA
- Gouda, Muhammed Gouda Ahmed, et al. “Improving the Classification Accuracy in Label-Free Flow Cytometry Using Event-Based Vision and Simple Logistic Regression.” IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, vol. 29, no. 2, 2023, doi:10.1109/JSTQE.2023.3244040.
- APA
- Gouda, M. G. A., Lugnan, A., Dambre, J., van den Branden, G., Posch, C., & Bienstman, P. (2023). Improving the classification accuracy in label-free flow cytometry using event-based vision and simple logistic regression. IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, 29(2). https://doi.org/10.1109/JSTQE.2023.3244040
- Chicago author-date
- Gouda, Muhammed Gouda Ahmed, Alessio Lugnan, Joni Dambre, Gerd van den Branden, Christoph Posch, and Peter Bienstman. 2023. “Improving the Classification Accuracy in Label-Free Flow Cytometry Using Event-Based Vision and Simple Logistic Regression.” IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS 29 (2). https://doi.org/10.1109/JSTQE.2023.3244040.
- Chicago author-date (all authors)
- Gouda, Muhammed Gouda Ahmed, Alessio Lugnan, Joni Dambre, Gerd van den Branden, Christoph Posch, and Peter Bienstman. 2023. “Improving the Classification Accuracy in Label-Free Flow Cytometry Using Event-Based Vision and Simple Logistic Regression.” IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS 29 (2). doi:10.1109/JSTQE.2023.3244040.
- Vancouver
- 1.Gouda MGA, Lugnan A, Dambre J, van den Branden G, Posch C, Bienstman P. Improving the classification accuracy in label-free flow cytometry using event-based vision and simple logistic regression. IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS. 2023;29(2).
- IEEE
- [1]M. G. A. Gouda, A. Lugnan, J. Dambre, G. van den Branden, C. Posch, and P. Bienstman, “Improving the classification accuracy in label-free flow cytometry using event-based vision and simple logistic regression,” IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, vol. 29, no. 2, 2023.
@article{01HR9QBZ8NQJS565YXEQ2EH52A,
abstract = {{Event-based cameras are novel bio-inspired vision sensors that do not follow the mechanism of traditional frame-based cameras. In the field of data acquisition, the replacement of CMOS cameras with event-based cameras has proved to enhance the accuracy of machine learning methods in situations where critical lighting conditions and rapid dynamics are paramount. In this paper, we investigate for the first time the use of extreme learning machines on data coming from event-based cameras in the context of flow cytometry. Except for the image sensor, the experimental setup is similar to a setup we used in (Lugnan et al., 2020) where we showed that a simple linear classifier can achieve around 10% error rate on background-subtracted cell frames. Here, we show that the the error rate of this simple imaging flow cytometer could be decreased to less than 2% just by making use of the capabilities of an event camera. Moreover, additional benefits like more sensitivity and efficient memory usage are gained. Finally, we suggest further possible improvements to the experimental setup used to record events from flowing micro-particles allowing for more accurate and stable cellx sorting.}},
articleno = {{7600608}},
author = {{Gouda, Muhammed Gouda Ahmed and Lugnan, Alessio and Dambre, Joni and van den Branden, Gerd and Posch, Christoph and Bienstman, Peter}},
issn = {{1077-260X}},
journal = {{IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS}},
keywords = {{Cameras,Particle measurements,Atmospheric measurements,Training,Machine learning,Semiconductor device modeling,Photonics,Event-based camera,extreme learning machine,flow cytometry,image classification}},
language = {{eng}},
number = {{2}},
pages = {{8}},
title = {{Improving the classification accuracy in label-free flow cytometry using event-based vision and simple logistic regression}},
url = {{http://doi.org/10.1109/JSTQE.2023.3244040}},
volume = {{29}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: