Projects per year
Abstract
An outstanding challenge for immunology is the classification of immune cells in a label-free fashion with high speed. For this purpose, optical techniques such as Raman spectroscopy or digital holographic microscopy have been used successfully to identify immune cell subsets. To achieve high accuracy, these techniques require a post-processing step using linear methods of multivariate processing, such as principal component analysis. Here we demonstrate for the first time a comparison between artificial neural networks and principal component analysis (PCA) to classify the key granulocyte cell lineages of neutrophils and eosinophils using both digital holographic microscopy and Raman spectroscopy. Artificial neural networks can offer advantages in terms of classification accuracy and speed over a PCA approach. We conclude that digital holographic microscopy with convolutional neural networks based analysis provides a route to a robust, stand-alone and high-throughput hemogram with a classification accuracy of 91.3 % at a throughput rate of greater than 100 cells per second.
Original language | English |
---|---|
Pages (from-to) | 13706-13720 |
Number of pages | 15 |
Journal | Optics Express |
Volume | 27 |
Issue number | 10 |
Early online date | 29 Apr 2019 |
DOIs | |
Publication status | Published - 13 May 2019 |
Keywords
- Deep learning
- Machine Learning
- Artificial Neural Networks
- Raman Spectroscopy
- Digital holographic microscopy
- immunology
Fingerprint
Dive into the research topics of 'Label-free optical hemogram of granulocytes enhanced by artificial neural networks'. Together they form a unique fingerprint.Projects
- 2 Finished
-
M Squared - USTAN Biophotonics Nexus: M Sqaured - St Andrews Biophotonics Nexus
Dholakia, K. (PI)
1/11/17 → 31/10/22
Project: Standard
-
Resonant and shaped photonics for under: Resonant and shaped photonics for understanding the physical and biomedical world
Dholakia, K. (PI) & Gather, M. C. (CoI)
1/08/17 → 31/07/22
Project: Standard
Datasets
-
Data underpinning: A label-free optical hemogram of granulocytes enhanced by artificial neural networks
Gupta, R. (Creator), Chen, M. (Creator), Malcolm, G. P. A. (Creator), Hempler, N. (Creator), Dholakia, K. (Creator) & Powis, S. J. (Creator), University of St Andrews, 30 Apr 2019
DOI: 10.17630/c3b0856b-3400-4211-9e7c-eacfc7082067
Dataset
File