3D side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysis
Compared with conventional fluorescence biomarker labeling, the classification of cell types based on their stain-free morphological characteristics enables the discovery of a new biological insight and simplifies the traditional cell analysis workflow. Most artificial intelligence aided image-based...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2020-12-01
|
Series: | APL Photonics |
Online Access: | http://dx.doi.org/10.1063/5.0024151 |
id |
doaj-2c9f2fbe03cd4c429a8007fe19d57733 |
---|---|
record_format |
Article |
spelling |
doaj-2c9f2fbe03cd4c429a8007fe19d577332021-01-05T15:00:10ZengAIP Publishing LLCAPL Photonics2378-09672020-12-01512126105126105-910.1063/5.00241513D side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysisRui Tang0Zunming Zhang1Xinyu Chen2Lauren Waller3Alex Ce Zhang4Jiajie Chen5Yuanyuan Han6Cheolhong An7Sung Hwan Cho8Yu-Hwa Lo9Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, California 92093, USADepartment of Electrical and Computer Engineering, University of California, San Diego, La Jolla, California 92093, USADepartment of Electrical and Computer Engineering, University of California, San Diego, La Jolla, California 92093, USADepartment of Bioengineering, University of California, San Diego, La Jolla, California 92093, USADepartment of Electrical and Computer Engineering, University of California, San Diego, La Jolla, California 92093, USACollege of Physics and Optoelectronics Engineering, Shenzhen University, Shenzhen 518060, ChinaDepartment of Electrical and Computer Engineering, University of California, San Diego, La Jolla, California 92093, USADepartment of Electrical and Computer Engineering, University of California, San Diego, La Jolla, California 92093, USANanoCellect Biomedical Inc., San Diego, California 92121, USADepartment of Electrical and Computer Engineering, University of California, San Diego, La Jolla, California 92093, USACompared with conventional fluorescence biomarker labeling, the classification of cell types based on their stain-free morphological characteristics enables the discovery of a new biological insight and simplifies the traditional cell analysis workflow. Most artificial intelligence aided image-based cell analysis methods primarily use transmitted bright-field images or holographic images. Here, we present the first study of the convolutional neural network (CNN) analysis on three-dimensional (3D) side-scattering cell images out of a unique 3D imaging flow cytometer study. Human cancer cell lines and leukocyte classifications were performed to investigate the information carried by the spatial distribution of side-scattering imaging of single cells. We achieved a balanced accuracy of 98.8% for cancer cell line classification and 92.3% for leukocyte classification. The results demonstrate that the side-scattering signals can not only produce general information about cell granularity following the common belief but also carry rich information about the properties and functions of cells, which can be uncovered by the availability of a side-scattering imaging flow cytometer and the application of CNN. Thereby, we have opened up a new avenue for cell phenotype analysis in biomedical and clinical research.http://dx.doi.org/10.1063/5.0024151 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rui Tang Zunming Zhang Xinyu Chen Lauren Waller Alex Ce Zhang Jiajie Chen Yuanyuan Han Cheolhong An Sung Hwan Cho Yu-Hwa Lo |
spellingShingle |
Rui Tang Zunming Zhang Xinyu Chen Lauren Waller Alex Ce Zhang Jiajie Chen Yuanyuan Han Cheolhong An Sung Hwan Cho Yu-Hwa Lo 3D side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysis APL Photonics |
author_facet |
Rui Tang Zunming Zhang Xinyu Chen Lauren Waller Alex Ce Zhang Jiajie Chen Yuanyuan Han Cheolhong An Sung Hwan Cho Yu-Hwa Lo |
author_sort |
Rui Tang |
title |
3D side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysis |
title_short |
3D side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysis |
title_full |
3D side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysis |
title_fullStr |
3D side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysis |
title_full_unstemmed |
3D side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysis |
title_sort |
3d side-scattering imaging flow cytometer and convolutional neural network for label-free cell analysis |
publisher |
AIP Publishing LLC |
series |
APL Photonics |
issn |
2378-0967 |
publishDate |
2020-12-01 |
description |
Compared with conventional fluorescence biomarker labeling, the classification of cell types based on their stain-free morphological characteristics enables the discovery of a new biological insight and simplifies the traditional cell analysis workflow. Most artificial intelligence aided image-based cell analysis methods primarily use transmitted bright-field images or holographic images. Here, we present the first study of the convolutional neural network (CNN) analysis on three-dimensional (3D) side-scattering cell images out of a unique 3D imaging flow cytometer study. Human cancer cell lines and leukocyte classifications were performed to investigate the information carried by the spatial distribution of side-scattering imaging of single cells. We achieved a balanced accuracy of 98.8% for cancer cell line classification and 92.3% for leukocyte classification. The results demonstrate that the side-scattering signals can not only produce general information about cell granularity following the common belief but also carry rich information about the properties and functions of cells, which can be uncovered by the availability of a side-scattering imaging flow cytometer and the application of CNN. Thereby, we have opened up a new avenue for cell phenotype analysis in biomedical and clinical research. |
url |
http://dx.doi.org/10.1063/5.0024151 |
work_keys_str_mv |
AT ruitang 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT zunmingzhang 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT xinyuchen 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT laurenwaller 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT alexcezhang 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT jiajiechen 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT yuanyuanhan 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT cheolhongan 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT sunghwancho 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis AT yuhwalo 3dsidescatteringimagingflowcytometerandconvolutionalneuralnetworkforlabelfreecellanalysis |
_version_ |
1724348063205556224 |