2021
DOI: 10.3390/cells10102587
|View full text |Cite
|
Sign up to set email alerts
|

Machine Learning Assisted Classification of Cell Lines and Cell States on Quantitative Phase Images

Abstract: In this report, we present implementation and validation of machine-learning classifiers for distinguishing between cell types (HeLa, A549, 3T3 cell lines) and states (live, necrosis, apoptosis) based on the analysis of optical parameters derived from cell phase images. Validation of the developed classifier shows the accuracy for distinguishing between the three cell types of about 93% and between different cell states of the same cell line of about 89%. In the field test of the developed algorithm, we demons… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
10
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 24 publications
(10 citation statements)
references
References 60 publications
0
10
0
Order By: Relevance
“…Moreover, investigated RAW 264.7 macrophages ( Figure 2 a), although causing high contrast in DHM QPI images, grew with tight cell-cell contacts in clusters, which hindered a reliable threshold-based image evaluation for single-cell data. Here, sophisticated algorithms that, e.g., rely on convolutional neural networks (CNNs) [ 57 ] prospect improved biophysical parameter extraction, suitable for subsequent advanced analysis with machine learning approaches [ 58 , 59 ]. This can be used for the detection of subpopulations or phenotypes.…”
Section: Discussionmentioning
confidence: 99%
“…Moreover, investigated RAW 264.7 macrophages ( Figure 2 a), although causing high contrast in DHM QPI images, grew with tight cell-cell contacts in clusters, which hindered a reliable threshold-based image evaluation for single-cell data. Here, sophisticated algorithms that, e.g., rely on convolutional neural networks (CNNs) [ 57 ] prospect improved biophysical parameter extraction, suitable for subsequent advanced analysis with machine learning approaches [ 58 , 59 ]. This can be used for the detection of subpopulations or phenotypes.…”
Section: Discussionmentioning
confidence: 99%
“…Digital holography (DH) in microscopy is a label-free computational imaging technique able to provide a posteriori multiple refocusing capability and quantitative phase-contrast imaging. [1][2][3] Thanks to these features, DH has been successfully employed in a variety of biomedicine applications, 4 including cancer cell identification and characterization, [5][6][7] diagnostics of blood diseases, [8][9][10][11] inflammations 12 and infectious diseases, [13][14][15] study of cell motility and migration, 16 and marker-free detection of lipid droplets (LDs). 17 The possibility to probe biological samples from different directions leads to the full 3D label-free imaging achieved by holographic tomography technology, 18,19 which represents the leading edge of biological inspection at the single-cell level.…”
Section: Introductionmentioning
confidence: 99%
“…As already mentioned in the discussion of the results in Figure 4 , cells that were activated pro- or anti-inflammatory presumably leaded an increased heterogeneity of biophysical cell parameters. Here, analysis of the data available by QPI with sophisticated evaluation concepts, e.g., based on machine learning algorithms that allow considering of multiple parameters [ 35 , 76 , 81 , 82 ], promises further insights into our data sets and into the identification of additional cell subfractions.…”
Section: Discussionmentioning
confidence: 99%