.png){kind=icon}
.png){kind=icon}
Return
Cell-MICS: Detecting Immune Cells With Label-Free Two-Photon Autofluorescence and Deep Learning
.png){kind=icon}
PRE
AI
K
C
R
L
T
C
W
S
F
H
DOI：10.1002/jbio.70260.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multiphoton imaging has been widely used for deep-tissue imaging. Although its label-free, metabolic contrast is ideal for investigating inflammation, the label-free two-photon induced autofluorescence is often regarded as less specific compared to conventional antibody markers. In this work, we investigate the potential for multiphoton imaging with computational specificity (MICS) by training a convolutional neural network on images of different immune cells. A low-complexity squeezeNet architecture was able to achieve reliable immune cell classification results (0.89 ROC-AUC, 0.95 PR-AUC for binary classification between T cells and neutrophils; 0.689 F1 score, 0.697 precision, 0.748 recall for multi-class classification between six isolated cell types). Perturbation tests confirmed that the model was not confused by the extracellular environment and that 2P-AF from NADH and FAD is equally important for the classification. In the future, deep learning could provide computational specificity for specific immune cells in unstained tissues, with great potential for label-free in vivo endomicroscopy.
Keywords:
autofluorescence
biophotonics
cellular metabolism
deep learning
label-free
multiphoton imaging
Journal
IF:
2.3
Papers:
133
Citations:
6.0K
Organization
Cited Papers