Back

Deep learning enables rapid and robust analysis of fluorescence lifetime imaging in photon-starved conditions

Yeh, H.-C.; Chen, Y.-I.; Chang, Y.-J.; Liao, S.-C.; Nguyen, T. D.; Yang, J.; Kuo, Y.-A.; Hong, S.; Liu, Y.-L.; Rylander, H. G.; Santacruz, S. R.; Yankeelov, T. E.

2020-12-02 cell biology
10.1101/2020.12.02.408195 bioRxiv
Show abstract

Fluorescence lifetime imaging microscopy (FLIM) is a powerful tool to quantify molecular compositions and study the molecular states in the complex cellular environment as the lifetime readings are not biased by the fluorophore concentration or the excitation power. However, the current methods to generate FLIM images are either computationally intensive or unreliable when the number of photons acquired at each pixel is low. Here we introduce a new deep learning-based method termed flimGANE (fluorescence lifetime imaging based on Generative Adversarial Network Estimation) that can rapidly generate accurate and high-quality FLIM images even in the photon-starved conditions. We demonstrated our model is not only 258 times faster than the most popular time-domain least-square estimation (TD_LSE) method but also provide more accurate analysis in barcode identification, cellular structure visualization, Forster resonance energy transfer characterization, and metabolic state analysis. With its advantages in speed and reliability, flimGANE is particularly useful in fundamental biological research and clinical applications, where ultrafast analysis is critical.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 8%
18.6%
Similar papers in this journal
2
Communications Biology
○ 993 papers in training set
Top 0.1%
12.0%
Similar papers in this journal
3
Light: Science & Applications
○ 16 papers in training set
Top 0.1%
9.7%
Similar papers in this journal
4
Advanced Science
○ 286 papers in training set
Top 0.8%
6.3%
Similar papers in this journal
5
Nature Methods
○ 385 papers in training set
Top 2%
5.5%
Similar papers in this journal
50% of probability mass above
6
Science Advances
● 1243 papers in training set
Top 7%
4.4%
7
ACS Sensors
● 49 papers in training set
Top 0.2%
3.3%
8
Analytical Chemistry
● 218 papers in training set
Top 1.0%
3.2%
9
Cell Reports Methods
○ 165 papers in training set
Top 0.8%
2.7%
10
Angewandte Chemie International Edition
○ 93 papers in training set
Top 0.6%
2.4%
11
Scientific Reports
○ 3612 papers in training set
Top 45%
2.1%
12
ACS Nano
● 113 papers in training set
Top 1%
1.7%
13
eLife
● 5828 papers in training set
Top 50%
1.7%
14
Nature Machine Intelligence
○ 70 papers in training set
Top 1%
1.7%
15
Nano Letters
● 71 papers in training set
Top 0.7%
1.7%
16
Optica
● 27 papers in training set
Top 0.2%
1.5%
17
iScience
○ 1154 papers in training set
Top 26%
1.1%
18
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 34%
1.1%
19
ACS Central Science
● 71 papers in training set
Top 1%
1.1%
20
Journal of the American Chemical Society
● 217 papers in training set
Top 2%
1.1%
21
Patterns
○ 78 papers in training set
Top 3%
0.9%
22
Journal of Cell Biology
● 392 papers in training set
Top 4%
0.9%
23
Biophysical Reports
○ 37 papers in training set
Top 0.4%
0.9%
24
Nature Biotechnology
○ 172 papers in training set
Top 4%
0.9%
25
Chemical Science
● 73 papers in training set
Top 2%
0.6%
26
Bioinformatics
◐ 1204 papers in training set
Top 9%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.