DeLTA 2.0: A deep learning pipeline for quantifying single-cell spatial and temporal dynamics
Problem
Analyzing time-lapse microscopy images of single cells is a major bottleneck because existing segmentation and tracking tools require human input, are setup-specific, or lack accuracy.
Why it matters
Manual image analysis slows quantitative biology research that now generates huge imaging datasets.
What the AI did
Deep convolutional neural networks automatically extract single-cell information (gene expression, growth) from time-lapse images with no human input after training, extending to 2D growth environments.
Results
not stated in source
Impact
The peer-reviewed DeLTA 2.0 pipeline automates single-cell analysis that previously needed human input.
Record
| Venue | PLoS Computational Biology |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Owen M. O’Connor, Razan N. Alnahhas, Jean‐Baptiste Lugagne, Mary J. Dunlop |
| Citations | 103 (OpenAlex, at import time) |
| References | 42 |
| Model or method | deep convolutional neural networks |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1371/journal.pcbi.1009797 |
| Open access | gold |
| Keywords | deep learning, cell segmentation, time-lapse microscopy, single-cell analysis, Python pipeline |
Importance rating
real but narrower advance
Automating a stated major bottleneck in single-cell microscopy analysis; benefits quantitative biology research, no scale quantified.