Related Experiment Video
Updated: Nov 5, 2025
14:48
Generation of Dynamical Environmental Conditions using a High-Throughput Microfluidic Device
Published on: April 17, 2021
4.3K
Closed-loop feedback control of microfluidic cell manipulation via deep-learning integrated sensor networks.
Ningquan Wang1, Ruxiu Liu1, Norh Asmare1
1School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA. sarioglu@gatech.edu.
Lab on a Chip
|May 19, 2021
Summary
This study introduces an adaptive microfluidic system using electrical sensors and deep learning for real-time cell tracking. The system maintains consistent cell flow speeds despite disruptions, improving reliability for biomedical tests.
Area of Science:
- Biomedical Engineering
- Microfluidics
- Sensor Technology
Background:
- Microfluidic devices manipulate cells using force fields for characterization.
- Standard microfluidic platforms struggle with specimen variability and external disturbances.
- Optimized conditions in microfluidics often fail to account for real-world complexities.
Purpose of the Study:
- To develop and validate an adaptive microfluidic system for robust cell manipulation.
- To integrate on-chip electrical sensors and closed-loop feedback control for real-time adjustments.
- To enhance the reliability and reduce artifacts in microfluidic cell analysis.
Main Methods:
- An adaptive microfluidic system with distributed electrical sensors was designed.
- Deep learning algorithms interpreted real-time cell flow speed data from sensors.
- A proportional-integral feedback controller modulated a pressure pump to maintain target flow speeds.
Main Results:
- The adaptive system successfully tracked cells and modulated chip parameters in real-time.
- Validation with static and dynamic targets demonstrated system efficacy.
- The system showed rapid convergence and resilience to continuous external perturbations.
Conclusions:
- Adaptive microfluidic systems can sustain optimal processing conditions autonomously.
- This technology reduces susceptibility to artifacts, enhancing data quality.
- The system holds potential for reliable, standardized biomedical tests at the point of care.
