Droplet menisci recognition by deep learning for digital microfluidics applications

Abstract

This paper demonstrates the use of deep learning, specifically the U-Net model, to recognize the menisci of droplets in an electrowetting-on-dielectric (EWOD) digital microfluidic (DMF) device. Accurate recognition of droplet menisci would enable precise control over the movement of droplets to improve the performance and reliability of an EWOD DMF system. Furthermore, important information such as fluid properties, droplet characteristics, spatial position, dynamic behavior, and reaction kinetics of droplets during DMF manipulation can be understood by recognizing the menisci. Through a convolutional neural network utilizing the U-Net architecture, precise identification of droplet menisci is achieved. A diverse dataset is prepared and used to train and test the model. As a showcase, details of training and the optimization of hyperparameters are described. Experimental validation demonstrated that the trained model achieves a 98% accuracy rate and a 0.92 Dice score, which confirms the model’s high performance. After the successful recognition of droplet menisci, postprocessing techniques are applied to extract essential information such as the droplet and bubble size and volume. This study shows that the trained U-Net model is capable of discerning droplet menisci even in the presence of background image interference and low-quality images. The model can detect not only simple droplets, but also compound droplets of two immiscible liquids, droplets containing gas bubbles, and multiple droplets of varying sizes. Finally, the model is shown to detect satellite droplets as small as 2% of the size of the primary droplet, which are byproducts of droplet splitting.

References

[1] Choi K, Ng AH, Fobel R, Wheeler AR. Digital microfluidics. Annu Rev Anal Chem. 2012;5:413-440.

[2] Kaler KV, Prakash R. Droplet microfluidics for chip-based diagnostics. Sensors. 2014;14:23283-23306.

[3] Cho SK, Moon H, Kim CJ. Creating, transporting, cutting, and merging liquid droplets by electrowetting-based actuation for digital microfluidic circuits. J Microelectromech Syst. 2003;12:70-80.

[4] Wang H, Chen L, Sun L. Digital microfluidics: a promising technique for biochemical applications. Front Mech Eng. 2017;12:510-525.

[5] Shen HH, Fan SK, Kim CJ, Yao DJ. EWOD microfluidic systems for biomedical applications. Microfluid Nanofluid. 2014;16:965-987.

[6] Cao J, An Q, Liu Z, et al. Electrowetting on the liquid-infused membrane for flexible and reliable digital droplet manipulation and application. Sens Actuators B. 2019;291:470-477.

[7] Ren H, Fair RB. Micro/nanoliter droplet formation and dispensing by capacitance metering and electrowetting actuation. Proceedings of the 2nd IEEE Conference on Nanotechnology, Washington, DC, USA, 2002:369-372.

[8] Gong J, Kim C-J. All-electronic droplet generation on-chip with real-time feedback control for EWOD digital microfluidics. Lab Chip. 2008;8:898-906.

[9] Jain V, Hole A, Deshmukh R, Patrikar R. Dynamic capacitive sensing of droplet parameters in a low-cost open EWOD system. Sens Actuators A. 2017;263:224-233.

[10] Shin YJ, Lee JB. Machine vision for digital microfluidics. Rev Sci Instrum. 2010;81:014302.

[11] Sotiropoulou CL, Voudouris L, Gentsos C, Demiris AM, Vassiliadis N, Nikolaidis S. Real-time machine vision FPGA implementation for microfluidic monitoring on lab-on-chips. IEEE Trans Biomed Circuits Syst. 2013;8:268-277.

[12] Vo PQ, Husser MC, Ahmadi F, Sinha H, Shih SC. Image-based feedback and analysis system for digital microfluidics. Lab Chip. 2017;17:3437-3446.

[13] Luo Z, Huang B, Xu J, et al. Machine vision-based driving and feedback scheme for digital microfluidics system. Open Chemistry. 2021;19:665-677.

[14] Torabinia M, Farzbod A, Moon H. Electromechanical model to predict the movability of liquids in an electrowetting-on-dielectric microfluidic device. J Appl Phys. 2018;123:154902.

[15] Paul S, Moon H. Separation of binary solution by liquid-liquid microextraction on EWOD digital microfluidics. IEEE 12th International Conference on Nano/Micro Engineered and Molecular Systems (NEMS), Los Angeles, CA, USA, 2017:342-345.

[16] Nahar MM, Moon H, Wijethunga P. Study of compound droplet dynamics and separation of immiscible liquids on EWOD DMF. IEEE 12th International Conference on Nano/Micro Engineered and Molecular Systems (NEMS), Los Angeles, CA, USA, 2017:694-697.

[17] Wijethunga PA, Nanayakkara YS, Kunchala P, Armstrong DW, Moon H. On-chip drop-to-drop liquid microextraction coupled with real-time concentration monitoring technique. Anal Chem. 2011;83:1658-1664.

[18] Paul S, Moon H. Drop-to-drop liquid-liquid extraction of DNA in electrowetting-on-dielectric digital microfluidics. Biomicrofluidics. 2021;15:034110.

[19] Torabinia M, Dakarapu US, Asgari P, Jeon J, Moon H. Electrowetting-on-dielectric (EWOD) digital microfluidic device for in-line workup in organic reactions: a critical step in the drug discovery work cycle. Sens Actuators B. 2021;330:129252.

[20] Nahar MM, Moon H. Phase separation of multiphase droplets in a digital microfluidic device. Micro Nano Syst Lett. 2019;7:19.

[21] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015:18th International Conference, Munich, Germany, 2015:234-241.

[22] Farzbod A, Moon H. Integration of reconfigurable potentiometric electrochemical sensors into a digital microfluidic platform. Biosens Bioelectron. 2018;106:37-42.

[23] Moon H, Torabinia M, inventors; University of Texas System, assignee. On-chip organic synthesis enabled by engine-and-cargo in an electrowetting-on-dielectric digital microfluidic device. United States Patent 11, 779, 927.2023.

[24] Paul S, Moon H. Drop-to-drop liquid-liquid extraction of DNA in electrowetting-on-dielectric digital microfluidics. Biomicrofluidics. 2021;15:034110.

[25] Nahar MM, Nikapitiya JB, You SM, Moon H. Droplet velocity in an electrowetting on dielectric digital microfluidic device. Micromachines. 2016;7:71.

[26] Torabinia M, Dakarapu US, Asgari P, Jeon J, Moon H. Electrowetting-on-dielectric (EWOD) digital microfluidic device for in-line workup in organic reactions: a critical step in the drug discovery work cycle. Sens Actuators B. 2021;330:129252.

[27] Schmitz A, Bansho Y, Noda K, Iwata H, Ogata T, Sugano S. Tactile object recognition using deep learning and dropout. IEEE-RAS International Conference on Humanoid Robots, Madrid, Spain, 2014:1044-1050.

RIGHTS & PERMISSIONS

2025 2025 The Author(s). Droplet published by Jilin University and John Wiley & Sons Australia, Ltd.