Accelerating intelligent microfluidic image processing with transfer deep learning: A microchannel droplet/bubble breakup case study

Zhang, Shuyuan; Li, Haoran; Wang, Kai; Qiu, Tong

doi:10.1016/j.seppur.2023.123703

Cited by 11 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But how do we take these AI-based techniques into our own lab? − “Bubble” is one of the thousand categories used in ImageNet; however, unfortunately, it refers to soap bubbles instead of gas bubbles dispersed in a liquid, the subject of this paper. In ImageNet there are roughly one million images divided over 1000 categories.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Bubble Segmentation on a Shoestring

Homan,

Deen

2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Image segmentation in bubble plumes is notoriously difficult, with individual bubbles having ill-defined shapes overlapping each other in images. In this paper, we present a cheap and robust segmentation procedure to identify bubbles from bubble swarm images. This is done in three steps. First, individual, nonoverlapping bubbles are detected and isolated from true experimental images. In the second step, these bubble images are combined to generate synthetic ground truth images. In the third and final step, the synthetic images are used as training data for a machine learning script. The trained model can now be used to segment the data of experimental bubble swarms. The segmentation procedure is demonstrated on three different experimental data sets, and general observations are discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning Bubble Segmentation on a Shoestring

Homan,

Deen

2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…Physically, the breaking up of bubbles in microchannels is similar to droplets [ 12 , 13 , 14 , 15 ], suggesting that many results on droplet breakup may also apply to bubbles [ 16 , 17 , 18 ]. In particular, the dominant factors of bubble breakup include the gas/liquid flow rates, channel/bubble dimensions, channel shape/materials, and fluid properties.…”

Section: Introductionmentioning

confidence: 99%

Behind the Non-Uniform Breakup of Bubble Slug in Y-Shaped Microchannel: Dynamics and Mechanisms

Huang,

Liu,

et al. 2024

Micromachines

View full text Add to dashboard Cite

Bubble flow in confined geometries is a problem of fundamental and technological significance. Among all the forms, bubble breakup in bifurcated microchannels is one of the most commonly encountered scenarios, where an in-depth understanding is necessary for better leveraging the process. This study numerically investigates the non-uniform breakup of a bubble slug in Y-shaped microchannels under different flow ratios, Reynolds numbers, and initial bubble volumes. Overall, the bubble can either breakup or non-breakup when passing through the bifurcation and shows different forms depending on flow regimes. The flow ratio-Reynolds number phase diagrams indicate a power–law transition line of breakup and non-breakup. The bubble takes longer to break up with rising flow ratios yet breaks earlier with higher Reynolds numbers and volumes. Non-breakup takes less time than the breakup patterns. Flow ratio is the origin of non-uniform breakup. Both the Reynolds number and initial volume influence the bubble states when reaching the bifurcation and thus affect subsequent processes. Bubble neck dynamics are analyzed to describe the breakup further. The volume distribution after breaking up is found to have a quadratic relation with the flow ratio. Our study is hoped to provide insights for practical applications related to non-uniform bubble breakups.

show abstract

Microfluidic Nanoparticle Separation for Precision Medicine

Lan,

Chen,

Zou

et al. 2024

Advanced Science

View full text Add to dashboard Cite

A deeper understanding of disease heterogeneity highlights the urgent need for precision medicine. Microfluidics, with its unique advantages, such as high adjustability, diverse material selection, low cost, high processing efficiency, and minimal sample requirements, presents an ideal platform for precision medicine applications. As nanoparticles, both of biological origin and for therapeutic purposes, become increasingly important in precision medicine, microfluidic nanoparticle separation proves particularly advantageous for handling valuable samples in personalized medicine. This technology not only enhances detection, diagnosis, monitoring, and treatment accuracy, but also reduces invasiveness in medical procedures. This review summarizes the fundamentals of microfluidic nanoparticle separation techniques for precision medicine, starting with an examination of nanoparticle properties essential for separation and the core principles that guide various microfluidic methods. It then explores passive, active, and hybrid separation techniques, detailing their principles, structures, and applications. Furthermore, the review highlights their contributions to advancements in liquid biopsy and nanomedicine. Finally, it addresses existing challenges and envisions future development spurred by emerging technologies such as advanced materials science, 3D printing, and artificial intelligence. These interdisciplinary collaborations are anticipated to propel the platformization of microfluidic separation techniques, significantly expanding their potential in precision medicine.

show abstract

Accelerating intelligent microfluidic image processing with transfer deep learning: A microchannel droplet/bubble breakup case study

Cited by 11 publications

References 43 publications

Deep Learning Bubble Segmentation on a Shoestring

Deep Learning Bubble Segmentation on a Shoestring

Behind the Non-Uniform Breakup of Bubble Slug in Y-Shaped Microchannel: Dynamics and Mechanisms

Microfluidic Nanoparticle Separation for Precision Medicine

Contact Info

Product

Resources

About