Search
Close this search box.

Deep learning and microfluidics: a review

Published on February 24th 2021

Introduction to deep learning techniques for microfluidics

Deep learning

The unique features of microfluidics-based devices brought tremendous advancements in many different applications, including experimental biology and biomedical research. 

Nevertheless, the full potential of this technology has not yet been reached. The high amount of data generated by the high-throughput systems needs to be analyzed as efficiently as it is generated. 

In this context, machine learning, a class of artificial intelligence (AI)-based methods, has already been applied to process data in biotechnological applications such as disease detection in liquid biopsies [2], single-cell lipid screening [3], cancer screening [4, 5], cell counting and prediction of water-in-oil emulsion sizes [6]. More recently, deep learning showed the ability to analyze structured data such as images or sequences. 
 
 
A first example is label-free cell classification, in which architectures identify cells starting from pre-defined features [7] or raw images as inputs exploiting the deep network’s ability to extract relevant features for improved prediction [8-10]. This review will discuss more straightforward and complex deep learning architectures to analyze different data sets.

Deep learning architectures for biological analysis

Label-free cell classification can be achieved with the most straightforward architecture: unstructured data-to-unstructured data. For example, the unstructured input could be a vector of cell traits (circularity, perimeter, and primary axis length), and the axis would be a cell type/class. 
 
 
An example is the positioning and orientation of C. elegans in a microfluidic chip by the Hang Lu group at the Georgia Institute of Technology to image synaptic punctum patterns in the organism [12]. Another exciting application is described in the excellent review by Vasilevich et al. [13].
1-Fluorescence-micrographs_Deep-Learning_Microfluidics_innovation center
Fig. 1: Fluorescence micrographs of synaptic sites in C. elegans immobilized in microfluidic chip. (Image taken from San-Miguel, A. et al. Nature Commun. 2016 [12]).

Other deep learning neural networks can handle sequential data, for example, data generated by microfluidic devices. These networks are called recurrent neural networks (RNNs). They can be further divided based on their output: sequence-to-unstructured data architectures produce a single production after receiving a sequential input. 

 

A sequence is a vector where the order of elements is essential (e.g., a sequence or image), whereas, for unstructured data, the ordering of components is unnecessary (e.g., a vector of cell traits – width, length, etc.). In the case of sequence-to-unstructured architectures, the training is achieved by a technique known as back-propagation through time [11]. This can be applied, for example, to characterize a microfluidic soft sensor and address its limitations, such as its nonlinearity and hysteresis in response [14].

 

Das et al. applied deep learning in the calibration stage to estimate a contact pressure’s magnitude and location simultaneously [14]. They fabricated two sensors to acquire data; one had a single straight microchannel with three different cross-sectional areas in three segments, and the other had a single-sized microchannel with three patterns in different locations. 

 

The experiments were carried out by compressing the top surface with different speeds and pressures in more places of the sensor. The RNN algorithm, composed of modular networks, can model the nonlinear characteristic with a hysteresis of the pressure response and find the pressure’s location.

2 Soft pressure sensors Deep Learning
Fig. 2: Different designs and cross-section of soft pressure sensors. (Image taken from Han, S. et al. Autom. Letter. 2018 [14]).

On the other hand, sequence-to-sequence neural networks offer sequence data as an output. DNA base calling is an example: the MinION nanopore sequencing platform is a high-throughput DNA sequencer that allows analyzing the data in real time as they are produced [15].

 

Applications that benefit from this type of neural network are those where accuracy can be increased by considering previous measurements, like the growth of a cell via volume [1] or mass [16]. For example, every pulse amplitude corresponds to the passage of a cell; this means that each element of the input sequence is annotated.

 

Images can be analyzed using deep learning networks with spatially distributed data. This further improves cell classification and could be done directly without requiring prior manual trait extraction. Neural networks used to process images are called convolutional neural networks (CNNs). 

 

The element used to analyze the image is the convolutional block, which can be described as a filter that slides along the image, outputs the weighted sum of pixel values for that filter within the region of the image processed, and applies a nonlinear transformation. 

These convolutional layers extract the most dominant values in the feature maps [19]. One example is using a deep-learning CNN to classify a binary population of lymphocytes and red blood cells at high throughput [8].

 

Image-to-image neural networks are used in many applications, but segmenting images is one growing area of interest due to the possibility of generating thoroughly segmented images starting from cell contours. 

For example, the nerve cell segmentation application aims to map each pixel in the input image to one of many classes in the corpus [21]. Nerve cell images are segmented into regions marking axon (blue), myelin (red), and background (black) [20].

3 Image analysis Deep Learning
Fig. 3: Example of image and corresponding output labels: axon (in blue in the figure), myelin (red), and background (black). (Image taken from Zaimi, A. et al. Scientific reports. 2018 [20]).

Video processing and deep learning

These different approaches can be used together to analyze videos; for example, Buggenthin and colleagues used a combination of RNN and CNN to identify hematopoietic lineage; in fact, they could predict the differentiation of cells before they expressed conventional molecular markers. 

The first step concerns extracting features from bright-field images by applying a CNN; the RNN then processes these data to track information in time by considering previous frames.

Organ-on-a-chip (OOC) and AI-autonomous living systems with deep-learning networks

Deep learning algorithms could significantly impact more complex systems like Organ-on-chip. OOC are 3D microfluidic devices that can reproduce tissues or entire organs and study their activity and environment. 

 

As OOC devices continue to evolve, a high number of data will be fed to deep learning networks from images and videos of tissues and organs development in their in vitro environments; moreover, large portions of tissue and organs could be analyzed to detect spatial heterogeneity like modern histopathology analysis [26]. 

 

CNNs have been used to organize and classify histomorphological information [27] and could also be used to analyze fluorescence microscopic images of tissue cultures on chips.

4-Automated image classification Deep Learning
Fig. 4: Automated tiling and classification of 1024×1024-pixel image patches using a trained CNN, global overview of lesion localization can be observed in brown. (Image taken from Faust, K. et al. BMC Bioinformatics. 2018 [27]).

Deep learning for experimental design and control

Deep learning networks could be implemented in the emerging field of multiorgan systems to monitor individual organs, assess their communication, and provide real-time control of multiple OOC systems; very interestingly, this could also lead to a multiorgan system that can regulate itself [28].

 

Deep learning could be an excellent resource for studying complex environments that require parallelization and control of multiple factors. The company Zymerg developed a network that controls thousands of parallel microwell-based microbial cultures, where the algorithm handles the microfluidic decisions, such as what and when to inject. 
 
 
An example of experiment planning and post-experiment analysis with deep learning networks is the study of Nguyen and colleagues. Different factors, such as temperature, light, food supply, and various pollutants, could be evaluated for microalgal growth [29].
MPS_Deep-Learning
Fig. 5: Microphysiological systems platforms and their flow partitioning. (Image taken from Nguyen, B. et al. Advanced science. 2018 [29]).

Cloud-based deep learning

Microfluidic point-of-care diagnostics, food safety, production of antibodies, therapeutics, vaccines, and supply chains could benefit from integrating deep learning networks. By feeding the network with globally distributed data generated, for example, by paper-based assays, deep learning algorithms could track, predict, and ultimately contain outbreaks [30].

Conclusions

This short review presents different biotechnological applications that could integrate deep learning networks. In particular, the combination of microfluidics and deep learning algorithms holds excellent potential for analyzing more and more data generated by highly parallelized systems, which could accelerate research in powerful ways. Finally, integrating this technology in laboratories presents relatively low challenges and costs.

Review done thanks to the support of the NeuroTrans 

H2020-MSCA-ITN-2019-Action “Innovative Training Networks”, Grant agreement number: 860954

Author: Francesca Romana Brugnoli, PhD 

Contact: Partnership[at]microfluidic.fr

Francesca_Brugnoli
eu_funded_en
logo-actions-marie-curie_0-300x223
References
  1. Riordon, J. et al. (2014) Quantifying the volume of single cells continuously using a microfluidic pressure-driven trap with media exchange. Biomicrofluidics 8, 011101
  2. Ko, J. et al. (2018) Machine learning to detect signatures of disease in liquid biopsies – a user’s guide. Lab Chip 18, 395–405
  3. Guo, B. et al. (2017) High-throughput, label-free, single-cell, microalgal lipid screening by machine-learning-equipped optofluidic time-stretch quantitative phase microscopy. Cytometry A 91, 494–502
  4. Ko, J. et al. (2017) Combining machine learning and nanofluidic technology to diagnose pancreatic cancer using exosomes. ACS Nano 11, 11182–11193
  5. Singh, D.K. et al. (2017) Label-free, high-throughput holographic screening and enumeration of tumor cells in blood. Lab Chip 17, 2920–2932
  6. Mahdi, Y. and Daoud, K. (2017) Microdroplet size prediction in microfluidic systems via artificial neural network modeling for water-in-oil emulsion formulation. J. Dispers. Sci. Technol. 38, 1501–1508
  7. Chen, C.L. et al. (2016) Deep learning in label-free cell classification. Sci. Rep. 6, 21471
  8. Heo, Y.J. et al. (2017) Real-time image processing for microscopy-based label-free imaging flow cytometry in a microfluidic chip. Sci. Rep. 7, 21471
  9. Van Valen, D.A. et al. (2016) Deep learning automates the quantitative analysis of individual cells in live-cell imaging experiments. PLoS Comput. Biol. 12, e1005177
  10. Gopakumar, G. et al. (2017) Cytopathological image analysis using deep-learning networks in microfluidic microscopy. J. Opt. Soc. Am. A Opt. Image Sci. Vis. 34, 111
  11. Das, D.K. et al. (2013) Machine learning approach for automated screening of malaria parasite using light microscopic images. Micron 45, 97–106
  12. San-Miguel, A. et al. (2016) Deep phenotyping unveils hidden traits and genetic relations in subtle mutants. Nat. Commun. 7, 12990
  13. Vasilevich, A.S. et al. (2017) How not to drown in data: a guide for biomaterial engineers. Trends Biotechnol. 35, 743–755
  14. Han, S. et al. (2018) Use of deep learning for characterization of microfluidic soft sensors. IEEE Robot. Autom. Lett. 3, 873–880
  15. Boža, V. et al. (2017) DeepNano: deep recurrent neural networks for base calling in MinION nanopore reads. PLoS One 12, e0178751
  16. Godin, M. et al. (2010) Using buoyant mass to measure the growth of single cells. Nat. Methods 7, 387–390
  17. Jozefowicz, R. et al. (2016) Exploring the limits of language modeling. arXiv
  18. Qu, Y.-H. et al. (2017) On the prediction of DNA-binding proteins only from primary sequences: a deep learning approach. PLoS One 12, e0188129
  19. LeCun, Y. and Bengio, Y. (1995) Convolutional networks for images, speech, and time series. Handb. Brain Theory Neural Netw. 3361, 1995
  20. Zaimi, A. et al. (2018) AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks. Sci. Rep. 8, 3816
  21. Long, J. et al. (2015) Fully convolutional networks for semantic segmentation. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440, IEEE
  22. Lin, G. et al. (2016) Efficient piecewise training of deep structured models for semantic segmentation. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3194–3203, IEEE
  23. Chen, L.-C. et al. (2016) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv
  24. Buggenthin, F. et al. (2017) Prospective identification of hematopoietic lineage choice by deep learning. Nat. Methods 14, 403– 406
  25. Yu, H. et al. (2018) Phenotypic antimicrobial susceptibility testing with deep learning video microscopy. Anal. Chem. 90, 6314– 6322
  26. Lu, C. et al. (2017) An oral cavity squamous cell carcinoma quantitative histomorphometric-based image classifier of nuclear morphology can risk stratify patients for disease-specific survival. Mod. Pathol. 30, 1655–1665
  27. Faust, K. et al. (2018) Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction. BMC Bioinform. 19, 173
  28. Edington, C.D. et al. (2018) Interconnected microphysiological systems for quantitative biology and pharmacology studies. Sci. Rep. 8, 4530
  29. Nguyen, B. et al. (2018) A platform for high-throughput assessments of environmental multistressors. Adv. Sci. (Weinh.) 5, 1700677
  30. Pandey, C.M. et al. (2017) Microfluidics based point-of-care diagnostics. J. 13, 1700047