Cytopathological image analysis using deep-learning networks in microfluidic microscopy

Gopakumar, G.; Babu, K. Hari; Mishra, Deepak; Gorthi, Sai Siva; Subrahmanyam, Gorthi R. K. Sai

doi:10.1364/josaa.34.000111

Cited by 23 publications

(15 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, experimental and data scientists in drug discovery have shown diverse applications of ML and DL. 66–73 For both AI–ML–DL and systems biology–inspired modeling space, the prediction of DILI or hepatotoxicity is one of the most notable areas in which these modeling efforts are being applied. DILI is a major clinical and pharmaceutical concern leading to the termination of potential drug candidates.…”

Section: Future Perspective and Conclusionmentioning

confidence: 99%

Recommended Guidelines for Developing, Qualifying, and Implementing Complex In Vitro Models (CIVMs) for Drug Discovery

et al. 2020

View full text Add to dashboard Cite

Section: Future Perspective and Conclusionmentioning

confidence: 99%

Recommended Guidelines for Developing, Qualifying, and Implementing Complex In Vitro Models (CIVMs) for Drug Discovery

et al. 2020

View full text Add to dashboard Cite

“…It also promotes the advancement of high‐throughput single‐cell imaging technology. Deep learning brings automatic analysis methods for large numbers of microfluidic cell microscopy images, and single‐cell optical image big data also make the deep learning model more generalized . Imaging flow cytometry is an emerging technology that combines the statistical functions of flow cytometry with the image capability of microscopy, which has rapidly become a sophisticated tool for single‐cell analysis in biological fields such as microbiology, immunology, and stem cell biology .…”

Section: Applications Of Deep Learning In Single‐cell Optical Image Smentioning

confidence: 99%

“…The deep learning method has been recently applied to the big‐data images obtained by imaging flow cytometry. For example, there are reports to combine deep learning with imaging flow cytometry for high‐throughput single‐cell classification and identification and for the reconstruction of continuous biological processes . Deep learning technologies are widely used for the analysis of big‐data optical images from label‐free cell imaging, high‐content screening, and high‐throughput imaging cytometry as illustrated in Figure .…”

Section: Applications Of Deep Learning In Single‐cell Optical Image Smentioning

confidence: 99%

“…Deep learning has been widely used in cellular image research, and a review about deep learning in imaging cytometry has been reported recently , which illustrates the broad applicability of deep learning methods for image cytometry. Deep learning technology has unique advantages in big data analysis, which have been reported to analyze big data from microfluidic microscopy and high‐throughput imaging flow cytometry . Figure shows the evolution of methods for single‐cell optical image process and analysis.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning‐Based Single‐Cell Optical Image Studies

Sun

Tárnok

2020

Cytometry Pt A

View full text Add to dashboard Cite

Optical imaging technology that has the advantages of high sensitivity and cost‐effectiveness greatly promotes the progress of nondestructive single‐cell studies. Complex cellular image analysis tasks such as three‐dimensional reconstruction call for machine‐learning technology in cell optical image research. With the rapid developments of high‐throughput imaging flow cytometry, big data cell optical images are always obtained that may require machine learning for data analysis. In recent years, deep learning has been prevalent in the field of machine learning for large‐scale image processing and analysis, which brings a new dawn for single‐cell optical image studies with an explosive growth of data availability. Popular deep learning techniques offer new ideas for multimodal and multitask single‐cell optical image research. This article provides an overview of the basic knowledge of deep learning and its applications in single‐cell optical image studies. We explore the feasibility of applying deep learning techniques to single‐cell optical image analysis, where popular techniques such as transfer learning, multimodal learning, multitask learning, and end‐to‐end learning have been reviewed. Image preprocessing and deep learning model training methods are then summarized. Applications based on deep learning techniques in the field of single‐cell optical image studies are reviewed, which include image segmentation, super‐resolution image reconstruction, cell tracking, cell counting, cross‐modal image reconstruction, and design and control of cell imaging systems. In addition, deep learning in popular single‐cell optical imaging techniques such as label‐free cell optical imaging, high‐content screening, and high‐throughput optical imaging cytometry are also mentioned. Finally, the perspectives of deep learning technology for single‐cell optical image analysis are discussed. © 2020 International Society for Advancement of Cytometry

show abstract

“…In fluid mechanics, neural networks have been reported recently [3][4][5] as tools that can help computational fluid mechanics simulations by mapping the estimates of low-resolution simulations to those with higher fidelity. In microfluidics, neural networks have been used to estimate various quantities for different applications [6][7][8][9] . Mahdi and Daoud 10 used neural networks to predict the size of the droplets in an emulsion while Khor et al 11 .…”

mentioning

confidence: 99%

Learning from droplet flows in microfluidic channels using deep neural networks

Hadikhani

Borhani

Hashemi

2019

Sci Rep

View full text Add to dashboard Cite

A non-intrusive method is presented for measuring different fluidic properties in a microfluidic chip by optically monitoring the flow of droplets. A neural network is used to extract the desired information from the images of the droplets. We demonstrate the method in two applications: measurement of the concentration of each component of a water/alcohol mixture, and measurement of the flow rate of the same mixture. A large number of droplet images are recorded and used to train deep neural networks (DNN) to predict the flow rate or the concentration. It is shown that this method can be used to quantify the concentrations of each component with a 0.5% accuracy and the flow rate with a resolution of 0.05 ml/h. The proposed method can in principle be used to measure other properties of the fluid such as surface tension and viscosity.Machine learning is a framework that learns from the data without being programmed. Deep leaning is a specific approach of machine learning 1 which has emerged in recent years as a powerful technique for a broad range of applications. Deep learning consists of several representation layers where each layer is obtained by the non-linear transformation of the previous layer 2 . Deep neural networks use the combination of these transformations to learn complex functions. In fluid mechanics, neural networks have been reported recently 3-5 as tools that can help computational fluid mechanics simulations by mapping the estimates of low-resolution simulations to those with higher fidelity. In microfluidics, neural networks have been used to estimate various quantities for different applications 6-9 . Mahdi and Daoud 10 used neural networks to predict the size of the droplets in an emulsion while Khor et al. 11 . used them to predict the stability of droplets in an emulsion. In our work, we employ neural networks to estimate fluid and flow parameters by observing the droplet formation process in a passive microfluidic chip. We extract this information by monitoring the flow of droplets with an optical microscope and training a neural network to obtain useful information from the recorded images. In one experiment, we trained a network to accurately measure the flow velocity at the inlet of the channel from droplet images. In a separate demonstration, a network was trained to identify the concentration of isopropanol in water in the droplet-forming solution. Our experiments demonstrate that DNNs can capture the complex nonlinear phenomena that result in the flow patterns and droplet shapes.The flow rate is a parameter that affects droplet formation 12 and can change the size, generation frequency, and pattern of droplets 13 . Similarly, the dilution ratio of isopropanol (IPA) in water affects the generation frequency and flow pattern of the droplets. Such effects can also be recognized by the DNN to measure the concentration. There are alternative methods for measuring the flow rate 14-17 or the dilution ratio 18-21 in a microfluidic chip. The two prominent methods for on-chip flow measurement...

show abstract

Cytopathological image analysis using deep-learning networks in microfluidic microscopy

Cited by 23 publications

References 23 publications

Recommended Guidelines for Developing, Qualifying, and Implementing Complex In Vitro Models (CIVMs) for Drug Discovery

Recommended Guidelines for Developing, Qualifying, and Implementing Complex In Vitro Models (CIVMs) for Drug Discovery

Deep Learning‐Based Single‐Cell Optical Image Studies

Learning from droplet flows in microfluidic channels using deep neural networks

Contact Info

Product

Resources

About