scholarly journals Neural network control of focal position during time-lapse microscopy of cells

2017 ◽  
Author(s):  
Ling Wei ◽  
Elijah Roberts
Keyword(s):  
Neural Network ◽  
High Throughput ◽  
Time Lapse ◽  
Network Control ◽  
Live Cell ◽  
Yeast Cells ◽  
Batch Size ◽  
Neural Network Approach ◽  
Cellular Processes ◽  
Focal Position

AbstractLive-cell microscopy is quickly becoming an indispensable technique for studying the dynamics of cellular processes. Maintaining the specimen in focus during image acquisition is crucial for high-throughput applications, especially for long experiments or when a large sample is being continuously scanned. Automated focus control methods are often expensive, imperfect, or ill-adapted to a specific application and are a bottleneck for widespread adoption of high-throughput, live-cell imaging. Here, we demonstrate a neural network approach for automatically maintaining focus during bright-field microscopy. Z-stacks of yeast cells growing in a microfluidic device were collected and used to train a convolutional neural network to classify images according to their z-position. We studied the effect on prediction accuracy of the various hyperparameters of the neural network, including downsampling, batch size, and z-bin resolution. The network was able to predict the z-position of an image with ±1 μm accuracy, outperforming human annotators. Finally, we used our neural network to control microscope focus in real-time during a 24 hour growth experiment. The method robustly maintained the correct focal position compensating for 40 μm of focal drift and was insensitive to changes in the field of view. Only ~100 annotated z-stacks were required to train the network making our method quite practical for custom autofocus applications.

Single-cell time-lapse imaging of the dynamic control of NF-κB signalling

2007 ◽  
Vol 35 (2) ◽  
pp. 263-266 ◽  
Author(s):  
K. Sillitoe ◽  
C. Horton ◽  
D.G. Spiller ◽  
M.R.H. White
Keyword(s):  
Single Cell ◽  
Dynamic Control ◽  
Time Lapse ◽  
Nuclear Factor Κb ◽  
Network Control ◽  
Dynamic Regulation ◽  
Cellular Processes ◽  
The Past ◽  
Single Cell Imaging ◽  
Time Lapse Imaging

The transcription factor NF-κB (nuclear factor κB) regulates critical cellular processes including the inflammatory response, apoptosis and the cell cycle. Over the past 20 years many of the components of the NF-κB signalling pathway have been elucidated along with their functions. Recent research in this field has focused on the dynamic regulation and network control of this system. With key roles in so many important cellular processes, it is critical that NF-κB signalling is tightly regulated. Recently, single-cell imaging and mathematical modelling have identified that the timing of cellular responses may play an important role in the regulation of this pathway. p65/RelA (RelA) has been shown to translocate between the nucleus and cytoplasm with varying oscillatory patterns in different cell lines leading to differences in transcriptional outputs from NF-κB-regulated genes. Variations in the timing or persistence of these movements may control the maintenance and differential expression of NF-κB-regulated genes.

scholarly journals High-throughput formation and image-based analysis of basal-in mammary organoids in 384-well plates

2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Soojung Lee ◽  
Jonathan Chang ◽  
Sung-Min Kang ◽  
Eric Parigoris ◽  
Ji-Hoon Lee ◽  
...  
Keyword(s):  
Growth Factor ◽  
High Throughput ◽  
Live Cell Imaging ◽  
Cell Imaging ◽  
Automated Analysis ◽  
Time Lapse ◽  
Culture Conditions ◽  
Live Cell ◽  
Future Research ◽  
Heparin Binding

AbstractThis manuscript describes a new method for forming basal-in MCF10A organoids using commercial 384-well ultra-low attachment (ULA) microplates and the development of associated live-cell imaging and automated analysis protocols. The use of a commercial 384-well ULA platform makes this method more broadly accessible than previously reported hanging drop systems and enables in-incubator automated imaging. Therefore, time points can be captured on a more frequent basis to improve tracking of early organoid formation and growth. However, one major challenge of live-cell imaging in multi-well plates is the rapid accumulation of large numbers of images. In this paper, an automated MATLAB script to handle the increased image load is developed. This analysis protocol utilizes morphological image processing to identify cellular structures within each image and quantify their circularity and size. Using this script, time-lapse images of aggregating and non-aggregating culture conditions are analyzed to profile early changes in size and circularity. Moreover, this high-throughput platform is applied to widely screen concentration combinations of Matrigel and epidermal growth factor (EGF) or heparin-binding EGF-like growth factor (HB-EGF) for their impact on organoid formation. These results can serve as a practical resource, guiding future research with basal-in MCF10A organoids.

Automated quantification of morphodynamics for high-throughput live cell time-lapse datasets

2013 ◽  
Author(s):  
German Gonzalez ◽  
Ludovico Fusco ◽  
Fethallah Benmansour ◽  
Pascal Fua ◽  
Olivier Pertz ◽  
...  
Keyword(s):  
High Throughput ◽  
Time Lapse ◽  
Live Cell ◽  
Automated Quantification

Refining PID Controllers Using Neural Networks

1992 ◽  
Vol 4 (5) ◽  
pp. 746-757 ◽  
Author(s):  
Gary M. Scott ◽  
Jude W. Shavlik ◽  
W. Harmon Ray
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Control ◽  
Pid Controllers ◽  
Water Tank ◽  
Neural Network Control ◽  
Neural Network Approach ◽  
Knowledge Based ◽  
Mathematical Equations ◽  
Artificial Neural

The KBANN (Knowledge-Based Artificial Neural Networks) approach uses neural networks to refine knowledge that can be written in the form of simple propositional rules. We extend this idea further by presenting the MANNCON (Multivariable Artificial Neural Network Control) algorithm by which the mathematical equations governing a PID (Proportional-Integral-Derivative) controller determine the topology and initial weights of a network, which is further trained using backpropagation. We apply this method to the task of controlling the outflow and temperature of a water tank, producing statistically significant gains in accuracy over both a standard neural network approach and a nonlearning PID controller. Furthermore, using the PID knowledge to initialize the weights of the network produces statistically less variation in test set accuracy when compared to networks initialized with small random numbers.

A fuzzy neural network approach for modeling the growth kinetics of FeB and Fe2B layers during the boronizing process

2018 ◽  
Vol 106 (6) ◽  
pp. 603 ◽  
Author(s):  
Bendaoud Mebarek ◽  
Mourad Keddam
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Fuzzy Neural Network ◽  
Treatment Time ◽  
Calculation Model ◽  
Average Error ◽  
Network Approach ◽  
Neural Network Approach ◽  
Fuzzy Neural ◽  
Kinetics Of

In this paper, we develop a boronizing process simulation model based on fuzzy neural network (FNN) approach for estimating the thickness of the FeB and Fe2B layers. The model represents a synthesis of two artificial intelligence techniques; the fuzzy logic and the neural network. Characteristics of the fuzzy neural network approach for the modelling of boronizing process are presented in this study. In order to validate the results of our calculation model, we have used the learning base of experimental data of the powder-pack boronizing of Fe-15Cr alloy in the temperature range from 800 to 1050 °C and for a treatment time ranging from 0.5 to 12 h. The obtained results show that it is possible to estimate the influence of different process parameters. Comparing the results obtained by the artificial neural network to experimental data, the average error generated from the fuzzy neural network was 3% for the FeB layer and 3.5% for the Fe2B layer. The results obtained from the fuzzy neural network approach are in agreement with the experimental data. Finally, the utilization of fuzzy neural network approach is well adapted for the boronizing kinetics of Fe-15Cr alloy.

Sign in / Sign up

Export Citation Format

Share Document