A new method using machine learning for automated image analysis applied to chip-based digital assays.

Authors:
Jiumei Hu
Jiumei Hu
Research Center for Analytical Instrumentation
Shufang Zhou
Shufang Zhou
Haian Hospital of Nantong University
China
Weibo Fang
Weibo Fang
College of Agronomy
College Station | United States
Jingjing Sun
Jingjing Sun
Shanghai Institute of Organic Chemistry
China
Zhenming Hu
Zhenming Hu
Chongqing Medical University
China

Analyst 2019 May;144(10):3274-3281

Research Center for Analytical Instrumentation, Institute of Cyber-Systems and Control, State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, P. R. China.

Chip-based digital assays such as the digital polymerase chain reaction (digital PCR), digital loop-mediated amplification (digital LAMP), digital enzyme-linked immunosorbent assay (digital ELISA) and digital proximity ligation assay (digital PLA) need high-throughput quantification of the captured fluorescence image data. However, traditional methods that are mainly based on image segmentation using either a fixed threshold or an automated hard threshold failed to extract valid signals over a broad range of image characteristics. In this study, we introduce a new method for automated image analysis to extract signals applied to chip-based digital assays. This approach precisely locates each micro-compartment based on the structure design of the chip, thereby eliminating the interference of non-signal noise in the image. Utilizing the principle that the human eyes can distinguish between the positive micro-compartments and the negative micro-compartments, we take the parameters of each micro-compartment together with its surrounding micro-compartments as the training dataset of the Random Forest classifier to classify the micro-compartments and extract valid signals, thus solving the problem caused by the differences among images. Furthermore, we adopted the iteration methodology that adds the output of a model's prediction to the input of the next model's training dataset, until the output of a model's prediction reaches the accuracy we expected, which improves the work efficiency during data training greatly. We demonstrate the method on the dPCR dataset and it performs well without any manual adjustment of settings. The results show that our proposed method can recognize the positive signals from the fluorescence images with an accuracy of 97.78%. With minor modification, bio-instrument companies or researchers can integrate this method into their digital assay devices' software conveniently.

Download full-text PDF

Source
http://xlink.rsc.org/?DOI=C9AN00149B
Publisher Site
http://dx.doi.org/10.1039/c9an00149bDOI Listing
May 2019
5 Reads

Publication Analysis

Top Keywords

digital
12
chip-based digital
12
digital assays
12
extract valid
8
applied chip-based
8
image analysis
8
training dataset
8
automated image
8
output model's
8
valid signals
8
model's prediction
8
assay digital
8
image
6
method
5
random forest
4
dataset random
4
surrounding micro-compartments
4
negative micro-compartments
4
micro-compartments parameters
4
parameters micro-compartment
4

References

(Supplied by CrossRef)
Article in Lab Chip
Kim et al.
Lab Chip 2015
Article in SLAS Technol.
Basu et al.
SLAS Technol. 2017
Article in Lab Chip
Zhu et al.
Lab Chip 2014
Article in Nat. Methods
Heyries et al.
Nat. Methods 2011
Article in Lab Chip
Zhu et al.
Lab Chip 2017
Article in Lab Chip
Zhu et al.
Lab Chip 2012
Article in PloS one
Leung et al.
PloS one 2010
Article in Lab Chip
Gansen et al.
Lab Chip 2012
Article in Nat. Biotechnol.
Rissin et al.
Nat. Biotechnol. 2010
Article in Anal. Chem.
Schubert et al.
Anal. Chem. 2016
Article in Lab Chip
Kim et al.
Lab Chip 2012

Similar Publications