Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2014 Aug 11;9(8):e104539.
doi: 10.1371/journal.pone.0104539. eCollection 2014.

A contact-imaging based microfluidic cytometer with machine-learning for single-frame super-resolution processing

Xiwei Huang  1 , Jinhong Guo  2 , Xiaolong Wang  1 , Mei Yan  1 , Yuejun Kang  2 , Hao Yu  1
Affiliations

A contact-imaging based microfluidic cytometer with machine-learning for single-frame super-resolution processing

Xiwei Huang et al. PLoS One. .

Abstract

Lensless microfluidic imaging with super-resolution processing has become a promising solution to miniaturize the conventional flow cytometer for point-of-care applications. The previous multi-frame super-resolution processing system can improve resolution but has limited cell flow rate and hence low throughput when capturing multiple subpixel-shifted cell images. This paper introduces a single-frame super-resolution processing with on-line machine-learning for contact images of cells. A corresponding contact-imaging based microfluidic cytometer prototype is demonstrated for cell recognition and counting. Compared with commercial flow cytometer, less than 8% error is observed for absolute number of microbeads; and 0.10 coefficient of variation is observed for cell-ratio of mixed RBC and HepG2 cells in solution.

PubMed Disclaimer

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Figure 1
Figure 1. Different contact imaging systems without optical lens.
(A) Static contact imaging system. (B) Microfluidic contact imaging system with capillary flow. (C) The proposed microfluidic contact-imaging cytometer system with continuous flow: (C1) bonding process; (C2) overall system structure.
Figure 2
Figure 2. Microfluidic contact-imaging cytometer system for flowing cell detection, recognition and counting.
(A) Cell shadow image by contact imaging. (B) Captured video of flowing cells. (C) CMOS image sensor board schematic with external controls. (D) System board of the developed microfluidic cytometer.
Figure 3
Figure 3. ELM enhanced single-frame super-resolution processing flow.
(A) ELM-SR processing flowchart. The training is performed off-line to generate a reference model that can map the interpolated LR images with the HF components from the HR images; and the testing is performed on-line to recover a SR image from the input LR image with the reference model. (B) Flowing cell recognition flowchart. The detected LR image is processed with ELM-SR to obtain SR images according to different off-line trained models. Then, the SR images are compared with typical HR cell images in the library with cell categorized to one type that has the largest MSSIM.
Figure 4
Figure 4. Comparison of concentration measurement results for 6 µm microbead solution between the developed microfluidic cytometer and the commercial flow cytometer.
The average counting result of the developed microfluidic cytometer matched well with that of the commercial cytometer with 8% error.
Figure 5
Figure 5. Comparison of counting results of different microbead concentration solutions between the developed microfluidic cytometer and the commercial flow cytometer.
(A) Measurement results correlate well between the developed system and the commercial one (y = 0.97x-8, correlation coefficient = 0.996). (B) The Bland-Altman analysis of the measurement results between the developed one and the commercial one show a mean bias of −13.6 uL−1, the lower 95% limit of agreement by −61.0 uL−1, and the upper 95% limit of agreement by 33.8 uL−1.
Figure 6
Figure 6. ELM-SR off-line training images for HepG2 and RBC cells.
(A) The original HR images for HepG2 cell with two different appearances; and the same for RBC cells. (B) The corresponding LR images. (C) The interpolated images of LR images, which cannot show HF details. (D) The extracted HF components. The scale bar indicates 5 µm.
Figure 7
Figure 7. ELM-SR on-line testing results for HepG2 and RBC cells.
The resolution is improved by 4× after ELM-SR processing. (A) The HepG2 on-line testing image and the recovered SR image. (B) The RBC on-line testing image and the recovered SR image. (C) The comparison of MSSIM for different SR images obtained under different training models. The detected HepG2 and RBC can be correctly categorized to its type as the SR image recovered by corresponding ELM-SR model produces a larger MSSIM when compared to each cell HR library. The scale bar indicates 5 µm.
Figure 8
Figure 8. Commercial flow cytometer counting results for the mixed RBC and HepG2 cells.
The absolute counts of RBC and HepG2 are 1054 and 978 with the ratio of RBC/HepG2 by 51.9%:48.1% = 1.08: 1.
See this image and copyright information in PMC

References

    1. Shapiro HM (2003) Practical Flow Cytometry, 4th Edition, Wiley.
    1. Givan A (2001) Flow cytometry: first principles, John Wiley & Sons.
    1. Brown M, Wittwer C (2000) Flow cytometry: principles and clinical applications in hematology. Clinical Chemistry 46: 1221–1229. - PubMed
    1. Gupta GP, Massagué J (2006) Cancer metastasis: building a framework. Cell 127: 679–695. - PubMed
    1. Hammer SM, Eron JJ, Reiss P (2008) Schooley RT, Thompson MA, et al (2008) Antiretroviral treatment of adult HIV infection. Journal of the American Medical Association 300: 555–570. - PubMed

Publication types

LinkOut - more resources