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

Huang X, Guo J, Wang X, Yan M, Kang Y, Yu H - PLoS ONE (2014)

Bottom Line: 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.

View Article: PubMed Central - PubMed

Affiliation: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore.

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.

Show MeSH

Related in: MedlinePlus

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.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4128713&req=5

pone-0104539-g005: 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.

Mentions: To further evaluate the developed microfluidic cytometer, five microbead samples of different concentrations, ranging from ∼50 uL−1 to ∼800 uL−1 were prepared. The flow rate and imaging time were used under the same settings. As shown from Fig. 5(A), the measurement results of the developed microfluidic cytometer correlated well with the commercial flow cytometer with a correlation coefficient of 0.99. Moreover, in order to assess the agreement between the two methods, the Bland-Altman analysis was also performed. As the results shown in Fig. 5(B), a systematic mean bias of −13 cells uL−1 was obtained for the developed microfluidic cytometer compared with the commercial flow cytometer. The under counting performance was due to the dead volume in the channel inlet/outlet as well as the cell lost and sedimentation in the tubing.


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

Huang X, Guo J, Wang X, Yan M, Kang Y, Yu H - PLoS ONE (2014)

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.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4128713&req=5

pone-0104539-g005: 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.
Mentions: To further evaluate the developed microfluidic cytometer, five microbead samples of different concentrations, ranging from ∼50 uL−1 to ∼800 uL−1 were prepared. The flow rate and imaging time were used under the same settings. As shown from Fig. 5(A), the measurement results of the developed microfluidic cytometer correlated well with the commercial flow cytometer with a correlation coefficient of 0.99. Moreover, in order to assess the agreement between the two methods, the Bland-Altman analysis was also performed. As the results shown in Fig. 5(B), a systematic mean bias of −13 cells uL−1 was obtained for the developed microfluidic cytometer compared with the commercial flow cytometer. The under counting performance was due to the dead volume in the channel inlet/outlet as well as the cell lost and sedimentation in the tubing.

Bottom Line: 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.

View Article: PubMed Central - PubMed

Affiliation: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore.

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.

Show MeSH
Related in: MedlinePlus