A Contact-Imaging Based Microfluidic Cytometer with Machine-Learning for Single-Frame Super-Resolution Processing

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.

On-chip cell analysis platform: Implementation of contact fluorescence microscopy in microfluidic chips

“…[15][16][17][18][19] However, implementation of contact fluorescence microscopy in a microfluidic chip platform is not simple, due to certain technical obstacles that arise from the characteristic features of fluorescence imaging. First, the fluorescence signal intensity and spatial resolution decreases at a greater rate as a function of the vertical distance between samples and the detection region (e.g.…”

A 64×64 1200fps dual-mode CMOS ion-image sensor for accurate DNA sequencing

“…As shown in Fig. 2, each dual-mode pixel contains a 4T-CIS pixel to capture the shadow image of microbeads through contact imaging [8]; and the source follower (SF) can work as ISFET to detect pH. Photodiode (PD) first collects photons and converts them to electrons, which are transferred to floating diffusion (FD) by turning on TX .…”

“…When microbeads attached with DNA slices are initially distributed onto the pixel array, the optical mode is turned on so that the sensor pixels can work as a normal 4T-CIS pixel to capture the shadow image of microbeads by contact imaging [8]. Hence, the existence of microbead at each pixel is determined.…”

An Optimal Pin-Count Design With Logic Optimization for Digital Microfluidic Biochips

“…In such a chip, complex sensing systems whose objective is to send feedback of the biochemical application to the control software are integrated to the original biochips. Moreover, a CMOS-based image sensor integrated in a microfluidic system has been successfully demonstrated in [8] and [9].…”

“…The minimum clique partition result of the graph G in Fig. 4 8 , v 9 }; and the number of cliques is 4.…”