Deep Learning-Assisted Droplet Digital PCR for Quantitative Detection of Human Coronavirus.

Since coronavirus disease 2019 (COVID-19) pandemic rapidly spread worldwide, there is an urgent demand for accurate and suitable nucleic acid detection technology. Although the conventional threshold-based algorithms have been used for processing images of droplet digital polymerase chain reaction (ddPCR), there are still challenges from noise and irregular size of droplets. Here, we present a combined method of the mask region convolutional neural network (Mask R-CNN)-based image detection algorithm and Gaussian mixture model (GMM)-based thresholding algorithm. This novel approach significantly reduces false detection rate and achieves highly accurate prediction model in a ddPCR image processing. We demonstrated that how deep learning improved the overall performance in a ddPCR image processing. Therefore, our study could be a promising method in nucleic acid detection technology.

Development of an IoT-integrated multiplexed digital PCR system for quantitative detection of infectious diseases.

For rapid detection of the COVID-19 infection, the digital polymerase chain reaction (dPCR) with higher sensitivity and specificity has been presented as a promising method of point-of-care testing (POCT). Unlike the conventional real-time PCR (qPCR), the dPCR system allows absolute quantification of the target DNA without a calibration curve. Although a number of dPCR systems have previously been reported, most of these previous assays lack multiplexing capabilities. As different variants of COVID-19 have rapidly emerged, there is an urgent need for highly specific multiplexed detection systems. Additionally, the advances in the Internet of Things (IoT) technology have enabled the onsite detection of infectious diseases. Here, we present an IoT-integrated multiplexed dPCR (IM-dPCR) system involving sample compartmentalization, DNA amplification, fluorescence imaging, and quantitative analysis. This IM-dPCR system comprises three modules: a plasmonic heating-based thermal cycler, a multi-color fluorescence imaging set-up, and a firmware control module. Combined with a custom-developed smartphone application built on an IoT platform, the IM-dPCR system enabled automatic processing, data collection, and cloud storage. Using a self-priming microfluidic chip, 9 RNA groups (e.g., H1N1, H3N2, IFZ B, DENV2, DENV3, DENV4, OC43, 229E, and NL63) associated with three infectious diseases (e.g., influenza, dengue, and human coronaviruses) were analyzed with higher linearity (>98%) and sensitivity (1 copy per µL). The IM-dPCR system exhibited comparable analytical accuracy to commercial qPCR platforms. Therefore, this IM-dPCR system plays a crucial role in the onsite detection of infectious diseases.