With the global pandemic of infectious diseases, the demand for accurate nucleic acid detection is daily increasing. The traditional threshold-based algorithms are adopted as the mainstream for processing the images of digital polymerase chain reaction (dPCR) now, but they are facing huge challenges on complex problems such as irregular noise, uneven illumination, and the lack of data. So, this paper proposed a novel few-shot learning method based on our improved YOLOv3 model with fast processing speed and high accuracy to deal with complicated situations. Besides, to reduce the requirement of the large training dataset and annotation time of deep neural networks, we proposed the Random Background Transfer Method (RBTM) and Source Traceability Annotation Method (STAM) as the data augmentation and annotation method separately, which exploit the prior knowledge of the data and successfully realized the few-shot learning. Bases on the domain knowledge of dPCR images, our method could effectively augment images and reduce the labeling time by 70% while retaining the visually prominent features and improves the detection accuracy from 63.96% of the traditional threshold-based algorithm to as high as 98.98%. With the optimal processing speed and accuracy, our method is the state-of-art strategy for the detection of dPCR images now.
Point‐of‐care detection for pathogen is of critical need for wide epidemic warning and medical diagnosis. In this work, we have designed and developed a fully portable and integrated microchip based real‐time polymerase chain reaction machine for rapid pathogen detection. The instrument consists of three functional components including heating, optical, and electrical modules, which are integrated into a portable compact box. The microchip is consumable material replaceable to meet various detection needs. Consequently, we demonstrated the outstanding performance of this portable machine for rapid detection of Salmonella and Escherichia coli O157:H7 with the advantage of time‐saving (∼25 min), less samples consumption, portability, and user‐friendly operation.
The result of molecular diagnostic and detection greatly dependent on the quality and integrity of the isolated nucleic acid. In this work, we developed an automated miniaturized nucleic acid extraction device based on magnetic beads method, consisting of four components including a sample processing disc and its associated rotary power output mechanism, a pipetting module, a magnet module and an external central controller to enable a customizable and automated robust nucleic acid sample preparation. The extracted nucleic acid using 293T cells were verified using real-time polymerase chain reaction (PCR) and the data implies a comparable efficiency to a manual process, with the advantages of performing a flexible, time-saving (~10 min), and simple nucleic acid sample preparation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.