New rapid viral plaque detection system, aided by deep learning and


In a new paper published in Natural Biomedical Engineering, a team of scientists led by Professor Aydogan Ozcan of the Department of Electrical and Computer Engineering at UCLA and associate director of the California NanoSystems Institute, developed a fast, smudge-free, automated viral plaque detection system enabled by holography and deep learning. The system incorporates a cost-effective, high-throughput holographic imaging device that continuously monitors unstained virus-infected cells throughout their incubation process. During each imaging cycle, the time-lapse hologram captured by the device is periodically analyzed by an AI-powered algorithm to automatically detect and quantify viral plaques that arise as a result of viral replication.


Viral infections have challenged humanity for centuries. Even with progressive scientific advances, the fight against the virus continues, as exemplified by the recent COVID-19 pandemic. In the fight against this viral infection, various techniques have been established to detect and quantify viruses, making a significant contribution to the development of critical vaccines and antiviral treatments. Among these techniques, the viral plaque assay stands out as the gold standard because of its unique ability to assess viral infectivity in a cost-effective manner by observing viral plaque formation caused by viral infection in the cell layer. However, the traditional viral plaque test requires an incubation period of 2~14 days, followed by staining of the sample using chemicals and human visual inspection to quantify the amount of viral plaque. This procedure is time consuming and prone to coloring artifacts and calculation errors caused by human technicians. Therefore, an accurate, automatic, fast, and cost-effective quantification of viral plaque is urgently needed.


The proof of concept and effectiveness of this system was demonstrated using three different types of viruses: vesicular stomatitis virus (VSV), herpes simplex virus type-1 (HSV-1), and encephalomyocarditis virus (EMCV). By leveraging this system, UCLA researchers achieved detection of more than 90% of VSV viral plaques within 20 hours of incubation without chemical staining, indicating a time saving of more than 24 hours compared to the traditional plaque assay, which requires 48 hours. sample incubation. In the case of HSV-1 and EMCV, this system effectively reduced the detection time of viral plaque by approximately 48 and 20 hours, respectively, compared to the detection time required for traditional stain-based viral plaque assays.


As well as offering major time savings, this stain-free and cost-effective system can successfully identify individual viral plaques within a cluster compared to traditional viral plaque assays, which fail to separately detect and enumerate individual plaques within a cluster due to spatial overlap. their signature.


Tairan Liu, Yuzhu Li, Hatice Ceylan Koydemir, Yijie Zhang, Ethan Yang, Merve Eryilmaz, Hongda Wang, Jingxi Li, Bijie Bai, Guangdong Ma, and Aydogan Ozcan

What Researchers Say:

Aydogan Ozkan: “Our results and analysis highlight the transformative potential of this AI-powered viral plaque detection system for use with a variety of plaque assays in virology, which can help accelerate vaccine and drug development research by significantly reducing the detection time required for traditional viral plaque assays. and eliminating chemical coloring and manual counting entirely.”


The study was published online in the journal Natural Biomedical Engineering.

Source link

Related Articles

Back to top button