Posted in | News | Biosensors

Deep Learning Biosensors Redefine Viral Particle Quantification

Rapid and precise diagnosis of viral infections has been the foundation of effective healthcare strategies, a fact that became critically clear during the global COVID-19 pandemic. 

DeepGT: Deep Learning-based quantification of nanosized bioparticles in bright-field micrographs of Gires-Tournois biosensor

The novel biosensing framework designed by researchers takes advantage of a Gires-Tournois immunosensor and deep learning algorithms to accurately quantify minuscule bioparticles such as viruses at even low concentrations. Credit: Professor Young Min Song from GIST, Korea

Traditional diagnostic methods often rely on time-consuming, laboratory-based processes, resulting in delayed results and hampering the swift implementation of necessary treatment and containment measures. However, an international research team has introduced a groundbreaking solution, DeepGT, which seamlessly merges nanophotonic resonators and deep learning, offering an accurate and rapid virus detection system that can revolutionize diagnostics and improve public health preparedness.

Introducing DeepGT and the Power of GT Biosensors

In a collaborative effort, spearheaded by Professor Young Min Song from the School of Electrical Engineering and Computer Science at Gwangju Institute of Science and Technology in Korea, DeepGT has emerged as a pioneering solution to the pressing challenges of viral detection. This innovation, detailed in a recent study set to be published in Volume 52 of the journal Nano Today, offers a novel approach to virus detection, combining the power of Gires-Tournois (GT) biosensors with deep learning algorithms.

GT biosensors, characterized by their capability to serve as nanophotonic resonators, have exhibited potential in the detection of minuscule virus particles, generating detailed and colorful micrographs. However, these systems have faced limitations due to visual artifacts and non-reproducibility, hampering their practicality in virus detection.

DeepGT brings together the advantages of GT biosensors and the prowess of deep learning to address these limitations effectively. It offers an objective and data-driven approach to assess the severity of infections, allowing for precise diagnosis and healthcare guidance.

Professor Song explained the motivation behind their study, stating, "We designed DeepGT to objectively assess the severity of an infection or disease. This means that we will no longer have to rely solely on subjective assessments for diagnosis and healthcare but will instead have a more accurate and data-driven approach to guide therapeutic strategies."

The DeepGT Methodology

The core of DeepGT's success lies in its methodological intricacies, as outlined in the research study. It begins with the design of a GT biosensor, featuring a trilayered thin-film configuration, biofunctionalized to enable colorimetric sensing when interacting with target analytes.

To verify the system's sensing abilities, the research team simulated the binding mechanism between host cells and viruses, utilizing specially prepared bioparticles mimicking the SARS-CoV-2 virus, which caused the COVID-19 pandemic.

DeepGT then takes the concept of virus detection to a new level by implementing convolutional neural networks (CNN) trained using a vast dataset of optical and scanning electron micrographs. This approach successfully refines visual artifacts associated with bright-field microscopy and enhances the accuracy of bioparticle quantification, even at viral concentrations as low as 138 picograms per milliliter (pg ml–1). In comparison, rule-based algorithms exhibited a mean absolute error (MAE) of 13.47, while DeepGT achieved a remarkably low MAE of 2.37 across 1,596 images.

DeepGT is not just about virus detection; it goes a step further by providing insights into the severity of infection, ranging from asymptomatic to severe cases. This advanced biosensing system can potentially offer valuable guidance in developing treatment strategies and empowering healthcare professionals with critical information.

A Solution for Swift Virus Detection

DeepGT's breakthrough in virus detection is not limited to specific virus sizes or diffraction limits in visible light.

Our approach provides a practical solution for the swift detection and management of emerging viral threats as well as the improvement of public health preparedness by potentially reducing the overall burden of costs associated with diagnostics.

Professor Young Min Song, School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology

In essence, DeepGT promises a significant leap forward in the field of virus detection, offering an efficient and precise method for screening viruses of varying sizes without being hindered by diffraction limits in visible light.

As we look to the future, the potential applications of DeepGT extend beyond virus detection. This innovation holds the promise of new AI-powered healthcare technologies that can enhance the quality of life for patients worldwide.

Introducing DeepGT represents a significant milestone in the ongoing battle against viral infections, ensuring more accurate diagnoses, faster responses, and ultimately, a healthier world.


Jiwon Kang et al., (2023) DeepGT: Deep learning-based quantification of nanosized bioparticles in bright-field micrographs of Gires-Tournois biosensor, Nano Today DOI: 10.1016/j.nantod.2023.101968

Megan Craig

Written by

Megan Craig

Megan graduated from The University of Manchester with a B.Sc. in Genetics, and decided to pursue an M.Sc. in Science and Health Communication due to her passion for learning about and sharing scientific innovations. During her time at AZoNetwork, Megan has interviewed key Thought Leaders across several scientific, medical and engineering sectors and attended prominent exhibitions worldwide.


Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Craig, Megan. (2023, October 18). Deep Learning Biosensors Redefine Viral Particle Quantification. AZoSensors. Retrieved on June 13, 2024 from

  • MLA

    Craig, Megan. "Deep Learning Biosensors Redefine Viral Particle Quantification". AZoSensors. 13 June 2024. <>.

  • Chicago

    Craig, Megan. "Deep Learning Biosensors Redefine Viral Particle Quantification". AZoSensors. (accessed June 13, 2024).

  • Harvard

    Craig, Megan. 2023. Deep Learning Biosensors Redefine Viral Particle Quantification. AZoSensors, viewed 13 June 2024,

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.