Point-of-care SARS-CoV-2 sensing using lens-free imaging and a deep learning-assisted quantitative agglutination...

Area of Science:

• Biomedical Engineering
• Infectious Disease Diagnostics
• Computational Imaging

Background:

• The COVID-19 pandemic highlights the need for rapid, sensitive point-of-care (POC) diagnostic tests.
• Current methods like RT-PCR and antigen tests have limitations in speed and sensitivity.
• Accurate viral detection is crucial for pandemic mitigation and patient management.

Purpose of the Study:

• To develop a novel, portable biosensor for rapid and sensitive SARS-CoV-2 detection.
• To integrate lens-free imaging with a particle agglutination assay for viral quantification.
• To utilize deep learning for accurate analysis of microbead agglutination patterns.

Main Methods:

• A portable lens-free holographic microscope images microbeads functionalized with ACE2 receptors.
• Computational imaging reconstructs high-resolution holograms of microbeads.
• A deep-learning algorithm analyzes microbead agglutination to quantify SARS-CoV-2 levels.

Main Results:

• The biosensor accurately determines viral concentrations above a limit of detection of 1.27 × 10^3 copies/mL.
• A dynamic range of 3 orders of magnitude was demonstrated.
• The system effectively distinguishes viral agglutination from other sample components.

Conclusions:

• This lens-free imaging biosensor offers a promising solution for rapid SARS-CoV-2 diagnosis at the POC.
• The technology is suitable for low-resource settings, enhancing pandemic response capabilities.
• It has the potential to significantly aid in controlling the spread of future viral outbreaks.