Related Experiment Video
Updated: May 5, 2026
10:25
Detection of SARS-CoV-2 Neutralizing Antibodies using High-Throughput Fluorescent Imaging of Pseudovirus Infection
Published on: June 5, 2021
4.8K
AI-Driven Comprehensive SERS-LFIA System: Improving Virus Automated Diagnostics Through SERS Image Recognition and
Shuai Zhao1,2,3, Meimei Xu1,2,3, Chenglong Lin1,2,3
1State Key Laboratory of High Performance Ceramics, Shanghai Institute of Ceramics, Chinese Academy of Sciences, 1295 Dingxi Road, Shanghai 200050, China.
Biosensors
|July 25, 2025
Summary
A new Surface-Enhanced Raman Scattering-Lateral Flow Immunoassay (SERS-LFIA) system uses artificial intelligence (AI) for rapid virus detection. This advanced diagnostic tool enhances accuracy and simplifies testing for infectious diseases.
Area of Science:
- Nanotechnology and Materials Science
- Biotechnology and Biosensing
- Artificial Intelligence in Diagnostics
Background:
- Global public health is threatened by highly infectious viruses, necessitating rapid and accurate diagnostic tools.
- Current diagnostic methods may lack the sensitivity or speed required for effective outbreak management.
- There is a need for integrated systems that combine sensitive detection with automated result interpretation.
Purpose of the Study:
- To develop a comprehensive Surface-Enhanced Raman Scattering-Lateral Flow Immunoassay (SERS-LFIA) detection system.
- To integrate SERS scanning imaging with artificial intelligence (AI) for automated result discrimination.
- To create a sensitive and reliable diagnostic platform for highly pathogenic viruses.
Main Methods:
- Development of an ultra-sensitive SERS-LFIA strip using SiO2-Au NSs as immunoprobes.
- Implementation of SERS scanning imaging for capturing probe distribution patterns.
- Application of a deep learning model (ResNet-18) for AI-based analysis and discrimination of results.
Main Results:
- The SERS-LFIA strip achieved a theoretical limit of detection (LOD) of 1.8 pg/mL.
- The AI-based method reliably detected viruses at concentrations as low as 2.5 pg/mL, reducing signal interference.
- The ResNet-18 model demonstrated high accuracy (100% training, 94.52% testing) in image recognition.
Conclusions:
- The integrated SERS-LFIA system simplifies the detection process, requiring less specialized personnel and reducing test time.
- The system offers improved diagnostic reliability and significant clinical potential for detecting various viruses.
- This technology provides a robust foundation for future pandemic preparedness and versatile pathogen detection.
