A new AI system developed by the University of Surrey’s Institute for People-Centred AI (PAI) in collaboration with the Rabies and Viral Zoonoses team at the Animal and Plant Health Agency (APHA) accelerates rabies virus detection in cell cultures. The system is designed to improve surveillance of rabies, a disease responsible for approximately 59,000 human deaths annually, and provide practical laboratory tools for endemic countries. Current diagnostic practices involve manual examination of microscope images, a process that is slow and subject to interpretation differences.
Researchers trained several deep learning models using over 2,300 fluorescence images containing over 36,000 annotated sections. The best-performing model achieved 99.6 percent accuracy in classifying rabies virus infection within cells and distinguished infected from uninfected cells effectively. The system’s capabilities include faster and more consistent sample analysis, reducing reliance on manual interpretation.
This technology could be particularly beneficial in countries with limited specialist expertise and is intended to reliably measure antibody levels, supporting vaccine protection assessments and international pet travel requirements. The research establishes a framework adaptable for the detection, analysis, and surveillance of other pathogens, potentially facilitating broader applications of AI in infectious disease research and diagnostics.
Further development aims to adapt the technology for detection in infected brain tissue, with the goal of transforming international rabies diagnostic laboratories. This innovation supports global efforts to eliminate human deaths from rabies by strengthening surveillance and improving diagnostic capabilities.