University of Surrey AI system detects rabies in cell cultures with 99.6% accuracy

AI Workflow Accelerates Rabies Detection in Cell Cultures

A new artificial intelligence system developed by researchers at the University of Surrey’s Institute for People-Centred AI and the Animal and Plant Health Agency speeds up rabies virus detection and antibody quantification in cell cultures.

Rabies claims approximately 59,000 human lives globally each year despite being nearly entirely preventable through vaccination. Current diagnostic methods rely on specialists manually examining thousands of microscope images, which remains slow, labor-intensive, and susceptible to interpretive variation.

Understanding the Automated Diagnostic Workflow

In a DEFRA-funded study published in Nature Scientific Reports, the research team created the first AI-based workflow that identifies rabies virus infection in cell cultures and measures antibody concentration levels. The team trained several deep learning models using more than 2,300 fluorescence images containing over 36,000 annotated image sections. The best-performing model correctly classified 99.6 percent of samples, distinguishing infected from uninfected cells while avoiding false alarms.

“Rabies is one of the world’s oldest and deadliest infectious diseases, claiming tens of thousands of lives every year because timely diagnosis and surveillance remain challenging in many parts of the world. Once clinical signs appear, it is almost always fatal, so prevention and early diagnosis are essential,” Joan Amaya-Cuesta, a PhD researcher at the University of Surrey and a Rabies and Viral Zoonoses Research Scientist at the APHA, stated.

“Our AI workflow provides laboratories with a faster and more consistent way to analyze samples while reducing the reliance on manual interpretation,” Amaya-Cuesta added.

Global Applications and Future Pathogens Research

The technology aims to help laboratories analyze samples quickly and consistently in countries where rabies remains endemic and specialist expertise is scarce. It also evaluates antibody levels used to assess vaccine protection and support international pet travel requirements.

“This research shows how AI can support scientists by carrying out complex image analysis quickly, consistently and at scale. While we’ve demonstrated this approach for rabies, the same framework could be applied to other infectious diseases that rely on similar laboratory tests, helping researchers and diagnostic laboratories make better use of AI in the future,” Professor Miroslaw Bober, Professor of Video Processing and Machine Intelligence at the University of Surrey, noted.

Parameter	Details
Study Publication	Nature Scientific Reports (2026)
Dataset Size	2,300+ fluorescence images (36,000+ annotated sections)
Model Accuracy	99.6 percent correct classification
Key Collaborators	University of Surrey PAI & Animal and Plant Health Agency (APHA)

Researchers are currently adapting the technology to detect the virus in infected brain tissue. Dr. Lorraine M. McElhinney, Head of the National Reference Laboratory for Human and Animal Rabies at the APHA, stated, “We hope this innovation will help strengthen rabies surveillance and, ultimately, support global efforts to eliminate human deaths from this disease. This technology is now being further developed for use to detect the virus in infected brain tissue which we hope will transform international rabies diagnostic laboratories.”

References

• Amaya-Cuesta, J., et al. (2026). Deep learning enables rabies virus detection and antibody quantification in cell culture. Scientific Reports. DOI: 10.1038/s41598-026-57955-8.