Tuberculosis (TB) is a preventable and treatable bacterial infection that mainly affects the lungs. TB still causes around 1.3 million deaths each year and remains the second leading cause of death in sub-Saharan Africa. Many people with TB show no symptoms, making early detection difficult. In primary healthcare, the lack of appropriate diagnostic tools, such as chest X-rays and molecular tests, contributes to missed or delayed diagnoses. There is a great need for accessible, affordable and scalable tools to support TB diagnosis and management.
The CAD LUS4TB project builds on a novel AI-driven algorithm developed to interpret portable ultrasound images via smartphone, enabling healthcare workers to rule out TB and guide patient management quickly. With 3,000 adult patients in Benin, Mali and South Africa, CAD LUS4TB will evaluate this technology at the primary-care level, generating population-tailored evidence for integration into health policy.
The consortium is funded by Global Health EDCTP3 and includes the University of Stellenbosch in South Africa (SU), the Swiss Federal Technology Institute of Lausanne (EPFL) Laboratory for Intelligent Global Health and Humanitarian Technologies (LiGHT), the National Teaching Center for Pneumology & Tuberculosis in Benin (UAC), the University of Sciences of Mali (USSTB), the Swiss Centre Hospitalier Universitaire Vaudois (CHUV), the Swiss Tropical and Public Health Institute (Swiss TPH), the Institute of Tropical Medicine in Antwerp, Belgium (ITM), the Foundation for Innovative New Diagnostics (FIND) in Switzerland, and Butterfly Network, Inc (NYSE: BFLY) in the USA.
Assess the performance of expert- and AI-assisted lung ultrasound for TB screening across different primary care settings
Develop and refine image-analysis models tailored to lung ultrasound and mobile device use
Evaluate the barriers and facilitators for the uptake of AI-assisted lung ultrasound into routine healthcare, including its economic impact
Support research and clinical capabilities by implementing programmes with point-of-care ultrasound training and AI workshops
