AI-Powered Smartphone Microscopy for Changas Parasite Detection

09/09/2026

Researchers from the Information Processing and Telecommunications Center (IPTC) from the Universidad Politécnica de Madrid (UPM) have contributed to the development of an artificial intelligence system capable of detecting and counting Trypanosoma cruzi parasites in real time using smartphone microscopy.

The study presents a portable, low-cost approach that combines a conventional optical microscope with a smartphone through a 3D-printed adapter, a telemedicine platform and lightweight AI models designed to run directly on mobile devices. The system was trained and evaluated using human blood and cerebrospinal fluid samples, as well as mice blood samples, covering different imaging conditions.

Among the models evaluated, SSD-MobileNetV2 achieved particularly strong results on human samples, with 86% precision, 87% recall and an F1-score of 86.5%. Its approximately 350-millisecond inference time on a smartphone demonstrates its potential for real-time analysis. In a laboratory pilot under operational conditions, the system achieved 96.4% recall, indicating its potential as a screening tool with human supervision.

The research could have important applications in the diagnosis and monitoring of Chagas disease, particularly in endemic and resource-limited regions where access to specialized equipment, connectivity and trained personnel may be limited. By providing rapid AI-assisted parasite detection directly at the point of care, the technology could help reduce diagnostic delays and support healthcare professionals. It could also facilitate parasite quantification in research and drug-development studies, where automated counting can provide faster and more consistent measurements of parasite burden.

The modular approach could ultimately be adapted to detect other pathogens and cellular structures, opening the door to broader AI-assisted microscopy applications in neglected tropical diseases.

🔬 Collaboration Statement

This research has been a collaboration between the Biomedical Image Technologies group at UPM, Spotlab, the CIBER in Bioengineering, Biomaterials and Nanomedicine, the Instituto de Salud Carlos III, the Facultad de Medicina at Universidad Mayor de San Simón (Cochabamba, Bolivia), the National Centre for Microbiology at Instituto de Salud Carlos III, the Centro de Investigación Biomédica en Red de Enfermedades Infecciosas (CIBERINFEC) at Instituto de Salud Carlos III, and the Fundación Mundo Sano.

Bibliograhic reference:

Lin L., Solano A.V., Gonzales F., Torrico, M.C., Illanes D., Díez N., et al. (2026) Artificial intelligence algorithm for real-time detection and counting of Trypanosoma cruzi parasites using smartphone microscopy. PLoS Negl TropDis 20(5): e0012955. https://doi.org/10.1371/journal.pntd.0012955

María Jesús Ledesma Carbayo: GS / ORCID / LinkedIn

Original source: UPM. Noticias de Investigación: https://short.upm.es/4fcw1

Authors of the image: SpotLab and Mary Cruz Torrico.