Smartphone AI to read thyroid biopsy slides in low-resource countries
Adapting a machine learning algorithm to predict thyroid cytopathologyin LMIC
This project trains a smartphone-based AI to help doctors in low- and middle-income countries identify whether thyroid biopsy samples are likely cancerous.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Duke University NIH-funded |
| Lab location | 1 site (Durham, United States) |
| Project ID | NIH-11176272 on NIH RePORTER |
What this research studies
You would have a photo taken of your thyroid fine-needle aspiration biopsy slide using a smartphone, and an artificial intelligence tool would give a probability that the sample is cancerous. The team will adapt their existing machine learning algorithm to work with smartphone images and partner with hospitals in Tanzania and Vietnam to implement the workflow. They will compare the AI's readings to those from trained cytopathologists and build local capacity to use the tool. The goal is faster, more accurate results where pathology services are scarce so fewer people undergo unnecessary surgery.
Who could benefit from this research
Good fit: People in low- and middle-income countries who have a thyroid nodule and are undergoing ultrasound-guided fine needle aspiration biopsy would be the ideal candidates.
Not a fit: Patients who already have access to expert local cytopathology or whose care does not depend on FNAB results are unlikely to benefit directly.
Why it matters
Potential benefit: If successful, this could provide faster, accurate biopsy readings in places without pathologists and reduce unnecessary thyroid surgeries.
How similar studies have performed: Machine learning models for pathology have shown promise in controlled settings, but using smartphone images for thyroid cytology in low-resource clinical settings is relatively new.
Where this research is happening
Durham, United States
- Duke University — Durham, United States (Active)
Researchers
- Principal investigator: Lee, Walter Tsong — Duke University
- Study coordinator: Lee, Walter Tsong
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.