Smartphone AI to help read thyroid biopsy slides in low-resource countries
Adapting a machine learning algorithm to predict thyroid cytopathologyin LMIC
This project uses smartphone photos and artificial intelligence to help detect cancer from thyroid biopsy samples for patients in low- and middle-income countries.
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-11418152 on NIH RePORTER |
What this research studies
If you have a thyroid nodule, clinicians would take an ultrasound-guided fine-needle aspiration biopsy and have the cytology slide photographed with a smartphone. The research team will adapt an AI (machine learning) model to read those smartphone images and estimate the probability the sample is malignant. The AI readings will be compared with expert cytopathologists to refine the model and check accuracy. After that, the team will work with hospitals in Tanzania and Vietnam to build local capacity and implement the smartphone-AI workflow.
Who could benefit from this research
Good fit: Ideal candidates are people at participating tertiary hospitals who have thyroid nodules and are scheduled for ultrasound-guided fine-needle aspiration biopsy.
Not a fit: People without thyroid nodules, those not undergoing FNAB, those with inadequate biopsy samples, or patients treated outside the participating hospitals are unlikely to benefit directly.
Why it matters
Potential benefit: If successful, this could bring faster, more accurate biopsy readings to low-resource hospitals and help avoid many unnecessary surgeries.
How similar studies have performed: Some AI tools have shown promise matching pathologists on cytology tasks, but using smartphone photos and deploying these tools in low-resource settings is a newer and less-proven approach.
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.