AI-powered urine test to detect bladder cancer from shed bladder cells
Official title: Noninvasive bladder cancer diagnostics via machine learning analysis of nanoscale surface images of epithelial cells extracted from voided urine samples
Funded at Tufts University Medford · NIH-11161161 · Data updated 2026-11-12
An AI-based urine test will use tiny surface images of bladder cells shed in urine to find bladder cancer and how aggressive it is in people at risk or under surveillance.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Tufts University Medford NIH-funded |
| Lab location | 1 site (Boston, UNITED STATES) |
| Project start | August 1, 2021 |
| Project end | July 31, 2026 |
| Funding year | 2025 |
| Award (this year) | $619,890 |
| NIH project number | 5R01CA262147-05 |
| Project ID | NIH-11161161 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates include adults with a history of bladder cancer under surveillance, people with blood in the urine, or those at elevated risk for bladder cancer.
✕Less likely to help
People who cannot provide voided urine samples, who have very low tumor cell shedding in urine, or who have non-bladder urinary tract cancers may not benefit from this test.
What this research studies
You would provide a routine voided urine sample and lab staff would collect the bladder epithelial cells that naturally slough off. Those individual cells are imaged at very high resolution to capture nanoscale surface features. Computer algorithms (machine learning) are trained to recognize patterns in those images that link to cancer presence and tumor grade. The team aims to make a fast, objective, noninvasive test that could reduce the number of follow-up cystoscopies.
Why it matters
Potential benefit: If successful, this could reduce the need for frequent invasive cystoscopy exams by providing an accurate, simple urine-based screening and monitoring option.
How similar studies have gone: Existing urine tests and cytology have had limited sensitivity and some AI approaches show promise, but combining nanoscale cell-surface imaging with machine learning is largely novel and experimental.
Where this research is happening
-
Tufts University Medford
Boston, United States Active
Researchers
- Principal investigator: Sokolov, Igor — Tufts University Medford
- Study coordinator: Sokolov, Igor
Related research
Other NIH-funded projects on the same topics.
-
Population modeling to reduce bladder cancer burden
Aimed at predicting and guiding effective, population-based ways to prevent and control bladder cancer.
-
Blocking a new immune checkpoint in bladder cancer
Researchers are trying medicines that block a newly found immune pathway to help people with bladder cancer, especially those whose tumors do not respond to current immunotherapy.
-
Nrf2 in T cells and how it could boost immune power against bladder cancer
A small grant will explore how a T-cell protein called Nrf2 affects muscle-invasive bladder cancer and whether targeting it could help patients respond better to immune therapies.
-
Understanding why bladder cancer spreads and resists treatment
This grant studies how advanced bladder cancer changes and spreads across the body, aiming to uncover why it’s hard to treat.
-
Molecular clues to bladder cancer cell changes and therapy response
This NIH grant looks at how bladder cancer cells change their identity and how that affects response to treatment, with a focus on aggressive neuroendocrine variants.
-
Repurposing spironolactone to treat bladder cancer inside the bladder
Aims to repurpose spironolactone as an intravesical treatment for non-muscle invasive bladder cancer to help prevent recurrence and progression.
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.