Explainable AI to help doctors detect abdominal cancers on scans
SCH: Visual explanation-guided learning for human-AI collaborative abdominal cancer diagnostic imaging
This project trains AI to highlight and explain suspicious areas on CT and MRI scans to help doctors find abdominal cancers earlier.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Emory University NIH-funded |
| Lab location | 1 site (Atlanta, United States) |
| Project ID | NIH-11172611 on NIH RePORTER |
What this research studies
If you participate, researchers will use your de-identified abdominal CT or MRI scans to train an AI that points out and visually explains suspicious regions. The AI will learn from doctor feedback so it improves even when there are few example scans. Clinicians will review the AI highlights and corrections so the system and doctors can work together to reduce missed small tumors. The team aims to make imaging results clearer, faster, and more trustworthy for patients and clinicians.
Who could benefit from this research
Good fit: Ideal candidates are people getting abdominal CT or MRI scans for symptoms, surveillance, or because they are at higher risk for abdominal cancers.
Not a fit: People without abdominal imaging, those with non-abdominal cancers, or patients whose disease is already clearly diagnosed and advanced are unlikely to benefit directly.
Why it matters
Potential benefit: If successful, this work could lead to earlier and more accurate detection of abdominal cancers by giving doctors clearer, explainable AI guidance.
How similar studies have performed: Explainable AI has shown encouraging results in medical imaging generally, but using visual-explanation guided learning specifically for abdominal cancer detection is relatively new.
Where this research is happening
Atlanta, United States
- Emory University — Atlanta, United States (Active)
Researchers
- Principal investigator: Zhao, Liang — Emory University
- Study coordinator: Zhao, Liang
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.