AI tool to triage body CT scans
Computer-Aided Triage of Body CT Scans with Deep Learning
An artificial intelligence tool that flags likely important findings on chest, abdomen, and pelvis CT scans to help radiologists read scans faster and catch problems sooner.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Duke University NIH-funded |
| Lab location | 1 site (Durham, United States) |
| Project ID | NIH-11134540 on NIH RePORTER |
What this research studies
If you take part, researchers will gather and deidentify a large collection of chest, abdomen, and pelvis CT images and have experts mark areas with important findings. They will train deep-learning models to highlight regions with a high likelihood of actionable disease and use active learning to improve performance with less manual labeling. The team will build a triage interface that directs radiologists' attention to high-priority regions and run reader studies to compare speed and accuracy with and without the tool. The project also plans to share annotated data and tools to support wider testing and future clinical use.
Who could benefit from this research
Good fit: People who have clinical chest, abdominal, or pelvic CT scans (or who can allow their deidentified CT images to be included) are the ideal contributors to this work.
Not a fit: Patients needing imaging outside the chest/abdomen/pelvis or those whose scans are too low quality for reliable AI analysis may not benefit directly from this project.
Why it matters
Potential benefit: If successful, this could help patients get faster CT readouts and reduce missed or delayed diagnoses by focusing radiologist attention on the most important findings.
How similar studies have performed: Narrow AI tools for specific CT findings have shown promise, but broad triage across chest, abdomen, and pelvis using a single system is relatively novel.
Where this research is happening
Durham, United States
- Duke University — Durham, United States (Active)
Researchers
- Principal investigator: Lo, Joseph Y — Duke University
- Study coordinator: Lo, Joseph Y
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.