Using advanced AI techniques to improve CT imaging evaluation
Adversarially Based Virtual CT Workflow for Evaluation of AI in Medical Imaging
This study is working on making AI better at reading medical images, like CT scans, so that patients can get more accurate and safer diagnoses.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Rensselaer Polytechnic Institute NIH-funded |
| Lab location | 1 site (Troy, United States) |
| Project ID | NIH-11045730 on NIH RePORTER |
What this research studies
This research focuses on enhancing the evaluation of artificial intelligence (AI) in medical imaging, specifically through the development of a virtual CT workflow. By generating diverse training datasets from low-dose CT scans and employing adversarial learning techniques, the project aims to address the challenges of algorithm bias and improve the robustness of AI systems. Patients may benefit from improved diagnostic accuracy and safety in medical imaging as AI technologies are refined and validated for clinical use.
Who could benefit from this research
Good fit: Ideal candidates for this research are individuals undergoing low-dose CT scans for diagnostic purposes.
Not a fit: Patients who do not require imaging or those who are not undergoing CT scans may not benefit from this research.
Why it matters
Potential benefit: If successful, this research could lead to more accurate and reliable AI applications in medical imaging, ultimately improving patient diagnosis and treatment.
How similar studies have performed: Other research has shown promise in using adversarial learning techniques to enhance AI performance in medical imaging, indicating that this approach could be effective.
Where this research is happening
Troy, United States
- Rensselaer Polytechnic Institute — Troy, United States (Active)
Researchers
- Principal investigator: Wang, Ge — Rensselaer Polytechnic Institute
- Study coordinator: Wang, Ge
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.